opener-ner 2.0.2 → 2.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5c77d158e1dd7057cdde02e255491363f5ec351f
-  data.tar.gz: f6dceeec56433da36aff8f86e400386505251992
+  metadata.gz: b7e44ba3a70a79bde04d36f74e250a6d0de510df
+  data.tar.gz: 0c5dc588060d3d8fc9b87f291f186d3efc37d655
 SHA512:
-  metadata.gz: 0a0bf3e06f4dfa59b632d35918a2c6b325061d30d753856660acf5998eecc97e2443e83b7ffe6c313e3504311918d3e2d3b207fd6f5b4c563d3faeff1731422d
-  data.tar.gz: ec1b103186afb95179b4edaa70f2a7148e47c4e96167de8113ad6ed6d78f1bb470a5389397de534502b667699f40d14c0ae923ac98dda802d058fa503692fd48
+  metadata.gz: 0ed9b436a48192cd51e291bfd65f312d5d526a9cef8f1d20f71362f05b31f1e9cd9881d8c39340e30dadf0b380bc656049111d2df144cdbe0b5a6610d75a345a
+  data.tar.gz: ea6ef030833d7c91906a892240ab651c5904d4ed52db927ebc5171c4e41193c03d3a8802a1fe2dee9ac1da82d25f37acd7a3e0fd30d80bfecb9399fa1656b58f

data/README.md

@@ -1,16 +1,11 @@
 # NER
 
-This repository contains the source code for the primary NER component of the
-OpeNER project. This component provides a CLI interface for the various kernels
-as well as providing a Sinatra based web service.
+This repository contains the source code for the primary NER component of the OpeNER project. This component provides a CLI interface for the various kernels as well as providing a Sinatra based web service.
 
 ### Confused by some terminology?
 
-This software is part of a larger collection of natural language processing
-tools known as "the OpeNER project". You can find more information about the
-project at [the OpeNER portal](http://opener-project.github.io). There you can
-also find references to terms like KAF (an XML standard to represent linguistic
-annotations in texts), component, cores, scenario's and pipelines.
+This software is part of a larger collection of natural language processing tools known as "the OpeNER project". You can find more information about the project at [the OpeNER portal](http://opener-project.github.io). There you can also find references to terms like KAF (an XML standard to represent linguistic annotations in texts), component, cores, scenario's and pipelines.
+
 
 Quick Use Example
 -----------------
@@ -19,21 +14,18 @@ Installing the ner can be done by executing:
 
     gem install opener-ner
 
-Please bare in mind that all components in OpeNER take KAF as an input and
-output KAF by default.
+Please bare in mind that all components in OpeNER take KAF as an input and output KAF by default.
 
 ### Command line interface
 
-You should now be able to call the NER as a regular shell
-command: by its name. Once installed the gem normalyl sits in your path so you can call it directly from anywhere.
+You should now be able to call the NER as a regular shell command: by its name. Once installed the gem normalyl sits in your path so you can call it directly from anywhere.
 
 This aplication reads a text from standard input in order to identify the language.
 
     cat some_kind_of_kaf_file.kaf | ner
 
 
-This will output a kaf file containing the named entities. An excerpt can be
-seen here
+This will output a kaf file containing the named entities. An excerpt can be seen here
 
 ```
 <entity eid="e3" type="organization">
@@ -54,26 +46,20 @@ You can launch a language identification webservice by executing:
 
     ner-server
 
-This will launch a mini webserver with the webservice. It defaults to port 9292,
-so you can access it at <http://localhost:9292>.
+This will launch a mini webserver with the webservice. It defaults to port 9292, so you can access it at <http://localhost:9292>.
 
-To launch it on a different port provide the `-p [port-number]` option like
-this:
+To launch it on a different port provide the `-p [port-number]` option like this:
 
     ner-server -p 1234
 
 It then launches at <http://localhost:1234>
 
-Documentation on the Webservice is provided by surfing to the urls provided
-above. For more information on how to launch a webservice run the command with
-the ```-h``` option.
+Documentation on the Webservice is provided by surfing to the urls provided above. For more information on how to launch a webservice run the command with the ```-h``` option.
 
 
 ### Daemon
 
-Last but not least the NER comes shipped with a daemon that
-can read jobs (and write) jobs to and from Amazon SQS queues. For more
-information type:
+Last but not least the NER comes shipped with a daemon that can read jobs (and write) jobs to and from Amazon SQS queues. For more information type:
 
     ner-daemon -h
 
@@ -81,8 +67,7 @@ information type:
 Description of dependencies
 ---------------------------
 
-This component runs best if you run it in an environment suited for OpeNER
-components. You can find an installation guide and helper tools in the [OpeNER installer](https://github.com/opener-project/opener-installer) and an
+This component runs best if you run it in an environment suited for OpeNER components. You can find an installation guide and helper tools in the [OpeNER installer](https://github.com/opener-project/opener-installer) and an
 [installation guide on the Opener Website](http://opener-project.github.io/getting-started/how-to/local-installation.html)
 
 At least you need the following system setup:
@@ -109,8 +94,7 @@ Language Extension
 The Core
 --------
 
-The component is a fat wrapper around the actual language technology core. You
-can find the core technolies in the following repositories:
+The component is a fat wrapper around the actual language technology core. You can find the core technolies in the following repositories:
 
 * [ner-base](https://github.com/opener-project/ner-base)
 
@@ -118,14 +102,14 @@ can find the core technolies in the following repositories:
 Where to go from here
 ---------------------
 
-* [Check the project websitere](http://opener-project.github.io)
+* [Check the project website](http://opener-project.github.io)
 * [Checkout the webservice](http://opener.olery.com/ner)
 
 Report problem/Get help
 -----------------------
 
-If you encounter problems, please email <support@opener-project.eu> or leave an
-issue in the [issue tracker](https://github.com/opener-project/ner/issues).
+If you encounter problems, please email <support@opener-project.eu> or leave an issue in the 
+[issue tracker](https://github.com/opener-project/ner/issues).
 
 
 Contributing

data/lib/opener/ner.rb

@@ -4,6 +4,7 @@ require 'nokogiri'
 
 require_relative 'ner/version'
 require_relative 'ner/cli'
+require_relative 'ner/error_layer'
 
 module Opener
   ##
@@ -52,16 +53,20 @@ module Opener
     # @return [Array]
     #
     def run(input)
-      language = language_from_kaf(input) || DEFAULT_LANGUAGE
-      args     = options[:args].dup
+      begin
+        language = language_from_kaf(input) || DEFAULT_LANGUAGE
+        args     = options[:args].dup
 
-      if language_constant_defined?(language)
-        kernel = language_constant(language).new(:args => args)
-      else
-        kernel = Ners::Base.new(:args => args, :language => language)
-      end
+        if language_constant_defined?(language)
+          kernel = language_constant(language).new(:args => args)
+        else
+          kernel = Ners::Base.new(:args => args, :language => language)
+        end
 
-      return kernel.run(input)
+        return kernel.run(input)
+      rescue Exception => error
+        return ErrorLayer.new(input, error.message, self.class).add
+      end
     end
 
     protected

data/lib/opener/ner/error_layer.rb

@@ -0,0 +1,88 @@
+module Opener
+  class Ner
+    ##
+    # Add Error Layer to KAF file instead of throwing an error.
+    #
+    class ErrorLayer
+      attr_accessor :input, :document, :error, :klass
+      
+      def initialize(input, error, klass)
+        @input    = input.to_s
+        # Make sure there is always a document, even if it is empty.
+        @document = Nokogiri::XML(input) rescue Nokogiri::XML(nil)
+        @error    = error
+        @klass    = klass
+      end
+      
+      def add
+        if is_xml?
+          unless has_errors_layer?
+            add_errors_layer
+          end
+        else
+          add_root
+          add_text
+          add_errors_layer
+        end
+        add_error
+        
+        xml = !!document.encoding ? document.to_xml : document.to_xml(:encoding => "UTF-8")
+        
+        return xml
+      end
+      
+      ##
+      # Check if the document is a valid XML file.
+      #
+      def is_xml?
+        !!document.root
+      end
+      
+      ##
+      # Add root element to the XML file.
+      #
+      def add_root
+        root = Nokogiri::XML::Node.new "KAF", document
+        document.add_child(root)
+      end
+      
+      ##
+      # Check if the document already has an errors layer.
+      #
+      def has_errors_layer?
+        !!document.at('errors')
+      end
+      
+      ##
+      # Add errors element to the XML file.
+      #
+      def add_errors_layer
+        node = Nokogiri::XML::Node.new "errors", document
+        document.root.add_child(node)
+      end
+      
+      ##
+      # Add the text file incase it is not a valid XML document. More
+      # info for debugging.
+      #
+      def add_text
+        node = Nokogiri::XML::Node.new "raw", document
+        node.inner_html = input
+        document.root.add_child(node)
+        
+      end
+      
+      ##
+      # Add the actual error to the errors layer.
+      #
+      def add_error
+        node = document.at('errors')
+        error_node = Nokogiri::XML::Node.new "error", node
+        error_node['class']   = "#{klass.to_s} #{klass::VERSION}"
+        error_node.inner_html = error
+        node.add_child(error_node)
+      end     
+      
+    end # ErrorLayer
+  end # Ner
+end # Opener

data/lib/opener/ner/version.rb

@@ -1,5 +1,5 @@
 module Opener
   class Ner
-    VERSION = '2.0.2'
+    VERSION = '2.0.3'
   end # NER
 end # Opener

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: opener-ner
 version: !ruby/object:Gem::Version
-  version: 2.0.2
+  version: 2.0.3
 platform: ruby
 authors:
 - development@olery.com
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-05-23 00:00:00.000000000 Z
+date: 2014-06-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: sinatra
@@ -140,24 +140,25 @@ description: Primary NER component that wraps the various NER kernels.
 email:
 executables:
 - ner
-- ner-server
 - ner-daemon
+- ner-server
 extensions: []
 extra_rdoc_files: []
 files:
+- README.md
+- bin/ner
+- bin/ner-daemon
+- bin/ner-server
+- config.ru
+- exec/ner.rb
 - lib/opener/ner.rb
-- lib/opener/ner/version.rb
-- lib/opener/ner/server.rb
 - lib/opener/ner/cli.rb
+- lib/opener/ner/error_layer.rb
 - lib/opener/ner/public/markdown.css
+- lib/opener/ner/server.rb
+- lib/opener/ner/version.rb
 - lib/opener/ner/views/index.erb
-- config.ru
 - opener-ner.gemspec
-- README.md
-- exec/ner.rb
-- bin/ner
-- bin/ner-server
-- bin/ner-daemon
 homepage:
 licenses: []
 metadata: {}
@@ -177,9 +178,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project:
-rubygems_version: 2.1.9
+rubygems_version: 2.2.2
 signing_key:
 specification_version: 4
 summary: Primary NER component that wraps the various NER kernels.
 test_files: []
-has_rdoc: yard