opener-constituent-parser-base 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 8daa009b3c65632398a5b77dbbe75e6c4d38968c
+  data.tar.gz: 4e446f65248f01b84bd82e666542272b2c22fef7
+SHA512:
+  metadata.gz: afabc3b04933f70e811278cb4fee2460c19cebf591779db2358310c79920578e28905bc15b633756035a13ebbc2907bbdfdb364cfa75be9c606d190f9807c508
+  data.tar.gz: 1a6ae1e2eff88c2e918ef57a0e7a13176f6ee7a8eedd122b1199e179b588d8f00efcfc6d070f4c4a6a179829eb05e0556c9647d9093aaefdbf6c88e733911efc

data/README.md

@@ -0,0 +1,79 @@
+[![Build Status](https://drone.io/github.com/opener-project/constituent-parser-base/status.png)](https://drone.io/github.com/opener-project/constituent-parser-base/latest)
+
+# Constituent Base Parsers
+
+This repository contains the source code of the base constituent parser which
+supports the following languages:
+
+* English
+* Spanish
+* Italian
+
+The parser takes KAF documents (with <wf> elements as it needs tokenized text)
+as standard input and outputs constituent syntactic analysis in treebank
+format, one sentence per line. It also provides an option of outputting the
+constituent heads, as defined by Collins PhD thesis.
+
+## Requirements
+
+* Java 1.7 or newer
+* Ruby 1.9.2 or newer
+
+Development requirements:
+
+* Maven
+* Bundler
+
+## Installation
+
+Installing as a regular Gem:
+
+    gem install opener-constituent-parser-base
+
+Using Bundler:
+
+    gem 'opener-constituent-parser-base',
+      :git    => 'git@github.com:opener-project/constituent-parser-base.git',
+      :branch => 'master'
+
+Using specific install:
+
+    gem install specific_install
+    gem specific_install opener-constituent-parser-base \
+       -l https://github.com/opener-project/constituent-parser-base.git
+
+## Usage
+
+    cat some_input_file.kaf | constituent-parser-base
+
+## 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.
+
+## Testing
+
+To run the tests (which are powered by Cucumber), simply run the following:
+
+    bundle exec rake
+
+This will take care of verifying the requirements, installing the required Java
+packages and running the tests.
+
+For more information on the available Rake tasks run the following:
+
+    bundle exec rake -T
+
+## 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/constituent-parser-en

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/constituent_parsers/base'
+
+kernel = Opener::ConstituentParsers::Base.new(:args => ARGV, :language => 'en')
+input  = STDIN.tty? ? nil : STDIN.read
+
+kernel.run!(input)

data/bin/constituent-parser-es

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/constituent_parsers/base'
+
+kernel = Opener::ConstituentParsers::Base.new(:args => ARGV, :language => 'es')
+input  = STDIN.tty? ? nil : STDIN.read
+
+kernel.run!(input)

data/bin/constituent-parser-fr

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/constituent_parsers/base'
+
+kernel = Opener::ConstituentParsers::Base.new(:args => ARGV, :language => 'fr')
+input  = STDIN.tty? ? nil : STDIN.read
+
+kernel.run!(input)

data/bin/constituent-parser-it

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/opener/constituent_parsers/base'
+
+kernel = Opener::ConstituentParsers::Base.new(:args => ARGV, :language => 'it')
+input  = STDIN.tty? ? nil : STDIN.read
+
+kernel.run!(input)

data/lib/opener/constituent_parsers/base.rb

@@ -0,0 +1,96 @@
+require 'open3'
+require 'stringio'
+
+require 'java'
+require  File.expand_path('../../../../core/target/ehu-parse-1.0.jar', __FILE__)
+
+import 'ehu.parse.Annotate'
+import 'ixa.kaflib.KAFDocument'
+import 'java.io.InputStreamReader'
+import 'ehu.heads.CollinsHeadFinder'
+
+require_relative 'base/version'
+
+module Opener
+  module ConstituentParsers
+    ##
+    # The base constituent parser kernel that supports multiple languages such
+    # as English and Spanish.
+    #
+    # @!attribute [r] args
+    #  @return [Array]
+    # @!attribute [r] options
+    #  @return [Hash]
+    #
+    class Base
+      attr_reader :args, :options
+
+      ##
+      # The default language to use.
+      #
+      # @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 The commandline arguments to pass to the
+      #  underlying Java code.
+      #
+      # @see Opener::ConstituentParsers::DEFAULT_OPTIONS
+      #
+      def initialize(options = {})
+        options  = DEFAULT_OPTIONS.merge(options)
+        @args    = options.delete(:args) || []
+        @options = options
+      end
+
+      ##
+      # Runs the command and returns the output of STDOUT, STDERR and the
+      # process information.
+      #
+      # @param [String] input The input to process.
+      # @return [Array]
+      #
+      def run(input)
+        input     = StringIO.new(input) unless input.kind_of?(IO)
+        annotator = Java::ehu.parse.Annotate.new(language)
+        reader    = InputStreamReader.new(input.to_inputstream)
+        kaf       = KAFDocument.create_from_stream(reader)
+        kaf.add_linguistic_processor("constituents","ehu-parse-"+language,"now","1.0")
+
+        if heads?
+          head_finder = CollinsHeadFinder.new(language)
+          annotator.parseWithHeads(kaf, head_finder)
+        else
+          annotator.parse(kaf)
+        end
+
+        return kaf.to_string
+      end
+      #
+      ##
+      # @return [String]
+      #
+      def language
+        return options[:language]
+      end
+
+      def heads?
+        true
+      end
+
+    end # Base
+  end # ConstituentParsers
+end # Opener

data/lib/opener/constituent_parsers/base/version.rb

@@ -0,0 +1,7 @@
+module Opener
+  module ConstituentParsers
+    class Base
+      VERSION = '1.0.0'
+    end # Base
+  end # ConstituentParsers
+end # Opener

data/opener-constituent-parser-base.gemspec

@@ -0,0 +1,29 @@
+require File.expand_path(
+  '../lib/opener/constituent_parsers/base/version',
+  __FILE__
+)
+
+Gem::Specification.new do |gem|
+  gem.name        = 'opener-constituent-parser-base'
+  gem.version     = Opener::ConstituentParsers::Base::VERSION
+  gem.authors     = ['development@olery.com']
+  gem.summary     = 'Constituent parser that supports various languages.'
+  gem.description = gem.summary
+  gem.has_rdoc    = 'yard'
+
+  gem.required_ruby_version = '>= 1.9.2'
+
+  gem.files = Dir.glob([
+    'core/target/ehu-parse-*.jar',
+    'lib/**/*.*',
+    '*.gemspec',
+    'README.md'
+  ])
+
+  gem.executables = Dir.glob('bin/*').map { |f| File.basename(f) }
+
+  gem.add_development_dependency 'opener-build-tools'
+  gem.add_development_dependency 'rspec'
+  gem.add_development_dependency 'cucumber'
+  gem.add_development_dependency 'rake'
+end

metadata

@@ -0,0 +1,112 @@
+--- !ruby/object:Gem::Specification
+name: opener-constituent-parser-base
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+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: 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: rspec
+  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: cucumber
+  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: Constituent parser that supports various languages.
+email:
+executables:
+- constituent-parser-fr
+- constituent-parser-en
+- constituent-parser-es
+- constituent-parser-it
+extensions: []
+extra_rdoc_files: []
+files:
+- core/target/ehu-parse-1.0.jar
+- lib/opener/constituent_parsers/base.rb
+- lib/opener/constituent_parsers/base/version.rb
+- opener-constituent-parser-base.gemspec
+- README.md
+- bin/constituent-parser-fr
+- bin/constituent-parser-en
+- bin/constituent-parser-es
+- bin/constituent-parser-it
+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: Constituent parser that supports various languages.
+test_files: []
+has_rdoc: yard