crosslanguagespotter 0.0.2-java → 0.0.3-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 68ee2d427d4dacc3d22b88a1deababeb2a1bcafd
-  data.tar.gz: 65ab29b3ba450f824a4930bd0a436170efabff57
+  metadata.gz: 7bd48f663e7200f5f464a495489c908d32add844
+  data.tar.gz: 96639998deb60e876be968f12a5aad253fe178a2
 SHA512:
-  metadata.gz: ec2f763115ece653ad3a1379f24397bd73e18f3d4d101b222a922fead038bb4498459319595ac86444e253176b66ca9ebe93f117632293f879ee1bbf2f348cb8
-  data.tar.gz: d7b1571637ec59db6e9519e035c4826fecde7d121b2e8f03898317f4eaf3cc237bb9253833f4f90357fa604fb1c0b31cfb9b1b27b496218b3066aa3034d4fae8
+  metadata.gz: b23e0d417a6e221563ef5d949f3d44e3966870d4990a96c6df152de8ce401742718d849737024e0a2e570da481b5fd6a3c63096c077d0f539b5cfe6168b1c1a5
+  data.tar.gz: 229df49be5b9ae4d781818baf3c56cb862063e7f8d48bf585fc5e494b9dfd28c171bf3066cc1e770a2ec41a3846bf335a391e64ce600a5f945adc2a64656816d

data/Rakefile

@@ -1,5 +1,6 @@
 require 'rake/testtask'
 require 'rubygems/tasks'
+require 'rubygems/package_task'
 
 Rake::TestTask.new do |t|
   t.libs << 'test'

data/lib/crosslanguagespotter/basic.rb

@@ -67,11 +67,14 @@ module CrossLanguageSpotter
                 context: :numeric,jaccard: :numeric,jaro: :numeric,tversky: :numeric,
                 result: :boolean}
             data_instances = hash2weka_instances("data",data,keys,:result)
+            puts "ARFF DATA BEFORE {{{\n#{data_instances}\n}}}"
             classification = classifier.classify(data_instances)
+            puts "ARFF DATA AFTER {{{\n#{data_instances}\n}}}"
 
             i=0
             results = []
             classification.each do |c|                
+                puts "CLASSIFICATION #{c}"
                 if c[:result]
                     # just put a true in the real relations
                     list_of_original_features_rows[i][:result] = true

data/lib/crosslanguagespotter/model_loading.rb

@@ -7,7 +7,6 @@ module CrossLanguageSpotter
 
 AngularParser = CodeModels::Html::AngularJs.parser_considering_angular_embedded_code
 
-
 def traverse_index(node)
     root = node.root(:also_foreign)
     i = 1

data/lib/crosslanguagespotter/oracle.rb

@@ -3,8 +3,6 @@ require 'codemodels/js'
 require 'codemodels/html'
 require 'csv'
 require 'crosslanguagespotter/model_loading'
-#require 'console'
-#require 'code_processing'
 
 include CodeModels
 
@@ -41,6 +39,7 @@ class OracleLoader
         WekaClassifier.new(train_instances)
     end
 
+    # TODO Make it private
     def to_train_data(srcpath,oraclepath)
         project = Project.new(srcpath)
 
@@ -76,19 +75,6 @@ class OracleLoader
                 line_b         = values[5].to_i
                 col_b          = values[6].to_i         
                 surface_form_b = values[7]
-                #if values[8]=='t'
-                #    result = true
-                #elsif values[8]=='f'
-                #    result = false
-                #else
-                #    raise "Exptected true or false"
-                #end
-
-                #if oracle_values.values.include?([end_a,end_b])
-                #    raise "Line #{l+1} is a duplicate of line #{oracle_values.find {|k,v| v==[end_a,end_b]}}"
-                #else
-                #    oracle_values[l] = [end_a,end_b]
-                #end             
 
                 file_a = "#{srcpath}/#{file_a}"
                 file_b = "#{srcpath}/#{file_b}"
@@ -163,16 +149,6 @@ class OracleLoader
             end
         end
 
-        pos = 0
-        neg = 0
-        train_data.each do |k,v|
-            if v[:result]
-                pos+=1
-                #puts v
-            else
-                neg+=1
-            end
-        end
         return train_data
     end
 
@@ -221,7 +197,6 @@ class OracleLoader
             unless smallest_candidate
                 puts "I did not find exactly once '#{surface_form}' at #{position}. I found it there #{candidates_in_correct_position.count} times (found elsewhere #{candidates_in_other_positions.count} times)"
 
-
                 candidates_in_other_positions.each do |wp|
                     puts " * #{wp.source.position(:absolute)}"
                 end

data/lib/crosslanguagespotter/report.rb

@@ -46,9 +46,7 @@ def _code(files_content,filename,begin_line,end_line,begin_col,end_col)
         code += HTMLEntities.new.encode(l,:decimal)
     end
     snippet_lines[:lines].each do |l|
-        #l = l.gsub("\t",'    ')
         code += HTMLEntities.new.encode(l[0...(begin_col-1)],:decimal)
-        puts "<<<#{l[(begin_col-1)...end_col]}>>>"
         code += '<span style="background-color:yellow;padding:2px">'+HTMLEntities.new.encode(l[(begin_col-1)...end_col],:decimal)+"</span>"
         code += HTMLEntities.new.encode(l[end_col..-1],:decimal)
     end

data/lib/crosslanguagespotter/version.rb

@@ -1,5 +1,5 @@
 # encoding: utf-8
 
 module CrossLanguageSpotter
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/lib/crosslanguagespotter/wekaintegration.rb

@@ -2,6 +2,9 @@ require 'java'
 
 module CrossLanguageSpotter
 
+# Initialize a RandomTree classifier using the given
+# instances
+# TODO make it a private method of WekaClassifier
 def build_classifier(training_instances)
     c = Java::weka::classifiers::trees::RandomTree.new
     c.build_classifier(training_instances)
@@ -19,7 +22,7 @@ class WekaClassifier
         data_instances.enumerate_instances.each do |instance|
             #puts "Classifying #{instance}"
             r = @weka_classifier.classify_instance(instance)
-            #puts "Result: #{r} #{instance}"
+            puts "Result: #{r} #{instance}"
             results.push({result: r==0.0, instance: instance})
         end
         return results
@@ -27,6 +30,7 @@ class WekaClassifier
 
 end
 
+# TODO: make it a private method of WekaClassifier
 def hash2weka_instances(name,data,keys,class_value)
     boolean_values = Java::weka::core::FastVector.new
     boolean_values.add_element("true")
@@ -72,6 +76,7 @@ def hash2weka_instances(name,data,keys,class_value)
     end
 
     if class_value
+        puts "Setting classIndex #{attributes_indexes[class_value]}"
         instances.setClassIndex(attributes_indexes[class_value])
     end
 

data/resources/services_example.html

@@ -22,106 +22,6 @@
     <div class="container">
       <h1> Cross Language Relations - Console Log</h1>
       
-      <div class="row text-left">
-        <div class="col-md-6">
-          <h2> ./test/data/services/index.html</h2>
-          <pre>
-            <code class="language-html"}}>
-                  &#60;body&#62;&#10;&#10;        &#60;form id=&#34;main&#34; ng-app ng-controller=&#34;myservices&#34;&#62;&#10;            &#60;h1&#62;My Services&#60;/h1&#62;&#10;&#10;            &#60;ul <span style="background-color:yellow;padding:2px">id=&#34;services&#34;&#62;</span>&#10;                &#60;!-- The services will be inserted here --&#62;&#10;                &#60;li ng-repeat=&#34;service in services&#34;&#62;&#10;                &#60;/li&#62;&#10;            &#60;/ul&#62;
-            </code>
-          </pre>
-          <!-- &ltp&gt<span style="color:red">TEST</span>&lt/p&gt -->
-        </div>
-        <div class="col-md-6">
-          <h2> ./test/data/services/script.js</h2>
-          <pre>
-            <code class="language-javascript">
-              function myservices($scope){&#10;    $scope.<span style="background-color:yellow;padding:2px">services</span>=[&#10;        { title: &#39;web development&#39;, price: 200},&#10;        { title: &#39;web design&#39;, price: 250},&#10;        { title: &#39;photography&#39;, price: 100},&#10;        { title: &#39;coffee drinking&#39;, price: 10}];&#10;    $scope.total=function(){
-            </code>
-          </pre>
-        </div>
-      </div> <!-- end row -->
-      
-      <div class="row text-left">
-        <div class="col-md-6">
-          <h2> ./test/data/services/index.html</h2>
-          <pre>
-            <code class="language-html"}}>
-                  &#60;body&#62;&#10;&#10;        &#60;form id=&#34;main&#34; ng-app ng-controller=&#34;myservices&#34;&#62;&#10;            &#60;h1&#62;My Services&#60;/h1&#62;&#10;&#10;            &#60;ul <span style="background-color:yellow;padding:2px">id=&#34;services&#34;&#62;</span>&#10;                &#60;!-- The services will be inserted here --&#62;&#10;                &#60;li ng-repeat=&#34;service in services&#34;&#62;&#10;                &#60;/li&#62;&#10;            &#60;/ul&#62;
-            </code>
-          </pre>
-          <!-- &ltp&gt<span style="color:red">TEST</span>&lt/p&gt -->
-        </div>
-        <div class="col-md-6">
-          <h2> ./test/data/services/script.js</h2>
-          <pre>
-            <code class="language-javascript">
-                  { title: &#39;web design&#39;, price: 250},&#10;    { title: &#39;photography&#39;, price: 100},&#10;    { title: &#39;coffee drinking&#39;, price: 10}];&#10;$scope.total=function(){&#10;    var t = 0;&#10;    angular.forEach($scope.<span style="background-color:yellow;padding:2px">services</span>, function(s){&#10;        if(s.selected)&#10;            t+=s.price;&#10;    });&#10;    return t;&#10;};
-            </code>
-          </pre>
-        </div>
-      </div> <!-- end row -->
-      
-      <div class="row text-left">
-        <div class="col-md-6">
-          <h2> ./test/data/services/index.html</h2>
-          <pre>
-            <code class="language-html"}}>
-                      &#60;form id=&#34;main&#34; ng-app ng-controller=&#34;myservices&#34;&#62;&#10;            &#60;h1&#62;My Services&#60;/h1&#62;&#10;&#10;            &#60;ul id=&#34;services&#34;&#62;&#10;                &#60;!-- The services will be inserted here --&#62;&#10;                &#60;li ng-repeat=&#34;service in <span style="background-color:yellow;padding:2px">services</span>&#34;&#62;&#10;                &#60;/li&#62;&#10;            &#60;/ul&#62;&#10;&#10;            &#60;p id=&#34;total&#34;&#62;total: &#60;span&#62;${{total()}}&#60;/span&#62;&#60;/p&#62;
-            </code>
-          </pre>
-          <!-- &ltp&gt<span style="color:red">TEST</span>&lt/p&gt -->
-        </div>
-        <div class="col-md-6">
-          <h2> ./test/data/services/script.js</h2>
-          <pre>
-            <code class="language-javascript">
-              function myservices($scope){&#10;    $scope.<span style="background-color:yellow;padding:2px">services</span>=[&#10;        { title: &#39;web development&#39;, price: 200},&#10;        { title: &#39;web design&#39;, price: 250},&#10;        { title: &#39;photography&#39;, price: 100},&#10;        { title: &#39;coffee drinking&#39;, price: 10}];&#10;    $scope.total=function(){
-            </code>
-          </pre>
-        </div>
-      </div> <!-- end row -->
-      
-      <div class="row text-left">
-        <div class="col-md-6">
-          <h2> ./test/data/services/index.html</h2>
-          <pre>
-            <code class="language-html"}}>
-                              &#60;!-- The services will be inserted here --&#62;&#10;                &#60;li ng-repeat=&#34;service in services&#34;&#62;&#10;                &#60;/li&#62;&#10;            &#60;/ul&#62;&#10;&#10;            &#60;p <span style="background-color:yellow;padding:2px">id=&#34;total&#34;&#62;</span>total: &#60;span&#62;${{total()}}&#60;/span&#62;&#60;/p&#62;&#10;&#10;            &#60;input type=&#34;submit&#34; id=&#34;order&#34; value=&#34;Order&#34;/&#62;&#10;&#10;        &#60;/form&#62;
-            </code>
-          </pre>
-          <!-- &ltp&gt<span style="color:red">TEST</span>&lt/p&gt -->
-        </div>
-        <div class="col-md-6">
-          <h2> ./test/data/services/script.js</h2>
-          <pre>
-            <code class="language-javascript">
-              $scope.services=[&#10;    { title: &#39;web development&#39;, price: 200},&#10;    { title: &#39;web design&#39;, price: 250},&#10;    { title: &#39;photography&#39;, price: 100},&#10;    { title: &#39;coffee drinking&#39;, price: 10}];&#10;$scope.<span style="background-color:yellow;padding:2px">total</span>=function(){&#10;    var t = 0;&#10;    angular.forEach($scope.services, function(s){&#10;        if(s.selected)&#10;            t+=s.price;&#10;    });
-            </code>
-          </pre>
-        </div>
-      </div> <!-- end row -->
-      
-      <div class="row text-left">
-        <div class="col-md-6">
-          <h2> ./test/data/services/index.html</h2>
-          <pre>
-            <code class="language-html"}}>
-                              &#60;!-- The services will be inserted here --&#62;&#10;                &#60;li ng-repeat=&#34;service in services&#34;&#62;&#10;                &#60;/li&#62;&#10;            &#60;/ul&#62;&#10;&#10;            &#60;p id=&#34;total&#34;&#62;total: &#60;span&#62;${{<span style="background-color:yellow;padding:2px">total</span>()}}&#60;/span&#62;&#60;/p&#62;&#10;&#10;            &#60;input type=&#34;submit&#34; id=&#34;order&#34; value=&#34;Order&#34;/&#62;&#10;&#10;        &#60;/form&#62;
-            </code>
-          </pre>
-          <!-- &ltp&gt<span style="color:red">TEST</span>&lt/p&gt -->
-        </div>
-        <div class="col-md-6">
-          <h2> ./test/data/services/script.js</h2>
-          <pre>
-            <code class="language-javascript">
-              $scope.services=[&#10;    { title: &#39;web development&#39;, price: 200},&#10;    { title: &#39;web design&#39;, price: 250},&#10;    { title: &#39;photography&#39;, price: 100},&#10;    { title: &#39;coffee drinking&#39;, price: 10}];&#10;$scope.<span style="background-color:yellow;padding:2px">total</span>=function(){&#10;    var t = 0;&#10;    angular.forEach($scope.services, function(s){&#10;        if(s.selected)&#10;            t+=s.price;&#10;    });
-            </code>
-          </pre>
-        </div>
-      </div> <!-- end row -->
-      
     </div>
 
     <!-- jQuery (necessary for Bootstrap's JavaScript plugins) -->

data/test/test_figures.rb

@@ -0,0 +1,15 @@
+require 'test_helper'
+
+class TestFigures < Test::Unit::TestCase
+
+def setup
+end
+
+def test_jaccard_best_match
+	a = [1, 2, 3]
+	b = [1, 2]
+	c = [1, 3]
+	assert_equal([[1, 2, 3], [1, 2]], Jaccard.best_match([a, b, c]) )
+end
+
+end

metadata

@@ -1,204 +1,204 @@
 --- !ruby/object:Gem::Specification
 name: crosslanguagespotter
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
 platform: java
 authors:
 - Federico Tomassetti
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
 date: 2014-03-31 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: codemodels
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-js
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-js
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-html
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-html
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-java
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-java
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-ruby
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-ruby
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-xml
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-xml
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: codemodels-properties
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: codemodels-properties
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: htmlentities
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: htmlentities
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: liquid
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: liquid
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
   prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: bundler
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rake
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: simplecov
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: simplecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rubygems-tasks
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rubygems-tasks
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
+  type: :development
 description: Automatic Spotter of Cross-Language references
 email: f.tomassetti@gmail.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
-- ".gitignore"
+- .gitignore
 - Gemfile
 - Rakefile
 - crosslanguagespotter.gemspec
@@ -284,6 +284,7 @@ files:
 - test/data/example.js
 - test/data/services/index.html
 - test/data/services/script.js
+- test/test_figures.rb
 - test/test_helper.rb
 - test/test_parsing.rb
 - test/test_spotter.rb
@@ -292,24 +293,24 @@ homepage: https://github.com/CrossLanguageProject/crosslanguagerelationsspotter
 licenses:
 - Apache v2
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
+rubyforge_project:
 rubygems_version: 2.2.2
-signing_key: 
+signing_key:
 specification_version: 4
 summary: Automatic Spotter of Cross-Language references
 test_files:
@@ -322,6 +323,7 @@ test_files:
 - test/data/example.js
 - test/data/services/index.html
 - test/data/services/script.js
+- test/test_figures.rb
 - test/test_helper.rb
 - test/test_parsing.rb
 - test/test_spotter.rb