opener-ner 2.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 8bb73b77467d92bf3cabce1ebaa94ba05ef0838e
+  data.tar.gz: 9756f377742951dc077446ddfb189b160c3a5874
+SHA512:
+  metadata.gz: 568efc611a6a4a11184ed6c7172658b370b858c58632894280b0544b5e5514d76ccd6cc3f2f2a416ef43bc9a41b545e876fb6efdaa842547f64065287c0a2da3
+  data.tar.gz: 2263ffdcebf1b5f91240ea595901baf6ad368040adde94dc3e200bbf74859f30e1b172ffa3c02950be7ac46ee972a9acf4a4f33962a4a7c4cf4af403152e8c0c

data/README.md

@@ -0,0 +1,29 @@
+# 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.
+
+## Requirements
+
+* Ruby 1.9.2 or newer
+* Bundler
+
+## Installation
+
+As a regular Ruby Gem:
+
+    gem install opener-ner
+
+
+Using Bundler:
+
+    gem 'opener-ner',
+      :git    => 'git@github.com:opener-project/ner.git',
+      :branch => 'master'
+
+Using specific install:
+
+    gem install specific_install
+    gem specific_install opener-ner \
+        -l https://github.com/opener-project/ner.git

data/bin/ner

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

data/bin/ner-server

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+require 'rack'
+
+# 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/ner', __FILE__)
+require File.expand_path('../lib/opener/ner/server', __FILE__)
+
+run Opener::Ner::Server

data/lib/opener/ner.rb

@@ -0,0 +1,95 @@
+require 'optparse'
+require 'opener/ners/base'
+require 'nokogiri'
+
+require_relative 'ner/version'
+require_relative 'ner/cli'
+
+module Opener
+  ##
+  # Primary NER class that takes care of delegating NER actions to the language
+  # specific kernels.
+  #
+  # @!attribute [r] options
+  #  @return [Hash]
+  #
+  class Ner
+    attr_reader :options
+
+    ##
+    # The default language to use when no custom one is specified.
+    #
+    # @return [String]
+    #
+    DEFAULT_LANGUAGE = 'en'.freeze
+
+    ##
+    # Hash containing the default options to use.
+    #
+    # @return [Hash]
+    #
+    DEFAULT_OPTIONS = {
+      :args     => [],
+      :language => DEFAULT_LANGUAGE
+    }.freeze
+
+    ##
+    # @param [Hash] options
+    #
+    # @option options [Array] :args Collection of arbitrary arguments to pass
+    #  to the underlying kernels.
+    # @option options [String] :language The language to use.
+    #
+    def initialize(options = {})
+      @options = DEFAULT_OPTIONS.merge(options)
+    end
+
+    ##
+    # Processes the input and returns an array containing the output of STDOUT,
+    # STDERR and an object containing process information.
+    #
+    # @param [String] input
+    # @return [Array]
+    #
+    def run(input)
+      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
+
+      return kernel.run(input)
+    end
+
+    protected
+
+    ##
+    # Returns `true` if the current language has a dedicated kernel class.
+    #
+    # @return [TrueClass|FalseClass]
+    #
+    def language_constant_defined?(language)
+      return language && Ners.const_defined?(language.upcase)
+    end
+
+    ##
+    # @return [Class]
+    #
+    def language_constant(language)
+      return Ners.const_get(language.upcase)
+    end
+
+    ##
+    # @param [String] input
+    # @return [String]
+    #
+    def language_from_kaf(input)
+      reader = Nokogiri::XML::Reader(input)
+
+      return reader.read.lang
+    end
+  end # Ner
+end # Opener

data/lib/opener/ner/cli.rb

@@ -0,0 +1,88 @@
+module Opener
+  class Ner
+    ##
+    # CLI wrapper around {Opener::Ner} 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   = 'ner'
+          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(
+            '-l',
+            '--language [VALUE]',
+            'Uses this specific language'
+          ) do |value|
+            @options[:language] = value
+          end
+
+          opts.separator <<-EOF
+
+Examples:
+
+  cat example.kaf | #{opts.program_name} -l en
+
+Languages:
+
+  Ner will try to detect the language of the KAF file if no language is given.
+
+  * Dutch (nl)
+  * English (en)
+  * French (fr)
+  * German (de)
+  * Italian (it)
+  * Spanish (es)
+          EOF
+        end
+      end
+
+      ##
+      # @param [String] input
+      #
+      def run(input)
+        option_parser.parse!(options[:args])
+
+        ner = Ner.new(options)
+
+        return ner.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 # Ner
+end # Opener

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

@@ -0,0 +1,283 @@
+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/ner/server.rb

@@ -0,0 +1,16 @@
+require 'sinatra/base'
+require 'opener/webservice'
+require 'httpclient'
+
+module Opener
+  class Ner
+    ##
+    # NER server powered by Sinatra.
+    #
+    class Server < Webservice
+      set :views, File.expand_path('../views', __FILE__)
+      text_processor Ner
+      accepted_params :input
+    end # Server
+  end # Ner
+end # Opener

data/lib/opener/ner/version.rb

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

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

@@ -0,0 +1,71 @@
+<!DOCTYPE html>
+<html>
+    <head>
+        <link type="text/css" rel="stylesheet" href="markdown.css" />
+
+        <title>NER Webservice</title>
+    </head>
+    <body>
+        <h1>NER 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>
+            <% 10.times do |t| %>
+            <div>
+              <label for="callbacks">Callback URL <%=t+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>language</dt>
+            <dd>The language (code) to use, e.g. "en" or "fr".</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>
+        </dl>
+    </body>
+</html>

data/opener-ner.gemspec

@@ -0,0 +1,29 @@
+require File.expand_path('../lib/opener/ner/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.name        = 'opener-ner'
+  gem.version     = Opener::Ner::VERSION
+  gem.authors     = ['development@olery.com']
+  gem.summary     = 'Primary NER component that wraps the various NER kernels.'
+  gem.description = gem.summary
+  gem.has_rdoc    = 'yard'
+
+  gem.required_ruby_version = '>= 1.9.2'
+
+  gem.files = Dir.glob([
+    'lib/**/*',
+    'config.ru',
+    '*.gemspec',
+    '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 'nokogiri'
+  gem.add_dependency 'opener-ner-base'
+  gem.add_dependency 'opener-webservice'
+
+  gem.add_development_dependency 'rake'
+end

metadata

@@ -0,0 +1,140 @@
+--- !ruby/object:Gem::Specification
+name: opener-ner
+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
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: httpclient
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: opener-ner-base
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: opener-webservice
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  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: Primary NER component that wraps the various NER kernels.
+email: 
+executables:
+- ner
+- ner-server
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- bin/ner
+- bin/ner-server
+- config.ru
+- lib/opener/ner.rb
+- lib/opener/ner/cli.rb
+- lib/opener/ner/public/markdown.css
+- lib/opener/ner/server.rb
+- lib/opener/ner/version.rb
+- lib/opener/ner/views/index.erb
+- opener-ner.gemspec
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Primary NER component that wraps the various NER kernels.
+test_files: []
+has_rdoc: yard