name-spotter 0.2.1 → 0.2.2

data/spec/name-spotter_spec.rb

@@ -10,6 +10,21 @@ describe "NameSpotter" do
     @clients = [@neti, @tf]
   end
 
+  it "should find if a text is in english" do 
+    eng = open(File.join(File.dirname(__FILE__), 'files', 'english.txt'), 'r:utf-8').read
+    eng2 = open(File.join(File.dirname(__FILE__), 'files', 'english.txt'), 'r:utf-8').read
+    eng3 = open(File.join(File.dirname(__FILE__), 'files', 'journalofentomol13pomo_0018.txt'), 'r:utf-8').read
+    eng3 = open(File.join(File.dirname(__FILE__), 'files', 'journalofentomol13pomo_0063.txt'), 'r:utf-8').read
+    
+    not_eng = open(File.join(File.dirname(__FILE__), 'files', 'not_english.txt'), 'r:utf-8').read
+    100.times do
+      NameSpotter.english?(eng).should be_true
+      NameSpotter.english?(eng2).should be_true
+      NameSpotter.english?(eng3).should be_false
+      NameSpotter.english?(not_eng).should be_false
+    end
+  end
+
   it "should exist" do
     @neti.is_a?(NameSpotter).should be_true
     @tf.is_a?(NameSpotter).should be_true
@@ -62,7 +77,9 @@ describe "NameSpotter" do
   end
 
   it "should get back correct names using offsets in utf-8 based text" do
-    text = "A text with multibyte characters नेति नेति:  Some text that has Betula\n alba and Mus musculus and \neven B. alba and even M. mus-\nculus. Also it has name unknown before: Varanus bitatawa species"
+    # this test depends on netineti tornado server, not on namespotter itself. Go and fix that!
+    # the issue and the fix: https://github.com/mbl-cli/NetiNeti/pull/1
+    text = "\r\r\n>':¥/. \r\nA text with multibyte characters नेति नेति:  Some text that has Betula\n alba and Mus musculus and \neven B. alba and even M. mus-\nculus. Also it has name unknown before: Varanus bitatawa species"
     res = @neti.find(text)[:names]
     res.map do |name|
       verbatim = name[:verbatim]

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: name-spotter
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.2.2
   prerelease: 
 platform: ruby
 authors:
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-11 00:00:00.000000000 Z
+date: 2012-07-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -93,6 +93,22 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: unsupervised-language-detection
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -233,6 +249,7 @@ files:
 - .document
 - .rspec
 - .rvmrc
+- CHANGELOG
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -249,8 +266,10 @@ files:
 - lib/name-spotter/scientific_name.rb
 - lib/name-spotter/taxon_finder_client.rb
 - name-spotter.gemspec
+- spec/files/english.txt
 - spec/files/journalofentomol13pomo_0018.txt
 - spec/files/journalofentomol13pomo_0063.txt
+- spec/files/not_english.txt
 - spec/name-spotter_spec.rb
 - spec/scientific_name_spec.rb
 - spec/spec_helper.rb
@@ -270,7 +289,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 1101945023410070648
+      hash: -2884343420129589551
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements: