alchemy_api 0.1.0 → 0.1.1

data/CHANGELOG.markdown

@@ -0,0 +1,4 @@
+0.1.1
+-----
+* Content tagging API added [jjulian, GH-1]
+* Added support for content-is-empty errors.

data/Rakefile

@@ -11,6 +11,7 @@ begin
     gem.homepage = "http://github.com/dbalatero/alchemy_api"
     gem.authors = ["David Balatero"]
     gem.add_development_dependency "rspec", ">= 1.2.9"
+    gem.add_development_dependency 'typhoeus_spec_cache', '>= 0.2.2'
     gem.add_dependency "monster_mash", ">= 0.1.1"
     # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
   end

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.1.1

data/alchemy_api.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = %q{alchemy_api}
-  s.version = "0.1.0"
+  s.version = "0.1.1"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["David Balatero"]
-  s.date = %q{2010-05-17}
+  s.date = %q{2010-09-12}
   s.description = %q{Provides a client API library for AlchemyAPI's awesome NLP services. Allows you to make parallel or serial requests.}
   s.email = %q{dbalatero@gmail.com}
   s.extra_rdoc_files = [
@@ -20,6 +20,7 @@ Gem::Specification.new do |s|
   s.files = [
     ".document",
      ".gitignore",
+     "CHANGELOG.markdown",
      "LICENSE",
      "README.markdown",
      "Rakefile",
@@ -28,11 +29,13 @@ Gem::Specification.new do |s|
      "lib/alchemy_api.rb",
      "lib/alchemy_api/base.rb",
      "lib/alchemy_api/categorization.rb",
+     "lib/alchemy_api/concept_tagging.rb",
      "lib/alchemy_api/language_detection.rb",
      "lib/alchemy_api/term_extraction.rb",
      "lib/alchemy_api/text_extraction.rb",
      "spec/alchemy_api/base_spec.rb",
      "spec/alchemy_api/categorization_spec.rb",
+     "spec/alchemy_api/concept_tagging_spec.rb",
      "spec/alchemy_api/language_detection_spec.rb",
      "spec/alchemy_api/term_extraction_spec.rb",
      "spec/alchemy_api/text_extraction_spec.rb",
@@ -40,6 +43,9 @@ Gem::Specification.new do |s|
      "spec/cache/categorization/get_categorization_from_html/ddc3cf50efe5bd5c2159abfb49121cfa2314ca88.cache",
      "spec/cache/categorization/get_categorization_from_text/8b476a3b532afd2da646b145e9dde07570c27352.cache",
      "spec/cache/categorization/get_categorization_from_url/7536a34e1d54a95d8ee07d2a98036362761e1621.cache",
+     "spec/cache/concept_tagging/get_concepts_from_html/7da223513abcfe2fd3d253fff60894829f858667.cache",
+     "spec/cache/concept_tagging/get_concepts_from_text/3e56901d7f01729b79ef73fc6d34fa97148eb35c.cache",
+     "spec/cache/concept_tagging/get_concepts_from_url/488c7dbb9b844b072cb284425b4ca8356b08dd15.cache",
      "spec/cache/language_detection/get_language_from_html/0faf7be978647b611d9c59e1efa497dd76e542f5.cache",
      "spec/cache/language_detection/get_language_from_text/1ad3f50c1fda37000e24c196f12212ea9d536cb4.cache",
      "spec/cache/language_detection/get_language_from_url/d077a95e60be0876bb7650ad213f5f43e83454d4.cache",
@@ -66,6 +72,7 @@ Gem::Specification.new do |s|
   s.test_files = [
     "spec/alchemy_api/base_spec.rb",
      "spec/alchemy_api/categorization_spec.rb",
+     "spec/alchemy_api/concept_tagging_spec.rb",
      "spec/alchemy_api/language_detection_spec.rb",
      "spec/alchemy_api/term_extraction_spec.rb",
      "spec/alchemy_api/text_extraction_spec.rb",
@@ -79,13 +86,16 @@ Gem::Specification.new do |s|
 
     if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
       s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_development_dependency(%q<typhoeus_spec_cache>, [">= 0.2.2"])
       s.add_runtime_dependency(%q<monster_mash>, [">= 0.1.1"])
     else
       s.add_dependency(%q<rspec>, [">= 1.2.9"])
+      s.add_dependency(%q<typhoeus_spec_cache>, [">= 0.2.2"])
       s.add_dependency(%q<monster_mash>, [">= 0.1.1"])
     end
   else
     s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    s.add_dependency(%q<typhoeus_spec_cache>, [">= 0.2.2"])
     s.add_dependency(%q<monster_mash>, [">= 0.1.1"])
   end
 end

data/lib/alchemy_api.rb

@@ -26,4 +26,5 @@ module AlchemyApi
   class PageIsNotValidHtmlError < StandardError; end
   class ContentExceedsMaxLimitError < StandardError; end
   class InvalidHtmlError < StandardError; end
+  class ContentIsEmptyError < StandardError; end
 end

data/lib/alchemy_api/base.rb

@@ -28,6 +28,8 @@ module AlchemyApi
           raise ContentExceedsMaxLimitError, "The page at #{json['url']} is larger than 600KB!"
         when 'invalid-html'
           raise InvalidHtmlError, "The HTML sent was invalid!"
+        when 'content-is-empty'
+          raise ContentIsEmptyError, "The content you provided was empty!"
         else
           raise UnknownError, "Got an unknown error: #{json['statusInfo']}"
         end

data/lib/alchemy_api/concept_tagging.rb

@@ -0,0 +1,60 @@
+# TODO: add support for linkedData return fields
+module AlchemyApi
+  ConceptTaggingResult = Struct.new(:concepts, :language, :url, :source_text)
+  Concept = Struct.new(:text, :relevance)
+
+  class ConceptTagging < Base
+    # http://www.alchemyapi.com/api/concept/textc.html
+    post(:get_concepts_from_text) do |text, *args|
+      options = args.first || {}
+      uri "#{AlchemyApi.base_text_uri}/TextGetRankedConcepts"
+      params :text => text,
+             :maxRetrieve => options[:max_retrieve] || 10,
+             :linkedData => 0,
+             :showSourceText => options[:show_source_text] ? 1 : 0
+      handler do |response|
+        AlchemyApi::ConceptTagging.get_concepts_handler(response)
+      end
+    end
+
+    # http://www.alchemyapi.com/api/concept/urls.html
+    post(:get_concepts_from_url) do |url, *args|
+      options = args.first || {}
+      uri "#{AlchemyApi.base_uri}/URLGetRankedConcepts"
+      params :url => url,
+             :maxRetrieve => options[:max_retrieve] || 10,
+             :linkedData => 0,
+             :showSourceText => options[:show_source_text] ? 1 : 0,
+             :sourceText => options[:source_text] || 'cleaned_or_raw',
+             :cquery => options[:cquery],
+             :xpath => options[:xpath]
+      handler do |response|
+        AlchemyApi::ConceptTagging.get_concepts_handler(response)
+      end
+    end
+
+    # http://www.alchemyapi.com/api/concept/htmlc.html
+    post(:get_concepts_from_html) do |html, *args|
+      options = args.first || {}
+      uri "#{AlchemyApi.base_html_uri}/HTMLGetRankedConcepts"
+      params :html => html,
+             :maxRetrieve => options[:max_retrieve] || 10,
+             :linkedData => 0,
+             :showSourceText => options[:show_source_text] ? 1 : 0,
+             :sourceText => options[:source_text] || 'cleaned_or_raw',
+             :cquery => options[:cquery],
+             :xpath => options[:xpath]
+      handler do |response|
+        AlchemyApi::ConceptTagging.get_concepts_handler(response)
+      end
+    end
+
+    def self.get_concepts_handler(response)
+      json = get_json(response)
+      concepts = json['concepts'].map do |c|
+        Concept.new(c['text'], c['relevance'].to_f)
+      end
+      ConceptTaggingResult.new(concepts, json['language'], json['url'], json['text'])
+    end
+  end
+end

data/spec/alchemy_api/concept_tagging_spec.rb

@@ -0,0 +1,50 @@
+require File.dirname(__FILE__) + "/../spec_helper"
+
+describe AlchemyApi::ConceptTagging do
+  typhoeus_spec_cache('spec/cache/concept_tagging/get_concepts_from_text') do |hydra|
+    describe "#get_concepts_from_text" do
+      before(:each) do
+        @url = "http://test.com"
+        text = fixture_for('article.txt')
+
+        @results = AlchemyApi::ConceptTagging.
+          get_concepts_from_text(text)
+      end
+
+      it "should return at least one concept" do
+        @results.concepts.should_not be_empty
+      end
+    end
+  end
+
+  typhoeus_spec_cache('spec/cache/concept_tagging/get_concepts_from_url') do |hydra|
+    describe "#get_concepts_from_url" do
+      before(:each) do
+        @url = 'http://www.macrumors.com/2010/04/30/apples-discontinuation-of-lala-streaming-music-service-not-likely-leading-to-imminent-launch-of-web-focused-itunes/'
+        @results = AlchemyApi::ConceptTagging.
+          get_concepts_from_url(@url,
+                                      :source_text => 'cleaned_or_raw')
+      end
+  
+      it "should return at least one concept" do
+        @results.concepts.should_not be_empty
+      end
+    end
+  end
+  
+  typhoeus_spec_cache('spec/cache/concept_tagging/get_concepts_from_html') do |hydra|
+    describe "#get_concepts_from_html" do
+      before(:each) do
+        @url = "http://www.businessweek.com/news/2010-04-29/bp-spill-may-alter-obama-s-offshore-drilling-plans-update1-.html"
+        @html = fixture_for('bp_spill.html')
+        @results = AlchemyApi::ConceptTagging.
+          get_concepts_from_html(@html, :url => @url,
+                                       :source_text => 'cleaned_or_raw')
+      end
+  
+      it "should return at least one concept" do
+        @results.concepts.should_not be_empty
+      end
+    end
+  end
+end

data/spec/cache/concept_tagging/get_concepts_from_html/7da223513abcfe2fd3d253fff60894829f858667.cache

@@ -0,0 +1,61 @@
+u:Typhoeus::Response�--- 
+:requested_http_method: 
+:headers: |
+  HTTP/1.1 100 Continue
+  
+  HTTP/1.1 200 OK
+  Server: nginx
+  Date: Sat, 11 Sep 2010 03:55:18 GMT
+  Content-Type: application/json
+  Transfer-Encoding: chunked
+  Connection: keep-alive
+  Cache-Control: no-cache
+  Content-Encoding: gzip
+  
+
+:requested_url: 
+:body: |
+  {
+      "status": "OK",
+      "usage": "By accessing AlchemyAPI or using information generated by AlchemyAPI, you are agreeing to be bound by the AlchemyAPI Terms of Use: http://www.alchemyapi.com/company/terms.html",
+      "url": "",
+      "language": "english",
+      "concepts": [
+          {
+              "text": "Robert Gibbs",
+              "relevance": "0.958553"
+          },
+          {
+              "text": "Bobby Jindal",
+              "relevance": "0.856261"
+          },
+          {
+              "text": "Barack Obama",
+              "relevance": "0.854173"
+          },
+          {
+              "text": "White House Press Secretary",
+              "relevance": "0.820978"
+          },
+          {
+              "text": "Petroleum",
+              "relevance": "0.702847"
+          },
+          {
+              "text": "Ken Salazar",
+              "relevance": "0.66043"
+          },
+          {
+              "text": "ExxonMobil",
+              "relevance": "0.621805"
+          },
+          {
+              "text": "Gulf of Mexico",
+              "relevance": "0.590221"
+          }
+      ]
+  }
+
+:code: 200
+:start_time: 
+:time: 2.276884

data/spec/cache/concept_tagging/get_concepts_from_text/3e56901d7f01729b79ef73fc6d34fa97148eb35c.cache

@@ -0,0 +1,48 @@
+u:Typhoeus::Responses--- 
+:requested_http_method: 
+:body: |
+  {
+      "status": "OK",
+      "usage": "By accessing AlchemyAPI or using information generated by AlchemyAPI, you are agreeing to be bound by the AlchemyAPI Terms of Use: http://www.alchemyapi.com/company/terms.html",
+      "url": "",
+      "language": "english",
+      "concepts": [
+          {
+              "text": "Bed and breakfast",
+              "relevance": "0.961337"
+          },
+          {
+              "text": "Hotel",
+              "relevance": "0.59768"
+          },
+          {
+              "text": "Breakfast",
+              "relevance": "0.536192"
+          },
+          {
+              "text": "Inn",
+              "relevance": "0.535763"
+          },
+          {
+              "text": "Lodging",
+              "relevance": "0.511123"
+          }
+      ]
+  }
+
+:requested_url: 
+:start_time: 
+:code: 200
+:time: 0.429581
+:headers: |
+  HTTP/1.1 100 Continue
+  
+  HTTP/1.1 200 OK
+  Server: nginx
+  Date: Sat, 11 Sep 2010 03:54:47 GMT
+  Content-Type: application/json
+  Connection: keep-alive
+  Content-Length: 754
+  Cache-Control: no-cache
+  
+

data/spec/cache/concept_tagging/get_concepts_from_url/488c7dbb9b844b072cb284425b4ca8356b08dd15.cache

@@ -0,0 +1,46 @@
+u:Typhoeus::Response�--- 
+:requested_http_method: 
+:headers: |
+  HTTP/1.1 200 OK
+  Server: nginx
+  Date: Sat, 11 Sep 2010 03:55:16 GMT
+  Content-Type: application/json
+  Connection: keep-alive
+  Content-Length: 921
+  Cache-Control: no-cache
+  
+
+:requested_url: 
+:body: |
+  {
+      "status": "OK",
+      "usage": "By accessing AlchemyAPI or using information generated by AlchemyAPI, you are agreeing to be bound by the AlchemyAPI Terms of Use: http://www.alchemyapi.com/company/terms.html",
+      "url": "http://www.macrumors.com/2010/04/30/apples-discontinuation-of-lala-streaming-music-service-not-likely-leading-to-imminent-launch-of-web-focused-itunes/",
+      "language": "english",
+      "concepts": [
+          {
+              "text": "EMI",
+              "relevance": "0.926603"
+          },
+          {
+              "text": "Record label",
+              "relevance": "0.917238"
+          },
+          {
+              "text": "Music industry",
+              "relevance": "0.754385"
+          },
+          {
+              "text": "ITunes Store",
+              "relevance": "0.734244"
+          },
+          {
+              "text": "Streaming media",
+              "relevance": "0.655383"
+          }
+      ]
+  }
+
+:code: 200
+:start_time: 
+:time: 0.313919

data/spec/spec_helper.rb

@@ -4,6 +4,8 @@ require 'alchemy_api'
 require 'spec'
 require 'spec/autorun'
 
+AlchemyApi.api_key = '3468d2194732163c69b0ac76079ca9f9c4193226'
+
 require 'typhoeus_spec_cache'
 
 Spec::Runner.configure do |config|

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 0
   - 1
-  - 0
-  version: 0.1.0
+  - 1
+  version: 0.1.1
 platform: ruby
 authors: 
 - David Balatero
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-05-17 00:00:00 -07:00
+date: 2010-09-12 00:00:00 -07:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -32,9 +32,23 @@ dependencies:
   type: :development
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
-  name: monster_mash
+  name: typhoeus_spec_cache
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 0
+        - 2
+        - 2
+        version: 0.2.2
+  type: :development
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: monster_mash
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
@@ -44,7 +58,7 @@ dependencies:
         - 1
         version: 0.1.1
   type: :runtime
-  version_requirements: *id002
+  version_requirements: *id003
 description: Provides a client API library for AlchemyAPI's awesome NLP services. Allows you to make parallel or serial requests.
 email: dbalatero@gmail.com
 executables: []
@@ -58,6 +72,7 @@ extra_rdoc_files:
 files: 
 - .document
 - .gitignore
+- CHANGELOG.markdown
 - LICENSE
 - README.markdown
 - Rakefile
@@ -66,11 +81,13 @@ files:
 - lib/alchemy_api.rb
 - lib/alchemy_api/base.rb
 - lib/alchemy_api/categorization.rb
+- lib/alchemy_api/concept_tagging.rb
 - lib/alchemy_api/language_detection.rb
 - lib/alchemy_api/term_extraction.rb
 - lib/alchemy_api/text_extraction.rb
 - spec/alchemy_api/base_spec.rb
 - spec/alchemy_api/categorization_spec.rb
+- spec/alchemy_api/concept_tagging_spec.rb
 - spec/alchemy_api/language_detection_spec.rb
 - spec/alchemy_api/term_extraction_spec.rb
 - spec/alchemy_api/text_extraction_spec.rb
@@ -78,6 +95,9 @@ files:
 - spec/cache/categorization/get_categorization_from_html/ddc3cf50efe5bd5c2159abfb49121cfa2314ca88.cache
 - spec/cache/categorization/get_categorization_from_text/8b476a3b532afd2da646b145e9dde07570c27352.cache
 - spec/cache/categorization/get_categorization_from_url/7536a34e1d54a95d8ee07d2a98036362761e1621.cache
+- spec/cache/concept_tagging/get_concepts_from_html/7da223513abcfe2fd3d253fff60894829f858667.cache
+- spec/cache/concept_tagging/get_concepts_from_text/3e56901d7f01729b79ef73fc6d34fa97148eb35c.cache
+- spec/cache/concept_tagging/get_concepts_from_url/488c7dbb9b844b072cb284425b4ca8356b08dd15.cache
 - spec/cache/language_detection/get_language_from_html/0faf7be978647b611d9c59e1efa497dd76e542f5.cache
 - spec/cache/language_detection/get_language_from_text/1ad3f50c1fda37000e24c196f12212ea9d536cb4.cache
 - spec/cache/language_detection/get_language_from_url/d077a95e60be0876bb7650ad213f5f43e83454d4.cache
@@ -129,6 +149,7 @@ summary: Provides a client API library for AlchemyAPI's awesome NLP services. Al
 test_files: 
 - spec/alchemy_api/base_spec.rb
 - spec/alchemy_api/categorization_spec.rb
+- spec/alchemy_api/concept_tagging_spec.rb
 - spec/alchemy_api/language_detection_spec.rb
 - spec/alchemy_api/term_extraction_spec.rb
 - spec/alchemy_api/text_extraction_spec.rb