treat 2.0.5 → 2.0.6

data/lib/treat/loaders/open_nlp.rb

@@ -3,9 +3,8 @@ require 'treat/loaders/bind_it'
 # A helper class to load the OpenNLP package.
 class Treat::Loaders::OpenNLP < Treat::Loaders::BindIt
   
-  require 'open-nlp'
-  
   def self.load(language = nil)
+    require 'open-nlp'
     super(OpenNLP, :open_nlp, language)
   end
 

data/lib/treat/loaders/stanford.rb

@@ -3,9 +3,8 @@ require 'treat/loaders/bind_it'
 # A helper class to load the CoreNLP package.
 class Treat::Loaders::Stanford < Treat::Loaders::BindIt
   
-  require 'stanford-core-nlp'
-  
   def self.load(language = nil)
+    require 'stanford-core-nlp'
     super(StanfordCoreNLP, :stanford, language)
   end
 

data/lib/treat/version.rb

@@ -1,7 +1,7 @@
 module Treat
   
   # The current version of Treat.
-  VERSION = "2.0.5"
+  VERSION = '2.0.6'
   
   # Treat requires Ruby >= 1.9.2
   if RUBY_VERSION < '1.9.2'

data/lib/treat/workers/lexicalizers/taggers/stanford.rb

@@ -48,7 +48,7 @@ class Treat::Workers::Lexicalizers::Taggers::Stanford
     isolated_token = entity.is_a?(Treat::Entities::Token)
 
     @@taggers[lang].apply(t_list).each do |tok|
-      tokens[i].set(:tag, tok.tag)
+      tokens[i].set(:tag, tok.tag.split('-').first)
       tokens[i].set(:tag_set,
       options[:tag_set]) if isolated_token
       return tok.tag if isolated_token

data/lib/treat/workers/processors/segmenters/stanford.rb

@@ -4,8 +4,6 @@
 # obtained tokens are then grouped into sentences.
 class Treat::Workers::Processors::Segmenters::Stanford
 
-  Treat::Loaders::Stanford.load
-  
   DefaultOptions = {
     :also_tokenize => false
   }
@@ -25,6 +23,8 @@ class Treat::Workers::Processors::Segmenters::Stanford
   # add the tokens as children of the sentence.
   def self.segment(entity, options = {})
 
+    Treat::Loaders::Stanford.load
+
     options = DefaultOptions.merge(options)
     entity.check_hasnt_children
 

data/lib/treat/workers/processors/tokenizers/open_nlp.rb

@@ -1,14 +1,13 @@
 # Maximum entropy tokenization supplied by OpenNLP.
 class Treat::Workers::Processors::Tokenizers::OpenNlp
-
-  require 'open-nlp'
-  Treat::Loaders::OpenNLP.load
   
   @@tokenizers = {}
   
   # Maximum entropy tokenization.
   def self.tokenize(entity, options = {})
     
+    Treat::Loaders::OpenNLP.load
+    
     lang = entity.language
     str = entity.to_s
     

data/lib/treat/workers/processors/tokenizers/stanford.rb

@@ -7,8 +7,6 @@
 # single forward- and backward- quotes (`` and '') by default.
 class Treat::Workers::Processors::Tokenizers::Stanford
 
-  Treat::Loaders::Stanford.load
-  
   # Default options for the tokenizer.
   DefaultOptions = {
     directional_quotes: false,
@@ -26,6 +24,7 @@ class Treat::Workers::Processors::Tokenizers::Stanford
   # to attempt to get correct directional quotes,
   # replacing "..." by ``...''. Off by default.
   def self.tokenize(entity, options = {})
+    Treat::Loaders::Stanford.load
     options = DefaultOptions.merge(options)
     @@tokenizer ||= StanfordCoreNLP.load(:tokenize)
     entity.check_hasnt_children

data/spec/sandbox.rb

@@ -18,8 +18,11 @@ Treat.core.verbosity.silence = false
 
 include Treat::Core::DSL
 
-s = sentence "This is a sentence to parse!"
-s.tokenize(:open_nlp).parse
+Treat.core.language.default = 'german' 
+Treat.core.verbosity.debug
+
+s = sentence 'Der wilde Kerl lebte in einem gelben Haus.'
+s.do(:tokenize, :tag => :stanford, :parse => :stanford)
 s.print_tree
 
 =begin

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: treat
 version: !ruby/object:Gem::Version
-  version: 2.0.5
+  version: 2.0.6
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-03 00:00:00.000000000 Z
+date: 2013-06-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: schiphol