opener-ned 2.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9040d06ad1e01c87c8748947ee3c66f61ea2d083
+  data.tar.gz: 843fc7ae1a18cf93118a9300bcfce32f4f5ba27d
+SHA512:
+  metadata.gz: 6947de909caf7c8ef1c496e994a18a99190b3b23c83e73528a7491531a6a22c08a3179303517a3c99f7041a3a66dffbb5519c7dd8008296c1bd96f45525423b7
+  data.tar.gz: cd2c1cdf5386e380cbb09663a2633f793bcb7f61fa83879df5e92cb118911e177b1d9b82daaa35b8bf5ca55de94a0a38ee5278de5a74c08b45683d9b0d0f2b60

data/README.md

@@ -0,0 +1,57 @@
+# NED
+
+This repository contains a Named Entity Disambiguation tool that queries a
+DBpedia spotlight server. The client takes KAF as input (containing
+`<entities>` nodes).
+
+## Requirements
+
+* Ruby 1.9.2 or newer
+* Java 1.7 or newer
+
+## Installation
+
+Installing as a regular Gem:
+
+    gem install opener-ned
+
+Using Bundler:
+
+    gem 'opener-ned',
+      :git    => 'git@github.com:opener-project/constituent-parser-base.git',
+      :branch => 'master'
+
+Using specific install:
+
+    gem install specific_install
+    gem specific_install opener-ned \
+       -l https://github.com/opener-project/constituent-parser-base.git
+
+## Usage
+
+The NED client requires a working DBpedia Spotlight server to be available. By
+default it tries to connect to http://localhost:2020 (English language) but you
+can change this using the `--host` and `--port` options in the CLI.
+
+A simple example:
+
+    cat some_input_file.kaf | ned --host=http://example.com/ --port=1234
+
+## Contributing
+
+First make sure all the required dependencies are installed:
+
+    bundle install
+
+Then compile the required Java code:
+
+    bundle exec rake compile
+
+For this you'll need to have Java 1.7 and Maven installed. These requirements
+are verified for you before the Rake task calls Maven.
+
+## Structure
+
+This repository comes in two parts: a collection of Java source files and Ruby
+source files. The Java code can be found in the `core/` directory, everything
+else will be Ruby source code.

data/bin/ned

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/ned'
+
+cli = Opener::Ned::CLI.new(:args => ARGV)
+
+cli.run(STDIN.tty? ? nil : STDIN.read)

data/bin/ned-server

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/ned/server'
+
+# Without calling `Rack::Server#options` manually the CLI arguments will never
+# be passed, thus the application can't be specified as a constructor argument.
+server                  = Rack::Server.new
+server.options[:config] = File.expand_path('../../config.ru', __FILE__)
+
+server.start

data/config.ru

@@ -0,0 +1,4 @@
+require File.expand_path('../lib/opener/ned', __FILE__)
+require File.expand_path('../lib/opener/ned/server', __FILE__)
+
+run Opener::Ned::Server

data/lib/opener/ned.rb

@@ -0,0 +1,96 @@
+require 'optparse'
+require 'java'
+require 'stringio'
+require 'nokogiri'
+
+require File.expand_path('../../../core/target/ehu-ned-1.0.jar', __FILE__)
+
+require_relative 'ned/version'
+require_relative 'ned/cli'
+
+import 'java.io.InputStreamReader'
+
+import 'ehu.ned.Annotate'
+import 'ixa.kaflib.KAFDocument'
+
+module Opener
+  ##
+  # Ruby wrapper around the Java based Ned tool that's powered by DBpedia.
+  #
+  # @!attribute [r] options
+  #  @return [Hash]
+  #
+  class Ned
+    attr_reader :options
+
+    LANGUAGE_ENDPOINTS = {
+      "en"=>"http://spotlight.sztaki.hu:2222",
+      "nl"=>"http://nl.dbpedia.org/spotlight",
+      "fr"=>"http://spotlight.sztaki.hu:2225",
+      "de"=>"http://de.dbpedia.org/spotlight",
+      "es"=>"http://spotlight.sztaki.hu:2231",
+      "it"=>"http://spotlight.sztaki.hu:2230",
+      "ru"=>"http://spotlight.sztaki.hu:2227",
+      "pt"=>"http://spotlight.sztaki.hu:2228",
+      "hu"=>"http://spotlight.sztaki.hu:2229",
+      "tr"=>"http://spotlight.sztaki.hu:2235"
+    }
+
+    ##
+    # Hash containing the default options to use.
+    #
+    # @return [Hash]
+    #
+    DEFAULT_OPTIONS = {
+      :args => [],
+    }.freeze
+
+    ##
+    # @param [Hash] options
+    #
+    # @option options [Array] :args Arbitrary arguments to pass to the
+    #  underlying kernel.
+    # @option options [String|Numeric] :port The port number to connect to.
+    # @option options [String] :host The hostname of the DBpedia server.
+    # @option options [String] :language When set the port number will be based
+    #  on this value.
+    #
+    def initialize(options = {})
+      @options = DEFAULT_OPTIONS.merge(options)
+    end
+
+    def run(input)
+      if !input or input.strip.empty?
+        raise ArgumentError, 'No input specified'
+      end
+
+      language = language_from_kaf(input)
+
+      input_io  = StringIO.new(input)
+      reader    = InputStreamReader.new(input_io.to_inputstream)
+      document  = KAFDocument.create_from_stream(reader)
+      annotator = Java::ehu.ned.Annotate.new
+
+      endpoint = @options.fetch(:endpoint, uri_for_language(language))
+
+      annotator.disambiguateNEsToKAF(
+        document,
+        endpoint.to_s
+      )
+
+      return document.to_string
+    end
+
+    private
+
+    def language_from_kaf(input)
+      document = Nokogiri::XML(input)
+      language = document.at('KAF').attr('xml:lang')
+    end
+
+    def uri_for_language(language)
+      LANGUAGE_ENDPOINTS[language]+"/rest/disambiguate"
+    end
+
+  end # Ned
+end # Opener

data/lib/opener/ned/cli.rb

@@ -0,0 +1,92 @@
+module Opener
+  class Ned
+    ##
+    # CLI wrapper around {Opener::Ned} using OptionParser.
+    #
+    # @!attribute [r] options
+    #  @return [Hash]
+    # @!attribute [r] option_parser
+    #  @return [OptionParser]
+    #
+    class CLI
+      attr_reader :options, :option_parser
+
+      ##
+      # @param [Hash] options
+      #
+      def initialize(options = {})
+        @options = DEFAULT_OPTIONS.merge(options)
+
+        @option_parser = OptionParser.new do |opts|
+          opts.program_name   = 'ned'
+          opts.summary_indent = '  '
+
+          opts.on('-h', '--help', 'Shows this help message') do
+            show_help
+          end
+
+          opts.on('-v', '--version', 'Shows the current version') do
+            show_version
+          end
+
+          opts.on('-p', '--port [VALUE]', 'Use a custom port') do |value|
+            @options[:port] = value
+          end
+
+          opts.on('-H', '--host [VALUE]', 'Use a custom hostname') do |value|
+            @options[:host] = value
+          end
+
+          opts.separator <<-EOF
+
+Examples:
+
+  cat input_file.kaf | #{opts.program_name}
+  cat input_file.kaf | #{opts.program_name} --host=http://some-host.com/
+
+Port Numbers:
+
+  Port numbers are required. Each language has its own port number (unless
+  specified otherwise):
+
+  * German: 2010
+  * English: 2020
+  * Spanish: 2030
+  * French: 2040
+  * Italian: 2050
+  * Dutch: 2060
+
+  By default port 2020 (English) is used.
+          EOF
+        end
+      end
+
+      ##
+      # @param [String] input
+      #
+      def run(input)
+        option_parser.parse!(options[:args])
+
+        ned = Ned.new(options)
+
+        puts ned.run(input)
+      end
+
+      private
+
+      ##
+      # Shows the help message and exits the program.
+      #
+      def show_help
+        abort option_parser.to_s
+      end
+
+      ##
+      # Shows the version and exits the program.
+      #
+      def show_version
+        abort "#{option_parser.program_name} v#{VERSION} on #{RUBY_DESCRIPTION}"
+      end
+    end # CLI
+  end # Ned
+end # Opener

data/lib/opener/ned/public/markdown.css

@@ -0,0 +1,284 @@
+
+input[type="text"], textarea
+{
+  width: 500px;
+}
+
+body {
+  font-family: Helvetica, arial, sans-serif;
+  font-size: 14px;
+  line-height: 1.6;
+  padding-top: 10px;
+  padding-bottom: 10px;
+  background-color: white;
+  padding: 30px; }
+
+body > *:first-child {
+  margin-top: 0 !important; }
+body > *:last-child {
+  margin-bottom: 0 !important; }
+
+a {
+  color: #4183C4; }
+a.absent {
+  color: #cc0000; }
+a.anchor {
+  display: block;
+  padding-left: 30px;
+  margin-left: -30px;
+  cursor: pointer;
+  position: absolute;
+  top: 0;
+  left: 0;
+  bottom: 0; }
+
+h1, h2, h3, h4, h5, h6 {
+  margin: 20px 0 10px;
+  padding: 0;
+  font-weight: bold;
+  -webkit-font-smoothing: antialiased;
+  cursor: text;
+  position: relative; }
+
+h1:hover a.anchor, h2:hover a.anchor, h3:hover a.anchor, h4:hover a.anchor, h5:hover a.anchor, h6:hover a.anchor {
+  background: url("../../images/modules/styleguide/para.png") no-repeat 10px center;
+  text-decoration: none; }
+
+h1 tt, h1 code {
+  font-size: inherit; }
+
+h2 tt, h2 code {
+  font-size: inherit; }
+
+h3 tt, h3 code {
+  font-size: inherit; }
+
+h4 tt, h4 code {
+  font-size: inherit; }
+
+h5 tt, h5 code {
+  font-size: inherit; }
+
+h6 tt, h6 code {
+  font-size: inherit; }
+
+h1 {
+  font-size: 28px;
+  color: black; }
+
+h2 {
+  font-size: 24px;
+  border-bottom: 1px solid #cccccc;
+  color: black; }
+
+h3 {
+  font-size: 18px; }
+
+h4 {
+  font-size: 16px; }
+
+h5 {
+  font-size: 14px; }
+
+h6 {
+  color: #777777;
+  font-size: 14px; }
+
+p, blockquote, ul, ol, dl, li, table, pre {
+  margin: 15px 0; }
+
+hr {
+  background: transparent url("../../images/modules/pulls/dirty-shade.png") repeat-x 0 0;
+  border: 0 none;
+  color: #cccccc;
+  height: 4px;
+  padding: 0; }
+
+body > h2:first-child {
+  margin-top: 0;
+  padding-top: 0; }
+body > h1:first-child {
+  margin-top: 0;
+  padding-top: 0; }
+body > h1:first-child + h2 {
+  margin-top: 0;
+  padding-top: 0; }
+body > h3:first-child, body > h4:first-child, body > h5:first-child, body > h6:first-child {
+  margin-top: 0;
+  padding-top: 0; }
+
+a:first-child h1, a:first-child h2, a:first-child h3, a:first-child h4, a:first-child h5, a:first-child h6 {
+  margin-top: 0;
+  padding-top: 0; }
+
+h1 p, h2 p, h3 p, h4 p, h5 p, h6 p {
+  margin-top: 0; }
+
+li p.first {
+  display: inline-block; }
+
+ul, ol {
+  padding-left: 30px; }
+
+ul :first-child, ol :first-child {
+  margin-top: 0; }
+
+ul :last-child, ol :last-child {
+  margin-bottom: 0; }
+
+dl {
+  padding: 0; }
+dl dt {
+  font-size: 14px;
+  font-weight: bold;
+  font-style: italic;
+  padding: 0;
+  margin: 15px 0 5px; }
+dl dt:first-child {
+  padding: 0; }
+dl dt > :first-child {
+  margin-top: 0; }
+dl dt > :last-child {
+  margin-bottom: 0; }
+dl dd {
+  margin: 0 0 15px;
+  padding: 0 15px; }
+dl dd > :first-child {
+  margin-top: 0; }
+dl dd > :last-child {
+  margin-bottom: 0; }
+
+blockquote {
+  border-left: 4px solid #dddddd;
+  padding: 0 15px;
+  color: #777777; }
+blockquote > :first-child {
+  margin-top: 0; }
+blockquote > :last-child {
+  margin-bottom: 0; }
+
+table {
+  padding: 0; }
+table tr {
+  border-top: 1px solid #cccccc;
+  background-color: white;
+  margin: 0;
+  padding: 0; }
+table tr:nth-child(2n) {
+  background-color: #f8f8f8; }
+table tr th {
+  font-weight: bold;
+  border: 1px solid #cccccc;
+  text-align: left;
+  margin: 0;
+  padding: 6px 13px; }
+table tr td {
+  border: 1px solid #cccccc;
+  text-align: left;
+  margin: 0;
+  padding: 6px 13px; }
+table tr th :first-child, table tr td :first-child {
+  margin-top: 0; }
+table tr th :last-child, table tr td :last-child {
+  margin-bottom: 0; }
+
+img {
+  max-width: 100%; }
+
+span.frame {
+  display: block;
+  overflow: hidden; }
+span.frame > span {
+  border: 1px solid #dddddd;
+  display: block;
+  float: left;
+  overflow: hidden;
+  margin: 13px 0 0;
+  padding: 7px;
+  width: auto; }
+span.frame span img {
+  display: block;
+  float: left; }
+span.frame span span {
+  clear: both;
+  color: #333333;
+  display: block;
+  padding: 5px 0 0; }
+span.align-center {
+  display: block;
+  overflow: hidden;
+  clear: both; }
+span.align-center > span {
+  display: block;
+  overflow: hidden;
+  margin: 13px auto 0;
+  text-align: center; }
+span.align-center span img {
+  margin: 0 auto;
+  text-align: center; }
+span.align-right {
+  display: block;
+  overflow: hidden;
+  clear: both; }
+span.align-right > span {
+  display: block;
+  overflow: hidden;
+  margin: 13px 0 0;
+  text-align: right; }
+span.align-right span img {
+  margin: 0;
+  text-align: right; }
+span.float-left {
+  display: block;
+  margin-right: 13px;
+  overflow: hidden;
+  float: left; }
+span.float-left span {
+  margin: 13px 0 0; }
+span.float-right {
+  display: block;
+  margin-left: 13px;
+  overflow: hidden;
+  float: right; }
+span.float-right > span {
+  display: block;
+  overflow: hidden;
+  margin: 13px auto 0;
+  text-align: right; }
+
+code, tt {
+  margin: 0 2px;
+  padding: 0 5px;
+  white-space: nowrap;
+  border: 1px solid #eaeaea;
+  background-color: #f8f8f8;
+  border-radius: 3px; }
+
+pre code {
+  margin: 0;
+  padding: 0;
+  white-space: pre;
+  border: none;
+  background: transparent; }
+
+.highlight pre {
+  background-color: #f8f8f8;
+  border: 1px solid #cccccc;
+  font-size: 13px;
+  line-height: 19px;
+  overflow: auto;
+  padding: 6px 10px;
+  border-radius: 3px; }
+
+pre {
+  background-color: #f8f8f8;
+  border: 1px solid #cccccc;
+  font-size: 13px;
+  line-height: 19px;
+  overflow: auto;
+  padding: 6px 10px;
+  border-radius: 3px; }
+pre code, pre tt {
+  background-color: transparent;
+  border: none; }
+

data/lib/opener/ned/server.rb

@@ -0,0 +1,13 @@
+require 'sinatra/base'
+require 'opener/webservice'
+require 'httpclient'
+
+module Opener
+  class Ned
+    class Server < Webservice
+      set :views, File.expand_path('../views', __FILE__)
+      text_processor Ned
+      accepted_params :input, :host, :port
+    end # Server
+  end # Ned
+end # Opener

data/lib/opener/ned/version.rb

@@ -0,0 +1,5 @@
+module Opener
+  class Ned
+    VERSION = '2.0.0'
+  end # Ned
+end # Opener

data/lib/opener/ned/views/index.erb

@@ -0,0 +1,87 @@
+
+<!DOCTYPE html>
+<html>
+    <head>
+        <link type="text/css" rel="stylesheet" href="markdown.css" />
+
+        <title>NED Webservice</title>
+    </head>
+    <body>
+        <h1>NED Webservice</h1>
+
+        <p>
+        * required
+
+        <br />
+
+        ** When entering a value no response will be displayed in the browser.
+        </p>
+
+        <form action="<%=url("/")%>" method="POST">
+            <div>
+                <label for="input">KAF input *</label>
+                <br />
+
+                <textarea id="input" name="input" cols="50" rows="10"></textarea>
+            </div>
+
+            <div>
+              <label for="endpoint">DBPedia disambiguate REST endpoint.</label>
+                <br />
+
+                <input id="host" type="text" name="host" />
+
+              Example: http://nl.dbpedia.org/spotlight/rest/disambiguate
+            </div>
+
+            <% 5.times do |number| %>
+
+            <div>
+                <label for="callbacks">Callback URL <%= number + 1 %> **</label>
+                <br />
+
+                <input id="callbacks" type="text" name="callbacks[]" />
+            </div>
+
+            <% end %>
+
+            <div>
+                <label for="error_callback">Error Callback</label>
+                <br />
+
+                <input id="error_callback" type="text" name="error_callback" />
+            </div>
+
+            <input type="submit" value="Submit" />
+        </form>
+
+        <h2>Actions</h2>
+
+        <dl>
+            <dt>GET /</dt>
+            <dd>Shows this page</dd>
+
+            <dt>POST /</dt>
+            <dd>Submits a KAF document</dd>
+        </dl>
+
+        <h2>Parameters</h2>
+
+        <dl>
+            <dt>text *</dt>
+            <dd>The KAF document to tag.</dd>
+
+            <dt>callbacks</dt>
+            <dd>A collection of callback URLs that are processed as a chain.</dd>
+
+            <dt>error_callback</dt>
+            <dd>Errors are submitted to this URL in the "error" field.</dd>
+
+            <dt>host</dt>
+            <dd>The hostname of the DBpedia Spotlight server.</dd>
+
+            <dt>port</dt>
+            <dd>The port number of the DBpedia Spotlight server.</dd>
+        </dl>
+    </body>
+</html>

data/opener-ned.gemspec

@@ -0,0 +1,30 @@
+require File.expand_path('../lib/opener/ned/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.name        = 'opener-ned'
+  gem.version     = Opener::Ned::VERSION
+  gem.authors     = ['development@olery.com']
+  gem.summary     = 'NED client using DBpedia'
+  gem.description = gem.summary
+  gem.has_rdoc    = 'yard'
+
+  gem.required_ruby_version = '>= 1.9.2'
+
+  gem.files = Dir.glob([
+    'core/target/ehu-ned-*.jar',
+    'lib/**/*',
+    '*.gemspec',
+    'config.ru',
+    'README.md'
+  ]).select { |file| File.file?(file) }
+
+  gem.executables = Dir.glob('bin/*').map { |file| File.basename(file) }
+
+  gem.add_dependency 'sinatra', '~> 1.4'
+  gem.add_dependency 'httpclient'
+  gem.add_dependency 'opener-webservice'
+  gem.add_dependency 'nokogiri'
+
+  gem.add_development_dependency 'opener-build-tools'
+  gem.add_development_dependency 'rake'
+end

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: opener-ned
+version: !ruby/object:Gem::Version
+  version: 2.0.0
+platform: ruby
+authors:
+- development@olery.com
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2014-05-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: sinatra
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: httpclient
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: opener-webservice
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: opener-build-tools
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rake
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :development
+description: NED client using DBpedia
+email:
+executables:
+- ned-server
+- ned
+extensions: []
+extra_rdoc_files: []
+files:
+- core/target/ehu-ned-1.0.jar
+- lib/opener/ned.rb
+- lib/opener/ned/version.rb
+- lib/opener/ned/server.rb
+- lib/opener/ned/cli.rb
+- lib/opener/ned/public/markdown.css
+- lib/opener/ned/views/index.erb
+- opener-ned.gemspec
+- config.ru
+- README.md
+- bin/ned-server
+- bin/ned
+homepage:
+licenses: []
+metadata: {}
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: 1.9.2
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: NED client using DBpedia
+test_files: []
+has_rdoc: yard