stanfordparser-infochimps 2.2.1.s

data/lib/stanfordparser/java_object.rb

@@ -0,0 +1,129 @@
+# Copyright 2007-2008 William Patrick McNeill
+#
+# This file is part of the Stanford Parser Ruby Wrapper.
+#
+# The Stanford Parser Ruby Wrapper is free software; you can redistribute it
+# and/or modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the License,
+# or (at your option) any later version.
+#
+# The Stanford Parser Ruby Wrapper is distributed in the hope that it will be
+# useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
+# Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# editalign; if not, write to the Free Software Foundation, Inc., 51 Franklin
+# St, Fifth Floor, Boston, MA 02110-1301 USA
+
+# Extenions to the {Ruby-Java Bridge}[http://rjb.rubyforge.org/] module that
+# add a generic Java object wrapper class.
+module Rjb
+
+  #--
+  # The documentation for this class appears next to its extension inside the
+  # StanfordParser module in stanfordparser.rb.  This should be changed if Rjb
+  # is ever moved into its own gem.  See the documention in stanfordparser.rb
+  # for more details.  
+  #++
+  class JavaObjectWrapper
+    include Enumerable
+
+    # The underlying Java object.
+    attr_reader :java_object
+
+    # Initialize with a Java object <em>obj</em>.  If <em>obj</em> is a
+    # String, treat it as a Java class name and instantiate it.  Otherwise,
+    # treat <em>obj</em> as an instance of a Java object.
+    def initialize(obj, *args)
+      @java_object = obj.class == String ?
+      Rjb::import(obj).send(:new, *args) : obj
+    end
+
+    # Enumerate all the items in the object using its iterator.  If the object
+    # has no iterator, this function yields nothing.
+    def each
+      if @java_object.getClass.getMethods.any? {|m| m.getName == "iterator"}
+        i = @java_object.iterator
+        while i.hasNext
+          yield wrap_java_object(i.next)
+        end
+      end
+    end # each
+
+    # Reflect unhandled method calls to the underlying Java object and wrap
+    # the return value in the appropriate Ruby object.
+    def method_missing(m, *args)
+      begin
+        wrap_java_object(@java_object.send(m, *args))
+      rescue RuntimeError => e
+        # The instance method failed.  See if this is a static method.
+        if not e.message.match(/^Fail: unknown method name/).nil?
+          getClass.send(m, *args)
+        end
+      end
+    end
+
+    # Convert a value returned by a call to the underlying Java object to the
+    # appropriate Ruby object.
+    #
+    # If the value is a JavaObjectWrapper, convert it using a protected
+    # function with the name wrap_ followed by the underlying object's
+    # classname with the Java path delimiters converted to underscores. For
+    # example, a <tt>java.util.ArrayList</tt> would be converted by a function
+    # called wrap_java_util_ArrayList.
+    #
+    # If the value lacks the appropriate converter function, wrap it in a
+    # generic JavaObjectWrapper.
+    #
+    # If the value is not a JavaObjectWrapper, return it unchanged.
+    #
+    # This function is called recursively for every element in an Array.
+    def wrap_java_object(object)
+      if object.kind_of?(Array)
+        object.collect {|item| wrap_java_object(item)}
+      elsif object.respond_to?(:_classname)
+        # Ruby-Java Bridge Java objects all have a _classname member which
+        # tells the name of their Java class.  Convert this to the
+        # corresponding wrapper function name.
+        wrapper_name = ("wrap_" + object._classname.gsub(/\./, "_")).to_sym
+        respond_to?(wrapper_name) ? send(wrapper_name, object) : JavaObjectWrapper.new(object)
+      else
+        object
+      end
+    end
+
+    # Convert <tt>java.util.ArrayList</tt> objects to Ruby Array objects.
+    def wrap_java_util_ArrayList(object)
+      array_list = []
+      object.size.times do
+        |i| array_list << wrap_java_object(object.get(i))
+      end
+      array_list
+    end
+
+    # Convert <tt>java.util.HashSet</tt> objects to Ruby Set objects.
+    def wrap_java_util_HashSet(object)
+      set = Set.new
+      i = object.iterator
+      while i.hasNext
+        set << wrap_java_object(i.next)
+      end
+      set
+    end
+
+    # Show the classname of the underlying Java object.
+    def inspect
+      "<#{@java_object._classname}>"
+    end
+
+    # Use the underlying Java object's stringification.
+    def to_s
+      toString
+    end
+
+    protected :wrap_java_object, :wrap_java_util_ArrayList, :wrap_java_util_HashSet
+
+  end # JavaObjectWrapper
+
+end # Rjb

data/stanfordparser.gemspec

@@ -0,0 +1,69 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run the gemspec command
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{stanfordparser}
+  s.version = "2.2.1.s"
+
+  s.required_rubygems_version = Gem::Requirement.new("> 1.3.1") if s.respond_to? :required_rubygems_version=
+  s.authors = ["John Wilkinson", "Bill McNeal"]
+  s.date = %q{2010-06-21}
+  s.description = %q{Ruby wrapper of the Stanford Parser, a NLP parser built in Java.}
+  s.email = %q{jcwilk@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.orig",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.orig",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION.yml",
+     "examples/connection_finder.rb",
+     "examples/stanford-sentence-parser.rb",
+     "lib/stanfordparser.rb",
+     "lib/stanfordparser/java_object.rb",
+     "spec/spec.opts",
+     "spec/spec_helper.rb",
+     "spec/stanfordparser_spec.rb",
+     "test/test_stanfordparser.rb"
+  ]
+  s.homepage = %q{http://github.com/jcwilk/stanfordparser}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{GitHub upload/extension of Bill McNeal's stanfordparser rubygem}
+  s.test_files = [
+    "spec/spec_helper.rb",
+     "spec/stanfordparser_spec.rb",
+     "test/test_stanfordparser.rb",
+     "examples/connection_finder.rb",
+     "examples/stanford-sentence-parser.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<rjb>, [">= 1.2.5"])
+      s.add_runtime_dependency(%q<treebank>, [">= 3.0.0"])
+      s.add_development_dependency(%q<rspec>, [">= 1.2.9"])
+    else
+      s.add_dependency(%q<rjb>, [">= 1.2.5"])
+      s.add_dependency(%q<treebank>, [">= 3.0.0"])
+      s.add_dependency(%q<rspec>, [">= 1.2.9"])
+    end
+  else
+    s.add_dependency(%q<rjb>, [">= 1.2.5"])
+    s.add_dependency(%q<treebank>, [">= 3.0.0"])
+    s.add_dependency(%q<rspec>, [">= 1.2.9"])
+  end
+end
+

data/test/test_stanfordparser.rb

@@ -0,0 +1,224 @@
+#!/bin/env ruby
+
+#--
+
+# Copyright 2007-2008 William Patrick McNeill
+#
+# This file is part of the Stanford Parser Ruby Wrapper.
+#
+# The Stanford Parser Ruby Wrapper is free software; you can redistribute it
+# and/or modify it under the terms of the GNU General Public License as
+# published by the Free Software Foundation; either version 2 of the License,
+# or (at your option) any later version.
+#
+# The Stanford Parser Ruby Wrapper is distributed in the hope that it will be
+# useful, but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General
+# Public License for more details.
+#
+# You should have received a copy of the GNU General Public License along with
+# editalign; if not, write to the Free Software Foundation, Inc., 51 Franklin
+# St, Fifth Floor, Boston, MA 02110-1301 USA
+#
+#++
+
+# Test cases for the Stanford Parser module
+
+require "test/unit"
+require "set"
+require "singleton"
+require "stanfordparser"
+
+
+class LexicalizedParserTestCase < Test::Unit::TestCase
+  def test_root_path
+    assert_equal StanfordParser::ROOT.class, Pathname
+  end
+
+  def setup
+    @parser = StanfordParser::DefaultParser.instance
+    @tree = @parser.apply("This is a sentence.")
+  end
+
+  def test_parser
+    assert_equal @parser.grammar, StanfordParser::ROOT + "englishPCFG.ser.gz"
+    assert_equal @tree.class, StanfordParser::Tree
+  end
+
+  def test_localTrees
+    # The following call exercises the conversion from java.util.HashSet
+    # objects to Ruby sets.
+    l = @tree.localTrees
+    assert_equal l.size, 5
+    assert_equal Set.new(l.collect {|t| "#{t.label}"}),
+                 Set.new(["S", "NP", "VP", "ROOT", "NP"])
+  end
+
+  def test_enumerable
+    # StanfordParser::LexicalizedParser is not an enumerable object.
+    assert_equal @parser.map, []
+  end
+end # LexicalizedParserTestCase
+
+
+class TreeTestCase < Test::Unit::TestCase
+  def setup
+    @parser = StanfordParser::DefaultParser.instance
+    @tree = @parser.apply("This is a sentence.")
+  end
+
+  def test_enumerable
+    assert @tree.all? {|n| n.class == StanfordParser::Tree}
+    assert @tree.all? {|n|
+      n._classname == "edu.stanford.nlp.trees.LabeledScoredTreeNode" or
+      n._classname == "edu.stanford.nlp.trees.LabeledScoredTreeLeaf"
+    }
+    assert_equal @tree.map {|n| "#{n.label}"},
+      ["ROOT", "S", "NP", "DT", "This", "VP", "VBZ", "is", "NP", "DT", "a", \
+       "NN", "sentence", ".", "."]
+  end
+end # TreeTestCase
+
+
+class FeatureLabelTestCase < Test::Unit::TestCase
+  def test_feature_label
+    f = StanfordParser::FeatureLabel.new
+    assert_equal "BEGIN_POS", f.BEGIN_POSITION_KEY
+    f.put(f.BEGIN_POSITION_KEY, 3)
+    assert_equal "END_POS", f.END_POSITION_KEY
+    f.put(f.END_POSITION_KEY, 7)
+    assert_equal "current", f.CURRENT_KEY
+    f.put(f.CURRENT_KEY, "word")
+    assert_equal "{BEGIN_POS=3, END_POS=7, current=word}", f.inspect
+    assert_equal "word [3,7]", f.to_s
+  end
+end
+
+
+class DocumentPreprocessorTestCase < Test::Unit::TestCase
+  def setup
+    @preproc = StanfordParser::DocumentPreprocessor.new
+    @standoff_preproc = StanfordParser::StandoffDocumentPreprocessor.new
+  end
+
+  def test_get_sentences_from_string
+    # The following call exercises the conversion from java.util.ArrayList
+    # objects to Ruby arrays.
+    s = @preproc.getSentencesFromString("This is a sentence.  So is this.")
+    assert_equal "#{s[0]}", "This is a sentence ."
+    assert_equal "#{s[1]}", "So is this ."
+  end
+
+  def test_enumerable
+    # StanfordParser::DocumentPreprocessor is not an enumerable object.
+    assert_equal @preproc.map, []
+  end
+
+  # Segment and tokenize text containing two sentences.
+  def test_standoff_document_preprocessor
+    sentences = @standoff_preproc.getSentencesFromString("He (John) is tall.  So is she.")
+    # Recognize two sentences.
+    assert_equal 2, sentences.length
+    assert sentences.all? {|sentence| sentence.instance_of? StanfordParser::StandoffSentence}
+    assert_equal "He (John) is tall.", sentences.first.to_s
+    assert_equal 7, sentences.first.length
+    assert sentences[0].all? {|token| token.instance_of? StanfordParser::StandoffToken}
+    assert_equal "So is she.", sentences.last.to_s
+    assert_equal 4, sentences.last.length
+    assert sentences[1].all? {|token| token.instance_of? StanfordParser::StandoffToken}
+    # Get the correct token information for the first sentence.
+    assert_equal ["He", "He"], [sentences[0][0].current(), sentences[0][0].word()]
+    assert_equal [0,2],        [sentences[0][0].begin_position(), sentences[0][0].end_position()]
+    assert_equal ["(", "-LRB-"], [sentences[0][1].current(), sentences[0][1].word()]
+    assert_equal [3,4],          [sentences[0][1].begin_position(), sentences[0][1].end_position()]
+    assert_equal ["John", "John"], [sentences[0][2].current(), sentences[0][2].word()]
+    assert_equal [4,8],            [sentences[0][2].begin_position(), sentences[0][2].end_position()]
+    assert_equal [")", "-RRB-"], [sentences[0][3].current(), sentences[0][3].word()]
+    assert_equal [8,9],          [sentences[0][3].begin_position(), sentences[0][3].end_position()]
+    assert_equal ["is", "is"], [sentences[0][4].current(), sentences[0][4].word()]
+    assert_equal [10,12],      [sentences[0][4].begin_position(), sentences[0][4].end_position()]
+    assert_equal ["tall", "tall"], [sentences[0][5].current(), sentences[0][5].word()]
+    assert_equal [13,17],          [sentences[0][5].begin_position(), sentences[0][5].end_position()]
+    assert_equal [".", "."], [sentences[0][6].current(), sentences[0][6].word()]
+    assert_equal [17,18],    [sentences[0][6].begin_position(), sentences[0][6].end_position()]
+    # Get the correct token information for the second sentence.
+    assert_equal ["So", "So"], [sentences[1][0].current(), sentences[1][0].word()]
+    assert_equal [20,22],      [sentences[1][0].begin_position(), sentences[1][0].end_position()]
+    assert_equal ["is", "is"], [sentences[1][1].current(), sentences[1][1].word()]
+    assert_equal [23,25],      [sentences[1][1].begin_position(), sentences[1][1].end_position()]
+    assert_equal ["she", "she"], [sentences[1][2].current(), sentences[1][2].word()]
+    assert_equal [26,29],        [sentences[1][2].begin_position(), sentences[1][2].end_position()]
+    assert_equal [".", "."], [sentences[1][3].current(), sentences[1][3].word()]
+    assert_equal [29,30],    [sentences[1][3].begin_position(), sentences[1][3].end_position()]
+  end
+
+  def test_stringification
+    assert_equal "<DocumentPreprocessor>", @preproc.inspect
+    assert_equal "<DocumentPreprocessor>", @preproc.to_s
+    assert_equal "<StandoffDocumentPreprocessor>", @standoff_preproc.inspect
+    assert_equal "<StandoffDocumentPreprocessor>", @standoff_preproc.to_s
+  end
+
+end # DocumentPreprocessorTestCase
+
+
+class StandoffParsedTextTestCase < Test::Unit::TestCase
+  def setup
+    @text = "He (John) is tall.  So is she."
+  end
+
+  def test_parse_text_default_nodetype
+    parsed_text = StanfordParser::StandoffParsedText.new(@text)
+    verify_parsed_text(parsed_text, StanfordParser::StandoffNode)
+  end
+
+  # Verify correct parsing with variable node types for text containing two sentences.
+  def verify_parsed_text(parsed_text, nodetype)
+    # Verify that there are two sentences.
+    assert_equal 2, parsed_text.length
+    assert parsed_text.all? {|sentence| sentence.instance_of? nodetype}
+    # Verify the tokens in the leaf node of the first sentence.
+    leaves = parsed_text[0].leaves.collect {|node| node.label}
+    assert_equal ["He", "He"], [leaves[0].current(), leaves[0].word()]
+    assert_equal [0,2],        [leaves[0].begin_position(), leaves[0].end_position()]
+    assert_equal ["(", "-LRB-"], [leaves[1].current(), leaves[1].word()]
+    assert_equal [3,4],          [leaves[1].begin_position(), leaves[1].end_position()]
+    assert_equal ["John", "John"], [leaves[2].current(), leaves[2].word()]
+    assert_equal [4,8],            [leaves[2].begin_position(), leaves[2].end_position()]
+    assert_equal [")", "-RRB-"], [leaves[3].current(), leaves[3].word()]
+    assert_equal [8,9],          [leaves[3].begin_position(), leaves[3].end_position()]
+    assert_equal ["is", "is"], [leaves[4].current(), leaves[4].word()]
+    assert_equal [10,12],      [leaves[4].begin_position(), leaves[4].end_position()]
+    assert_equal ["tall", "tall"], [leaves[5].current(), leaves[5].word()]
+    assert_equal [13,17],          [leaves[5].begin_position(), leaves[5].end_position()]
+    assert_equal [".", "."], [leaves[6].current(), leaves[6].word()]
+    assert_equal [17,18],    [leaves[6].begin_position(), leaves[6].end_position()]
+    # Verify the tokens in the leaf node of the second sentence.
+    leaves = parsed_text[1].leaves.collect {|node| node.label}
+    assert_equal ["So", "So"], [leaves[0].current(), leaves[0].word()]
+    assert_equal [20,22],      [leaves[0].begin_position(), leaves[0].end_position()]
+    assert_equal ["is", "is"], [leaves[1].current(), leaves[1].word()]
+    assert_equal [23,25],      [leaves[1].begin_position(), leaves[1].end_position()]
+    assert_equal ["she", "she"], [leaves[2].current(), leaves[2].word()]
+    assert_equal [26,29],        [leaves[2].begin_position(), leaves[2].end_position()]
+    assert_equal [".", "."], [leaves[3].current(), leaves[3].word()]
+    assert_equal [29,30],    [leaves[3].begin_position(), leaves[3].end_position()]
+    # Verify that the original string is recoverable.
+    assert_equal "He (John) is tall.  ", parsed_text[0].to_original_string
+    assert_equal "So is she."          , parsed_text[1].to_original_string
+    # Draw < and > brackets around 3 constituents.
+    b = parsed_text[0].to_bracketed_string([[0,0], [0,0,1,1], [0,1,1]], "<", ">")
+    assert_equal "<He (<John>)> is <tall>.  ", b
+  end
+end
+
+
+class MiscPreprocessorTestCase < Test::Unit::TestCase
+  def test_model_location
+    assert_equal "$(ROOT)/englishPCFG.ser.gz", StanfordParser::ENGLISH_PCFG_MODEL
+  end
+
+  def test_word
+    assert StanfordParser::Word.new("edu.stanford.nlp.ling.Word", "dog") ==  "dog"
+  end
+end # MiscPreprocessorTestCase

metadata

@@ -0,0 +1,207 @@
+--- !ruby/object:Gem::Specification 
+name: stanfordparser-infochimps
+version: !ruby/object:Gem::Version 
+  hash: 12
+  prerelease: 6
+  segments: 
+  - 2
+  - 2
+  - 1
+  - s
+  version: 2.2.1.s
+platform: ruby
+authors: 
+- John Wilkinson
+- Bill McNeal
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2011-01-27 00:00:00 -06:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  requirement: *id001
+  prerelease: false
+  name: rjb
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  requirement: *id002
+  prerelease: false
+  name: rake
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  requirement: *id003
+  prerelease: false
+  name: jeweler
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 7
+        segments: 
+        - 3
+        - 0
+        - 0
+        version: 3.0.0
+  requirement: *id004
+  prerelease: false
+  name: treebank
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 13
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  requirement: *id005
+  prerelease: false
+  name: rspec
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id006 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 21
+        segments: 
+        - 1
+        - 2
+        - 5
+        version: 1.2.5
+  requirement: *id006
+  prerelease: false
+  name: rjb
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id007 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 7
+        segments: 
+        - 3
+        - 0
+        - 0
+        version: 3.0.0
+  requirement: *id007
+  prerelease: false
+  name: treebank
+  type: :runtime
+- !ruby/object:Gem::Dependency 
+  version_requirements: &id008 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 13
+        segments: 
+        - 1
+        - 2
+        - 9
+        version: 1.2.9
+  requirement: *id008
+  prerelease: false
+  name: rspec
+  type: :development
+description: Ruby wrapper of the Stanford Parser, a NLP parser built in Java.
+email: jcwilk@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.orig.rdoc
+- README.rdoc
+files: 
+- .document
+- Gemfile
+- LICENSE
+- README.orig.rdoc
+- README.rdoc
+- Rakefile
+- TESTS_STATUS.rdoc
+- VERSION.yml
+- examples/stanford-sentence-parser.rb
+- lib/stanfordparser.rb
+- lib/stanfordparser/java_object.rb
+- stanfordparser.gemspec
+- test/test_stanfordparser.rb
+has_rdoc: true
+homepage: http://github.com/jcwilk/stanfordparser
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">"
+    - !ruby/object:Gem::Version 
+      hash: 25
+      segments: 
+      - 1
+      - 3
+      - 1
+      version: 1.3.1
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.4.2
+signing_key: 
+specification_version: 3
+summary: GitHub upload/extension of Bill McNeal's stanfordparser rubygem
+test_files: 
+- examples/stanford-sentence-parser.rb
+- test/test_stanfordparser.rb