ark_tweet_nlp 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3e871d9a343c2765aa5ffe330399d65186a8f53d
-  data.tar.gz: e38987b047782875d9da857935b0570fda9ed8fd
+  metadata.gz: edcfbf9006fa1fd8b4d0f8fd882f33cdda06d903
+  data.tar.gz: f87ed6b80eac040f92a109641dafb651761eb592
 SHA512:
-  metadata.gz: 96f63bbdd0534f4b63a5a93c96c5d14702ea572c2286febc45dccda9ee6844c0070e878286557bb66dc2a6c89bc34cc146cf75095d48a99324f82d1efff09c54
-  data.tar.gz: 5f709d7f6ef82b0942cad0380afc827d4c080ea9acc9f5ec6294797691a893f1582e820a2c66636ea10d5fc5edb2b4149dcc19c488e838e57e1d34e8b6aa82b7
+  metadata.gz: ab69ac07296077fe85ccbf2e11d411d97cc690ba1dca8e215255f0d5ae02edff780dbf7406d3482b10a7d4697731f273060241645ab0aa12f7bda26ff091c17f
+  data.tar.gz: b02476e693cb8ebf6968a9d252dc090e0df0b8529d99ce441058c1e0871a69f99c92bee6769b88455885bcef73b354a698f791784b54f42c88a54e32f77f8c2e

data/lib/ark_tweet_nlp/parser.rb

@@ -40,7 +40,7 @@ module ArkTweetNlp
     end
 
     def Parser.find_tags text
-      result = Parser.run_tagger(text)
+      result = Parser.run_tagger(text.tr_s("\t"," ")).gsub(/\t\t\t\s*\n/,'')
       result.split("\n").map{ |line| Parser.convert_line( line ) }
     end
 
@@ -73,9 +73,9 @@ module ArkTweetNlp
     end
 
     def Parser.convert_line line
-      text = line.split("\t")[0].split
-      tags = line.split("\t")[1].split
-      text.each.with_index.inject({}){ |result,(value,index)| result[value] = tags[index].to_sym; result }
+        text = line.split("\t")[0].split
+        tags = line.split("\t")[1].split
+        text.each.with_index.inject({}){ |result,(value,index)| result[value] = tags[index].to_sym; result }
     end
 
     def Parser.safe_invert hash

data/lib/ark_tweet_nlp/version.rb

@@ -1,3 +1,3 @@
 module ArkTweetNlp
-  VERSION = "0.3.1"
+  VERSION = "0.3.2"
 end

data/spec/parser_spec.rb

@@ -6,6 +6,7 @@ describe ArkTweetNlp::Parser do
       expect(ArkTweetNlp::Parser::TAGSET.size).to eq 25
     end
   end
+
   describe '#find_tags' do
     it "cathegorizes words in tweets" do
       expect(ArkTweetNlp::Parser.find_tags('faceboooooooook is awesome')).to eq([ {'faceboooooooook' => :^,
@@ -15,13 +16,16 @@ describe ArkTweetNlp::Parser do
     it "suports urls" do
       expect(ArkTweetNlp::Parser.find_tags("I think I haven't had a segmentation fault in years http://t.co/COjaaFj6Ib")).to eq( [{"I"=>:O, "think"=>:V, "haven't"=>:V, "had"=>:V, "a"=>:D, "segmentation"=>:N, "fault"=>:N, "in"=>:P, "years"=>:N, "http://t.co/COjaaFj6Ib"=>:U}] )
     end
-    it "supoorts ponctuation from the tweets" do
-      expect(ArkTweetNlp::Parser.find_tags("Delayed... And waiting on a tire from Louisville. \"You can't be serious #Disappointed #pissed #letdown http://t.co/BFqsPZmr8m")).to eq([{"Delayed"=>:V, "..."=>:",", "And"=>:&, "waiting"=>:V, "on"=>:P, "a"=>:D, "tire"=>:N, "from"=>:P, "Louisville"=>:^, "."=>:",", "\""=>:",", "You"=>:O, "can't"=>:V, "be"=>:V, "serious"=>:A, "#Disappointed"=>:"#", "#pissed"=>:"#", "#letdown"=>:"#", "http://t.co/BFqsPZmr8m"=>:U}])
+    it "supoorts ponctuation from the tweets, but removes \t" do
+      expect(ArkTweetNlp::Parser.find_tags("Delayed... And waiting on \t a tire from Louisville. \"You can't be serious #Disappointed #pissed #letdown http://t.co/BFqsPZmr8m")).to eq([{"Delayed"=>:V, "..."=>:",", "And"=>:&, "waiting"=>:V, "on"=>:P, "a"=>:D, "tire"=>:N, "from"=>:P, "Louisville"=>:^, "."=>:",", "\""=>:",", "You"=>:O, "can't"=>:V, "be"=>:V, "serious"=>:A, "#Disappointed"=>:"#", "#pissed"=>:"#", "#letdown"=>:"#", "http://t.co/BFqsPZmr8m"=>:U}])
     end
     it "tags multiple tweets per line" do
       expect(ArkTweetNlp::Parser.find_tags("faceboooooooook is awesome\nfaceboooooooook is awesome")).to eq([{'faceboooooooook' => :^,'is' => :V,'awesome' => :A},{'faceboooooooook' => :^,'is' => :V,'awesome' => :A} ])
 
     end
+    it 'supports empty strings' do
+      expect(ArkTweetNlp::Parser.find_tags("\t\t\t\nfaceboooooooook is awesome\nfaceboooooooook is awesome")).to eq([{'faceboooooooook' => :^,'is' => :V,'awesome' => :A},{'faceboooooooook' => :^,'is' => :V,'awesome' => :A} ])
+    end
   end
 
   describe '#get_words_tagged_as' do

metadata

@@ -1,167 +1,167 @@
 --- !ruby/object:Gem::Specification
 name: ark_tweet_nlp
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Bernardo
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-15 00:00:00.000000000 Z
+date: 2014-09-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.7'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '1.7'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ~>
+    - - "~>"
       - !ruby/object:Gem::Version
         version: '10.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   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'
 - !ruby/object:Gem::Dependency
   name: rspec-nc
   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'
 - !ruby/object:Gem::Dependency
   name: pry
   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'
 - !ruby/object:Gem::Dependency
   name: pry-nav
   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'
 - !ruby/object:Gem::Dependency
   name: pry-rescue
   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'
 - !ruby/object:Gem::Dependency
   name: pry-stack_explorer
   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'
 - !ruby/object:Gem::Dependency
   name: pry-doc
   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'
 - !ruby/object:Gem::Dependency
   name: guard
   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'
 - !ruby/object:Gem::Dependency
   name: guard-rspec
   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'
 description: Tags tweets word into multiple cathegories using NLP
@@ -173,7 +173,7 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
-- .gitignore
+- ".gitignore"
 - Gemfile
 - Guardfile
 - LICENSE.txt
@@ -197,20 +197,21 @@ 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: 
-rubygems_version: 2.0.14
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Ruby wrapper for the Carnegie Mellon Twitter NLP
 test_files:
 - spec/parser_spec.rb
 - spec/spec_helper.rb
+has_rdoc: