stanford-core-nlp 0.3.2 → 0.3.4

data/README.md

@@ -1,5 +1,3 @@
-[![Build Status](https://secure.travis-ci.org/louismullie/stanford-core-nlp.png)](http://travis-ci.org/louismullie/stanford-core-nlp)
-
 **About**
   
 This gem provides high-level Ruby bindings to the [Stanford Core NLP package](http://nlp.stanford.edu/software/corenlp.shtml), a set natural language processing tools for tokenization, part-of-speech tagging, lemmatization, and parsing of several languages, as well as named entity recognition and coreference resolution in English. This gem is compatible with Ruby 1.9.2 and above.
@@ -8,6 +6,8 @@ If you are looking for an full-scale natural language processing framework in Ru
 
 **Installing**
 
+_Note: This gem uses the Ruby-Java Bridge (Rjb), which currently does not support Java 7. Therefore, if you have installed Java 7, you should set your JAVA_HOME to point to your old Java 6 install before installing Rjb; for example, `export "JAVA_HOME=/usr/lib/jvm/java-6-openjdk/"`._
+
 First, install the gem: `gem install stanford-core-nlp`. Then, download the Stanford Core NLP JAR and model files. Three different packages are available:
 
 * A [minimal package for English](http://louismullie.com/treat/stanford-core-nlp-minimal.zip) with one tagger model  and one parser model for English.

data/bin/AnnotationBridge.java

@@ -0,0 +1,12 @@
+import edu.stanford.nlp.ling.CoreAnnotation;
+import edu.stanford.nlp.util.ArrayCoreMap;
+
+public class AnnotationBridge {
+    
+    public static Object getAnnotation(Object entity, String name) throws ClassNotFoundException {
+    	Class<CoreAnnotation> klass;
+    	klass = (Class<CoreAnnotation>) Class.forName(name);
+    	Object object = ((ArrayCoreMap) entity).get(klass);
+		return object;
+    }
+}

data/bin/Stanford.java

@@ -0,0 +1,13 @@
+import edu.stanford.nlp.ling.CoreAnnotation;
+import edu.stanford.nlp.ling.CoreLabel;
+
+public class Stanford {
+    
+    public static Object getAnnotation(CoreLabel entity, String name) throws ClassNotFoundException{
+    	Class<CoreAnnotation> klass;
+    	klass = (Class<CoreAnnotation>) Class.forName(name);
+    	Object object = entity.get(klass);
+		return object;
+    }
+
+}

data/lib/stanford-core-nlp.rb

@@ -1,6 +1,6 @@
 module StanfordCoreNLP
 
-  VERSION = '0.3.2'
+  VERSION = '0.3.4'
 
   require 'bind-it'
   extend BindIt::Binding
@@ -12,7 +12,7 @@ module StanfordCoreNLP
   # The default path for the JAR files 
   # is the gem's bin folder.
   self.jar_path = File.dirname(__FILE__).
-  gsub('/lib', '') + '/bin/'
+  gsub(/\/lib\z/, '') + '/bin/'
   
   # Load the JVM with a minimum heap size of 512MB,
   # and a maximum heap size of 1024MB.
@@ -94,7 +94,7 @@ module StanfordCoreNLP
   end
 
   # Use english by default.
-  self.use(:english)
+  self.use :english
 
   # Set a model file. 
   def self.set_model(name, file)
@@ -135,10 +135,11 @@ module StanfordCoreNLP
       properties[k] = f
     end
 
-    # Bug fix for French parser due to Stanford bug
+    # Bug fix for French/German parser due to Stanford bug.
     # Otherwise throws IllegalArgumentException: 
     # Unknown option: -retainTmpSubcategories
-    if self.language == :french
+    if self.language == :french ||
+       self.language == :german
       properties['parser.flags'] = ''
     end
     

data/lib/stanford-core-nlp/config.rb

@@ -9,8 +9,7 @@ module StanfordCoreNLP
       :german => [:de, :ger, :german],
       :french => [:fr, :fre, :french],
       :arabic => [:ar, :ara, :arabic],
-      :chinese => [:ch, :chi, :chinese],
-      :xinhua => [:xi, :xin, :xinhua]
+      :chinese => [:ch, :chi, :chinese]
     }
 
     # Folders inside the JAR path for the models.
@@ -37,8 +36,7 @@ module StanfordCoreNLP
         :german => 'german-fast.tagger',
         :french  => 'french.tagger',
         :arabic => 'arabic-fast.tagger',
-        :chinese  => 'chinese.tagger',
-        :xinhua   => nil
+        :chinese  => 'chinese.tagger'
       },
       
       :parser => {
@@ -46,8 +44,7 @@ module StanfordCoreNLP
         :german => 'germanPCFG.ser.gz',
         :french  => 'frenchFactored.ser.gz',
         :arabic => 'arabicFactored.ser.gz',
-        :chinese  => 'chinesePCFG.ser.gz',
-        :xinhua   => 'xinhuaPCFG.ser.gz'
+        :chinese  => 'chinesePCFG.ser.gz'
       },
       
       :ner => {
@@ -59,8 +56,7 @@ module StanfordCoreNLP
         :german => {},
         :french  => {},
         :arabic => {},
-        :chinese  => {},
-        :xinhua   => {}
+        :chinese  => {}
       },
       
       :dcoref => {
@@ -74,15 +70,14 @@ module StanfordCoreNLP
           'plural' => 'plural.unigrams.txt',
           'singular' => 'singular.unigrams.txt',
           'states' => 'state-abbreviations.txt',
-          'countries' => 'unknown.txt',          # Fix - can somebody provide this file?
-          'states.provinces' => 'unknown.txt',   # Fix - can somebody provide this file?
+          'countries' => 'countries', 
+          'states.provinces' => 'statesandprovinces',
           'extra.gender' => 'namegender.combine.txt'
         },
         :german => {},
         :french  => {},
         :arabic => {},
-        :chinese  => {},
-        :xinhua   => {}
+        :chinese  => {}
       }
       
       # Models to add.

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: stanford-core-nlp
 version: !ruby/object:Gem::Version
-  version: 0.3.2
+  version: 0.3.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-05-15 00:00:00.000000000 Z
+date: 2012-12-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bind-it
@@ -40,7 +40,9 @@ files:
 - lib/stanford-core-nlp/bridge.rb
 - lib/stanford-core-nlp/config.rb
 - lib/stanford-core-nlp.rb
+- bin/AnnotationBridge.java
 - bin/bridge.jar
+- bin/Stanford.java
 - README.md
 - LICENSE
 homepage: https://github.com/louismullie/stanford-core-nlp
@@ -63,7 +65,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.21
+rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Ruby bindings to the Stanford Core NLP tools.