sem_extractor 0.0.2 → 0.0.3

data/README.rdoc

@@ -6,36 +6,36 @@ SemExtractor is made to have in a single place, wrappers for most of the semanti
 - Yahoo Boss
 - OpenCalais
 
-= H2 Please tell me if there are more API's to include!
+Please tell me if there are more API's to include!
 
 <em>After using Term Extraction gem, I happened to need the score of the different tags I got from the different APIS + I wanted to use Nokogiri for performance concerns.
 I thank alexrabarts, because his work gave me the idea to create my first gem</em>
 
 == Installation
 
-To install (I strongly recommend you use RVM):
-gem install sem_extractor
+	gem install sem_extractor
 
 
-== Usage
+== Examples
+For sure, you'll have to request your own API Key for each kind of API you want to use.
 Most of the methods below retrieve a hash with 'name' and 'score'
 
-Initialize:
-- yahoo = SemExtractor::Yahoo.new(:api_key => your_key, :context => your_text)
-- zemanta = SemExtractor::Zemanta.new(:api_key => your_key, :context => your_text)
-- sem = SemExtractor::Textwise.new(:api_key => your_key, :context => your_text_or_url)
-- calais = SemExtractor::Calais.new(:api_key => CALAIS, :context => REQUEST)
-
-Get info:
-- yahoo.terms
-- zemanta.terms 
-- zemanta.categories
-- sem.terms
-- sem.categories
-- sem.filter  #filters the useful content of a web page, retrieves text
-- calais.terms
-- calais.categories
-- calais.geos
+=== Initialize:
+	yahoo = SemExtractor::Yahoo.new(:api_key => your_key, :context => your_text)
+	zemanta = SemExtractor::Zemanta.new(:api_key => your_key, :context => your_text)
+	sem = SemExtractor::Textwise.new(:api_key => your_key, :context => your_text_or_url)
+	calais = SemExtractor::Calais.new(:api_key => your_key, :context => your_text)
+
+===Get info:
+	yahoo.terms
+	zemanta.terms 
+	zemanta.categories
+	sem.terms
+	sem.categories
+	sem.filter  #filters the useful content of a web page, retrieves text
+	calais.terms
+	calais.categories
+	calais.geos
 
 == Note on Patches/Pull Requests
  

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.0.3

data/lib/apis/calais.rb

@@ -6,17 +6,16 @@ class SemExtractor
         Nokogiri::XML(remote_xml).xpath('//rdf:Description').map { |h|  
           node_type = h.xpath('rdf:type').first['resource']
           if node_type.include?('/type/cat/')
-            @categories << { "name" => h.xpath('c:categoryName').first.content, "score"=>h.xpath('c:score').first.content}
+            @categories << { "name" => sanitize(h.xpath('c:categoryName')), "score"=> sanitize(h.xpath('c:score'))}
           elsif node_type.include?('/type/em/')
-            nationality = h.xpath('c:nationality').first.nil? ? 'N/A' : h.xpath('c:nationality').first.content
-            @terms << { "name" => h.xpath('c:name').first.content, "score" => nil, "nationality" => nationality }
+            @terms << { "name" => sanitize(h.xpath('c:name')), "score" => nil, "nationality" => sanitize(h.xpath('c:nationality')) }
           elsif node_type.include?('/type/sys/InstanceInfo')
             #nothing to do, no info to take
           elsif node_type.include?('/type/sys/RelevanceInfo')
             # I assume here, Open Calais will keep on giving information in the proper order, seems fair :)
-            @terms.last["score"] = h.xpath('c:relevance').first.content
+            @terms.last["score"] = sanitize(h.xpath('c:relevance'))
           elsif node_type.include?('/Geo/')
-            @geos <<{ "name" => h.xpath('c:name').first.content } 
+            @geos <<{ "name" => sanitize(h.xpath('c:name')) } 
           end
           }
       end
@@ -33,6 +32,10 @@ class SemExtractor
     end
 
   private
+      def sanitize(item)
+        item.first.nil? ? 'N/A' : item.first.content 
+      end
+      
       def gateway
         'http://api.opencalais.com/enlighten/rest/'
       end

data/sem_extractor.gemspec

@@ -5,7 +5,7 @@
 
 Gem::Specification.new do |s|
   s.name = %q{sem_extractor}
-  s.version = "0.0.2"
+  s.version = "0.0.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["apneadiving"]
@@ -29,6 +29,7 @@ Gem::Specification.new do |s|
      "lib/sem_extractor.rb",
      "pkg/sem_extractor-0.0.0.gem",
      "pkg/sem_extractor-0.0.1.gem",
+     "pkg/sem_extractor-0.0.2.gem",
      "sem_extractor.gemspec",
      "test/helper.rb",
      "test/test_sem_extractor.rb"

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: sem_extractor
 version: !ruby/object:Gem::Version 
-  hash: 27
+  hash: 25
   prerelease: false
   segments: 
   - 0
   - 0
-  - 2
-  version: 0.0.2
+  - 3
+  version: 0.0.3
 platform: ruby
 authors: 
 - apneadiving
@@ -54,6 +54,7 @@ files:
 - lib/sem_extractor.rb
 - pkg/sem_extractor-0.0.0.gem
 - pkg/sem_extractor-0.0.1.gem
+- pkg/sem_extractor-0.0.2.gem
 - sem_extractor.gemspec
 - test/helper.rb
 - test/test_sem_extractor.rb