luisparravicini-classifier 1.4.0 → 1.4.1

data/README.rdoc

@@ -41,10 +41,10 @@ You can specify language and encoding for internal stemmer:
 	  b = Classifier::Bayes.new :categories => ['Interesting', 'Uninteresting'],
       :language => 'ro', :encoding => 'ISO_8859_2'
 
-The default values are 'en' for language and 'UTF-8' for the encoding.
+The default values are 'en' for language and 'UTF_8' for the encoding. The encoding name must have underscores instead of hyphens (i.e.: UTF_8 instead of UTF-8).
 
 Each language uses a word list to exclude certain words (stopwords). classifier comes with three included stopword lists, for English, Russian and Spanish.
-The English list is the list that comes with the original gem (don't know where it was taken from) and the Russian and Spanish are from snowball[http://snowball.tartarus.org/algorithms/].
+The English list is the one that comes with the original gem (don't know where it was taken from) and the Russian and Spanish are from snowball[http://snowball.tartarus.org/algorithms/].
 
 You can override the default stopword list, or add lists for new languages sending a value for :lang_dir when initializing Bayes:
 
@@ -55,6 +55,19 @@ This directory is used when loading the list from disk and takes precedence over
 
 The stopwords file can have comments (indicated with '#'), blank lines are ignored and the encoding must be utf-8.
 
+=== A warning about classifier serialization
+If you serialize a classifier and then deserialize it in another process, you need to be careful that the stemmer is reinitialized
+the next time you want to use it. Here is an example using ActiveRecord:
+
+    class User < ActiveRecord::Base
+      serialize :classifier, Classifier::Bayes
+      before_save :remove_stemmer
+
+      def remove_stemmer
+        self.classifier.remove_stemmer
+      end
+    end
+
 === Bayesian Classification
 
 * http://www.process.com/precisemail/bayesian_filtering.htm

data/VERSION.yml

@@ -1,5 +1,5 @@
 --- 
+:build: 
+:patch: 1
 :major: 1
 :minor: 4
-:patch: 0
-:build: 

data/lib/classifier.rb

@@ -24,7 +24,7 @@
 # Copyright:: Copyright (c) 2005 Lucas Carlson
 # License::   LGPL
 
-require 'activesupport'
+require 'active_support'
 require 'lingua/stemmer'
 require 'classifier/base'
 require 'classifier/bayes'

data/lib/classifier/base.rb

@@ -31,6 +31,15 @@ module Classifier
   	def clean_word_hash str
   		word_hash_for_words str.gsub(/[^\w\s]/,"").split
   	end
+
+    # When a Classifier instance is serialized, it is saved with an instance
+    # of Lingua::Stemmer that may not be initialized when deserialized later,
+    # raising a "RuntimeError: Stemmer is not initialized".
+    #
+    # You can run remove_stemmer to force a new Stemmer to be initialized.
+    def remove_stemmer
+      @stemmer = nil
+    end
   	
   	private 
   	

data/luisparravicini-classifier.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{luisparravicini-classifier}
-  s.version = "1.4.0"
+  s.version = "1.4.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Luis Parravicini"]
-  s.date = %q{2009-12-26}
+  s.date = %q{2010-01-29}
   s.description = %q{Bayesian classifier and others.}
   s.email = %q{lparravi@gmail.com}
   s.extra_rdoc_files = [
@@ -37,6 +37,7 @@ Gem::Specification.new do |s|
      "lib/classifier/stopwords/ru",
      "lib/init.rb",
      "luisparravicini-classifier.gemspec",
+     "pkg/luisparravicini-classifier-1.4.0.gem",
      "tasks/test.rake",
      "test/base_test.rb",
      "test/bayes/bayesian_test.rb",

data/test/bayes/bayesian_test.rb

@@ -1,7 +1,7 @@
 # coding:utf-8
-$KCODE = 'utf8'
 
 require File.dirname(__FILE__) + '/../test_helper'
+
 class BayesianTest < Test::Unit::TestCase
 	def setup
 		@classifier = Classifier::Bayes.new :categories => ['Interesting', 'Uninteresting']
@@ -58,11 +58,11 @@ class BayesianTest < Test::Unit::TestCase
 
   def test_serialize
     txt = "this can be serialized"
-    b = Classifier::Bayes.new(:categories => ['Interesting', 'Uninteresting'])
-    b.train_interesting(txt)
-    b.train_uninteresting("really uninteresting")
+    @classifier.train_interesting(txt)
+    @classifier.train_uninteresting("really uninteresting")
 
-    b2 = Marshal::load(Marshal::dump(b))
-    assert_equal b.classify(txt), b2.classify(txt)
+    b2 = Marshal::load(Marshal::dump(@classifier))
+    assert_equal @classifier.classify(txt), b2.classify(txt)
   end
+
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: luisparravicini-classifier
 version: !ruby/object:Gem::Version 
-  version: 1.4.0
+  version: 1.4.1
 platform: ruby
 authors: 
 - Luis Parravicini
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-12-26 00:00:00 -02:00
+date: 2010-01-29 00:00:00 -02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -62,6 +62,7 @@ files:
 - lib/classifier/stopwords/ru
 - lib/init.rb
 - luisparravicini-classifier.gemspec
+- pkg/luisparravicini-classifier-1.4.0.gem
 - tasks/test.rake
 - test/base_test.rb
 - test/bayes/bayesian_test.rb