uea-stemmer 0.9.10

data/.document

@@ -0,0 +1,5 @@
+README.rdoc
+lib/**/*.rb
+bin/*
+features/**/*.feature
+LICENSE

data/.gitignore

@@ -0,0 +1,6 @@
+*.sw?
+.DS_Store
+coverage
+rdoc
+pkg
+*.tmproj

data/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

data/README.rdoc

@@ -0,0 +1,73 @@
+= uea-stemmer
+
+Similar to other stemmers, UEA-Lite[http://www.uea.ac.uk/cmp/research/graphicsvisionspeech/speech/WordStemming] operates on a set of rules which are used as steps. There are two groups of rules: the first to clean the tokens, and the second to alter suffixes.
+
+The first group of rules first avoids a small list of six frequent problem words. An improvement to the stemmer would be to expand this list by adding other problem words which the second rule set cannot deal with. Second, possessive apostrophes are removed and contractions are expanded. All hyphens are removed and tokens containing digits are left untouched. Strings which are all upper case and digits are left untouched unless there is a lower case terminal 's' (i.e. transforming plural forms of acronyms to singular forms).
+
+Proper nouns should not usually be stemmed, except to remove possessives; our implementation will respect PoS tags if they are present. If the text is untagged the stemmer uses the simple heuristic that any capitalized token not preceded by sentence breaking punctuation is a proper noun.
+
+Many texts, particularly scientific papers, contain sequences of digits, single letters, and other non-word tokens. Our implementation ignores tokens containing digits, single-letter tokens, and tokens with embedded punctuation.
+
+The second group of rules contains 139 suffix rules, each testing for a specific type of suffix. The rules are set in a particular order so that the longest suffix applicable is used rather a shorter one which could lead to nonsense words and more words not stemmed entirely to their root form.
+
+This is a port to Ruby from the port to Java from the original Perl script by Marie-Claire Jenkins and Dr. Dan J. Smith at the University of East Anglia.
+
+== Installation
+
+Install the gem via Github:
+
+  gem sources -a http://gems.github.com   # only need to do this once
+  sudo gem install ealdent-uea-stemmer
+
+Install the gem from source:
+
+  git clone git://github.com/ealdent/uea-stemmer.git
+  cd uea-stemmer
+  rake install
+
+== Example Usage
+
+Typical usage:
+
+  require 'uea-stemmer'
+  stemmer = UEAStemmer.new
+
+  stemmer.stem('helpers')   # helper
+  stemmer.stem('dying')     # die
+  stemmer.stem('scarred')   # scar
+
+  'buries'.stem             # bury
+  'bodies'.stem             # body
+  'ordained'.stem           # ordain
+
+You can also extract the stemmed word along with the rule by using the `stem_with_rule` method.
+
+  stem = stemmer.stem_with_rule('invited')   # Word('invite', Rule #22.3)
+  puts stem.rule  # rule #22.3 (remove -d when the word ends in -ited)
+
+== TODO
+
+* test handling of POS tags
+* add tests to mimic methodology used in the paper
+
+== Note on Patches/Pull Requests
+
+* Fork the project.
+* Make your feature addition or bug fix.
+* Add tests for it. This is important so I don't break it in a
+  future version unintentionally.
+* Commit, do not mess with rakefile, version, or history.
+  (if you want to have your own version, that is fine but bump version in a commit by itself I can ignore when I pull)
+* Send me a pull request. Bonus points for topic branches.
+
+== Relevant Web Pages
+
+* http://www.uea.ac.uk/cmp/research/graphicsvisionspeech/speech/WordStemming
+* Stemming[http://en.wikipedia.org/wiki/Stemming]
+
+== Copyright
+
+Copyright (c) 2005 by the University of East Anglia and authored by Marie-Claire Jenkins and Dr. Dan J Smith.  This port to Ruby was done by Jason Adams using the port to Java by Richard Churchill.
+
+This project is distributed under the Apache 2.0 License[http://www.apache.org/licenses/LICENSE-2.0]. See LICENSE for details.
+

data/Rakefile

@@ -0,0 +1,59 @@
+require 'rubygems'
+require 'rake'
+
+begin
+  require 'jeweler'
+  Jeweler::Tasks.new do |gem|
+    gem.name = "uea-stemmer"
+    gem.summary = %Q{Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.}
+    gem.description = %Q{Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.}
+    gem.email = "jasonmadams@gmail.com"
+    gem.homepage = "http://github.com/ealdent/uea-stemmer"
+    gem.authors = ["Marie-Claire Jenkins", "Dan J. Smith", "Richard Churchill", "Jason Adams"]
+    # gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
+  end
+
+rescue LoadError
+  puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
+end
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/*_test.rb'
+  test.verbose = true
+end
+
+begin
+  require 'rcov/rcovtask'
+  Rcov::RcovTask.new do |test|
+    test.libs << 'test'
+    test.pattern = 'test/**/*_test.rb'
+    test.verbose = true
+  end
+rescue LoadError
+  task :rcov do
+    abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
+  end
+end
+
+
+
+
+task :default => :test
+
+require 'rake/rdoctask'
+Rake::RDocTask.new do |rdoc|
+  if File.exist?('VERSION.yml')
+    config = YAML.load(File.read('VERSION.yml'))
+    version = "#{config[:major]}.#{config[:minor]}.#{config[:patch]}"
+  else
+    version = ""
+  end
+
+  rdoc.rdoc_dir = 'rdoc'
+  rdoc.title = "uea-stemmer #{version}"
+  rdoc.rdoc_files.include('README*')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+end
+

data/VERSION

@@ -0,0 +1 @@
+0.9.10

data/lib/uea-stemmer/rule.rb

@@ -0,0 +1,108 @@
+#
+# Copyright 2005 University of East Anglia
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+#
+# Authored by Marie-Claire Jenkins and Dr. Dan J. Smith.  Ported to Java
+# from Perl by Richard Churchill.  Ported from Java to Ruby by Jason M. Adams.
+#
+
+require 'uea-stemmer/string_helpers'
+
+class UEAStemmer
+  class Rule
+    include StringHelpers
+
+    attr_reader :pattern, :suffix_size, :rule_num
+
+    def initialize(pattern, suffix_size, rule_num)
+      @pattern = pattern.dup.freeze
+      @suffix_size = suffix_size
+      @rule_num = rule_num
+    end
+
+    def handle(word)
+      [remove_suffix(word, @suffix_size), @rule_num, self] if word =~ @pattern
+    end
+
+    def to_s
+      "rule ##{@rule_num} (remove #{@suffix_size} letters from the end of the word when it matches pattern #{@pattern})"
+    end
+  end
+
+  class EndingRule < Rule
+    attr_reader :original_pattern
+
+    def initialize(pattern, suffix_size, rule_num)
+      super(/^.*#{pattern}$/, suffix_size, rule_num)
+      @original_pattern = pattern.dup.freeze
+    end
+
+    def to_s
+      "rule ##{@rule_num} (remove -#{@original_pattern[@original_pattern.size - @suffix_size, @suffix_size]} when the word ends in -#{@original_pattern})"
+    end
+  end
+
+  class ConcatenatingEndingRule < EndingRule
+    attr_reader :new_suffix
+
+    def initialize(pattern, suffix_size, rule_num, new_suffix)
+      super(pattern, suffix_size, rule_num)
+      @new_suffix = new_suffix.dup.freeze
+    end
+
+    def handle(word)
+      [remove_suffix(word, @suffix_size) + @new_suffix, @rule_num, self] if word =~ @pattern
+    end
+
+    def to_s
+      "rule ##{@rule_num} (remove -#{@original_pattern[@original_pattern.size - @suffix_size, @suffix_size]} and add -#{new_suffix} when the word ends in -#{@original_pattern})"
+    end
+  end
+
+  class NonExhaustiveEndingRule < EndingRule
+    def handle(word)
+      super(word) if word != @original_pattern
+    end
+
+    def to_s
+      "rule ##{@rule_num} (remove -#{@original_pattern[@original_pattern.size - @suffix_size, @suffix_size]} when the word ends in -#{@original_pattern} unless the word is #{@original_pattern})"
+    end
+  end
+
+  class ExhaustiveConcatenatingEndingRule < ConcatenatingEndingRule
+    def handle(word)
+      super(word) if word == @original_pattern
+    end
+  end
+
+  class CustomRule < Rule
+    def initialize(pattern, suffix_size, rule_num)
+      super(pattern, suffix_size, rule_num)
+    end
+
+    def handle(word)
+      [stem_with_duplicate_character_check(word), @rule_num, self] if word =~ @pattern
+    end
+
+    protected
+
+    def stem_with_duplicate_character_check(word)
+      new_suffix_size = ends_with?(word, 's') ? @suffix_size + 1 : @suffix_size
+      stemmed_word = remove_suffix(word, new_suffix_size)
+      stemmed_word.chop! if stemmed_word =~ /.*(\w)\1$/
+      stemmed_word
+    end
+  end
+end

data/lib/uea-stemmer/string_helpers.rb

@@ -0,0 +1,9 @@
+module StringHelpers
+  def remove_suffix(word, suffix_size)
+    word[0, word.size - suffix_size]
+  end
+
+  def ends_with?(word, suffix)
+    !!(word =~ /#{suffix}$/)
+  end
+end

data/lib/uea-stemmer/word.rb

@@ -0,0 +1,39 @@
+#
+# Copyright 2005 University of East Anglia
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+#
+# Authored by Marie-Claire Jenkins and Dr. Dan J. Smith.  Ported to Java
+# from Perl by Richard Churchill.  Ported from Java to Ruby by Jason M. Adams.
+#
+
+class UEAStemmer
+  class Word
+    attr_reader :word, :rule_num, :rule
+
+    def initialize(word, rule_num, rule = nil)
+      @word = word.dup.freeze
+      @rule_num = rule_num
+      @rule = rule
+    end
+
+    def to_s
+      if @rule_num > 0
+        "#{@word} (Rule ##{@rule_num} #{@rule})"
+      else
+        "#{@word} (No rule)"
+      end
+    end
+  end
+end

data/lib/uea-stemmer.rb

@@ -0,0 +1,354 @@
+#
+# Copyright 2005 University of East Anglia
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+#
+# Authored by Marie-Claire Jenkins and Dr. Dan J. Smith.  Ported to Java
+# from Perl by Richard Churchill.  Ported from Java to Ruby by Jason M. Adams.
+#
+
+require 'uea-stemmer/rule'
+require 'uea-stemmer/word'
+require 'uea-stemmer/string_helpers'
+require 'singleton'
+
+class UEAStemmer
+  include StringHelpers
+
+  attr_accessor :max_acronym_length, :max_word_length
+  attr_reader :rules
+
+  def initialize(max_word_length = nil, max_acronym_length = nil)
+    @max_word_length = max_word_length || 'deoxyribonucleicacid'.size
+    @max_acronym_length = max_acronym_length || 'CAVASSOO'.size
+
+    @rules = Array.new
+    create_rules
+  end
+
+  def stem_with_rule(word)
+    stemmed_word = word.dup;
+    ruleno = 0;
+
+    if problem_word?(word)
+      Word.new(word, 94)
+    elsif (word.size > @max_acronym_length && word =~ /^[A-Z]+$/) || (word.size > (@max_acronym_length + 1) && word =~ /^[A-Z]+s$/)
+      Word.new(word, 96)      # added by JMA to catch long acronyms
+    elsif word.size > @max_word_length
+      Word.new(word, 95)
+    elsif word.index("'")
+      if word =~ /^.*'[s]$/i
+        stemmed_word = remove_suffix(stemmed_word, 2)
+      elsif word =~ /^.*'$/
+        stemmed_word = remove_suffix(stemmed_word, 1)
+      end
+
+      stemmed_word.gsub!(/n't/, ' not')
+      stemmed_word.gsub!(/'ve/, ' have')
+      stemmed_word.gsub!(/'re/, ' are')
+      stemmed_word.gsub!(/'m/, ' am')
+
+      Word.new(stemmed_word, 93)
+    else
+      stemmed_word, rule_num, rule = apply_rules(stemmed_word)
+      Word.new(stemmed_word, rule_num, rule)
+    end
+  end
+
+  def stem(word)
+    stem_with_rule(word).word
+  end
+
+  def num_rules
+    @rules.map { |r| r.rule_num }.uniq.size + 4    # four rules not covered by the rules array
+  end
+
+  def to_s
+    "UEA-Lite Stemmer (#{num_rules} rules)"
+  end
+
+  def add_rule(rule)
+    if rule.kind_of?(Rule)
+      @rules << rule.dup.freeze
+      true
+    else
+      false
+    end
+  end
+
+  private
+
+  def apply_rules(word)
+    @rules.each do |rule|
+      stemmed_word, rule_num, tmp_rule = rule.handle(word)
+      return [stemmed_word, rule_num, rule] if stemmed_word && rule_num
+    end
+
+    [word, 0, nil]
+  end
+
+  def create_rules
+    @rules << Rule.new(/^\d+$/, 0, 90.3)
+    @rules << Rule.new(/^\w+-\w+$/, 0, 90.2)
+    @rules << Rule.new(/^.*-.*$/, 0, 90.1)
+    @rules << Rule.new(/^.*_.*$/, 0, 90)
+    @rules << Rule.new(/^[A-Z]+s$/, 1, 91.1)
+    @rules << Rule.new(/^[A-Z]+$/, 0, 91)
+    @rules << Rule.new(/^((.*[A-Z].*[A-Z])|([A-Z]{1})).*$/, 0, 92)
+
+    @rules << EndingRule.new('aceous', 6, 1)
+    @rules << EndingRule.new('ces', 1, 2)
+    @rules << EndingRule.new('cs', 0, 3)
+    @rules << EndingRule.new('sis', 0, 4)
+    @rules << EndingRule.new('tis', 0, 5)
+    @rules << EndingRule.new('ss', 0, 6)
+
+    # plural change - this differs from Perl v1.03
+    @rules << EndingRule.new('eed', 0, 7)
+    @rules << EndingRule.new('eeds', 1, 7)
+
+    @rules << EndingRule.new('ued', 1, 8)
+    @rules << EndingRule.new('ues', 1, 9)
+    @rules << EndingRule.new('ees', 1, 10)
+    @rules << EndingRule.new('iases', 2, 11.4)
+    @rules << EndingRule.new('uses', 1, 11.3)
+    @rules << EndingRule.new('sses', 2, 11.2)
+    @rules << ConcatenatingEndingRule.new('eses', 2, 11.1, 'is')
+    @rules << EndingRule.new('ses', 1, 11)
+    @rules << EndingRule.new('tled', 1, 12.5)
+    @rules << EndingRule.new('pled', 1, 12.4)
+    @rules << EndingRule.new('bled', 1, 12.3)
+
+    @rules << EndingRule.new('eled', 2, 12.2)
+    @rules << EndingRule.new('lled', 2, 12.1)
+    @rules << EndingRule.new('led', 2, 12)
+    @rules << EndingRule.new('ened', 2, 13.7)
+    @rules << EndingRule.new('ained', 2, 13.6)
+    @rules << EndingRule.new('erned', 2, 13.5)
+    @rules << EndingRule.new('rned', 2, 13.4)
+    @rules << EndingRule.new('nned', 2, 13.3)
+    @rules << EndingRule.new('oned', 2, 13.2)
+    @rules << EndingRule.new('gned', 2, 13.1)
+    @rules << EndingRule.new('ned', 1, 13)
+    @rules << EndingRule.new('ifted', 2, 14)
+    @rules << EndingRule.new('ected', 2, 15)
+    @rules << EndingRule.new('vided', 1, 16)
+    @rules << EndingRule.new('ved', 1, 17)
+    @rules << EndingRule.new('ced', 1, 18)
+    @rules << EndingRule.new('arred', 3, 19.1)
+    @rules << NonExhaustiveEndingRule.new('erred', 3, 19)
+    @rules << EndingRule.new('urred', 3, 20.5)
+    @rules << EndingRule.new('lored', 2, 20.4)
+    @rules << EndingRule.new('eared', 2, 20.3)
+    @rules << EndingRule.new('tored', 2, 20.2)
+    @rules << EndingRule.new('ered', 2, 20.1)
+
+    # plural change - this differs from Perl v1.03
+    @rules << EndingRule.new('red', 1, 20)
+    @rules << EndingRule.new('reds', 2, 20)
+    @rules << EndingRule.new('tted', 3, 21)
+
+    # added some rules to handle invited vs. exited
+    @rules << EndingRule.new('noted', 1, 22.6)
+    @rules << EndingRule.new('leted', 1, 22.5)
+    @rules << Rule.new(/^.*[^vm]ited$/, 2, 22.4)
+    @rules << Rule.new(/^.*(ch|[vm])i[td]ed$/, 1, 22.3)
+    @rules << EndingRule.new('uted', 1, 22.2)
+    @rules << EndingRule.new('ated', 1, 22.1)
+    @rules << EndingRule.new('ted', 2, 22)
+
+    @rules << EndingRule.new('anges', 1, 23)
+    @rules << EndingRule.new('aining', 3, 24)
+    @rules << EndingRule.new('acting', 3, 25)
+
+    # plural change - this differs from Perl v1.03
+    @rules << EndingRule.new('tting', 4, 26)
+    @rules << EndingRule.new('ttings', 5, 26)
+
+    @rules << EndingRule.new('viding', 3, 27)
+    @rules << EndingRule.new('ssed', 2, 28)
+    @rules << EndingRule.new('sed', 1, 29)
+    @rules << EndingRule.new('titudes', 1, 30)
+
+    # added some additional rules to handle other vowels and consonants
+    # (added by Jason M. Adams)
+    @rules << EndingRule.new('oed', 1, 31.3)
+    @rules << EndingRule.new('oes', 1, 31.2)
+    @rules << EndingRule.new('oked', 1, 31.1)
+    @rules << EndingRule.new('aked', 1, 31.1)
+    @rules << EndingRule.new('iked', 1, 31.1)
+    @rules << EndingRule.new('uked', 1, 31.1)
+    @rules << EndingRule.new('amed', 1, 31)
+    @rules << EndingRule.new('imed', 1, 31)
+    @rules << EndingRule.new('umed', 1, 31)
+
+    @rules << EndingRule.new('ulted', 2, 32)
+    @rules << ConcatenatingEndingRule.new('uming', 3, 33, 'e')
+    @rules << EndingRule.new('fulness', 4, 34)
+    @rules << EndingRule.new('ousness', 4, 35)
+    @rules << EndingRule.new('rabed', 1, 36.1)
+    @rules << EndingRule.new('rebed', 1, 36.1)
+    @rules << EndingRule.new('ribed', 1, 36.1)
+    @rules << EndingRule.new('robed', 1, 36.1)
+    @rules << EndingRule.new('rubed', 1, 36.1)
+    @rules << EndingRule.new('bed', 2, 36)
+    @rules << EndingRule.new('beds', 3, 36)
+    @rules << EndingRule.new('ssing', 3, 37)
+    @rules << EndingRule.new('ssings', 4, 37)
+    @rules << EndingRule.new('ulting', 3, 38)
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('ving', 3, 39, 'e')
+    @rules << ConcatenatingEndingRule.new('vings', 4, 39, 'e')
+
+    @rules << EndingRule.new('eading', 3, 40.7)
+    @rules << EndingRule.new('eadings', 4, 40.7)
+    @rules << EndingRule.new('oading', 3, 40.6)
+    @rules << EndingRule.new('oadings', 4, 40.6)
+    @rules << EndingRule.new('eding', 3, 40.5)
+    @rules << EndingRule.new('edings', 4, 40.5)
+    @rules << EndingRule.new('dding', 4, 40.4)
+    @rules << EndingRule.new('ddings', 5, 40.4)
+    @rules << EndingRule.new('lding', 3, 40.3)
+    @rules << EndingRule.new('ldings', 4, 40.3)
+    @rules << EndingRule.new('rding', 3, 40.2)
+    @rules << EndingRule.new('rdings', 4, 40.2)
+    @rules << EndingRule.new('nding', 3, 40.1)
+    @rules << EndingRule.new('ndings', 4, 40.1)
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('ding', 3, 40, 'e')
+    @rules << ConcatenatingEndingRule.new('dings', 4, 40, 'e')
+
+    @rules << EndingRule.new('lling', 4, 41)
+    @rules << EndingRule.new('llings', 5, 41)
+    @rules << EndingRule.new('ealing', 3, 42.4)
+    @rules << EndingRule.new('ealings', 4, 42.4)
+    @rules << EndingRule.new('oling', 3, 42.3)
+    @rules << EndingRule.new('olings', 4, 42.3)
+    @rules << EndingRule.new('ailing', 3, 42.2)
+    @rules << EndingRule.new('ailings', 4, 42.2)
+    @rules << EndingRule.new('eling', 3, 42.1)
+    @rules << EndingRule.new('elings', 4, 42.1)
+    @rules << ConcatenatingEndingRule.new('ling', 3, 42, 'e')
+    @rules << ConcatenatingEndingRule.new('lings', 4, 42, 'e')
+    @rules << EndingRule.new('nged', 1, 43.2)
+    @rules << EndingRule.new('gged', 3, 43.1)
+    @rules << EndingRule.new('ged', 1, 43)
+    @rules << EndingRule.new('mming', 4, 44.3)
+    @rules << EndingRule.new('mmings', 5, 44.3)
+    @rules << EndingRule.new('rming', 3, 44.2)
+    @rules << EndingRule.new('lming', 3, 44.1)
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('ming', 3, 44, 'e')
+    @rules << ConcatenatingEndingRule.new('mings', 4, 44, 'e')
+
+    @rules << EndingRule.new('nging', 3, 45.2)
+    @rules << EndingRule.new('ngings', 4, 45.2)
+    @rules << EndingRule.new('gging', 4, 45.1)
+    @rules << EndingRule.new('ggings', 5, 45.1)
+    @rules << EndingRule.new('ging', 3, 45)
+    @rules << EndingRule.new('gings', 4, 45)
+    @rules << EndingRule.new('aning', 3, 46.6)
+    @rules << EndingRule.new('ening', 3, 46.5)
+    @rules << EndingRule.new('gning', 3, 46.4)
+    @rules << EndingRule.new('nning', 4, 46.3)
+    @rules << EndingRule.new('oning', 3, 46.2)
+    @rules << EndingRule.new('rning', 3, 46.1)
+    @rules << ConcatenatingEndingRule.new('ning', 3, 46, 'e')
+
+    # plural change - this differs from Perl v1.03
+    @rules << EndingRule.new('sting', 3, 47)
+    @rules << EndingRule.new('stings', 4, 47)
+    @rules << EndingRule.new('eting', 3, 48.4)
+    @rules << EndingRule.new('etings', 4, 48.4)
+
+    @rules << EndingRule.new('pting', 3, 48.3)
+    @rules << EndingRule.new('nting', 3, 48.2)
+    @rules << EndingRule.new('ntings', 4, 48.2)
+    @rules << EndingRule.new('cting', 3, 48.1)
+    @rules << ConcatenatingEndingRule.new('ting', 3, 48, 'e')
+    @rules << ConcatenatingEndingRule.new('tings', 4, 48, 'e')
+
+    @rules << EndingRule.new('ssed', 2, 49)
+    @rules << EndingRule.new('les', 1, 50)
+    @rules << EndingRule.new('tes', 1, 51)
+    @rules << EndingRule.new('zed', 1, 52)
+    @rules << EndingRule.new('lled', 2, 53)
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('iring', 3, 54.4, 'e')
+    @rules << ConcatenatingEndingRule.new('irings', 4, 54.4, 'e')
+    @rules << ConcatenatingEndingRule.new('uring', 3, 54.3, 'e')
+    @rules << ConcatenatingEndingRule.new('urings', 4, 54.3, 'e')
+    @rules << ConcatenatingEndingRule.new('ncing', 3, 54.2, 'e')
+    @rules << ConcatenatingEndingRule.new('ncings', 4, 54.2, 'e')
+
+    @rules << ConcatenatingEndingRule.new('zing', 3, 54.1, 'e')
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('sing', 3, 54, 'e')
+    @rules << ConcatenatingEndingRule.new('sings', 4, 54, 'e')
+
+    @rules << EndingRule.new('lling', 3, 55)
+    @rules << ConcatenatingEndingRule.new('ied', 3, 56, 'y')
+    @rules << ConcatenatingEndingRule.new('ating', 3, 57, 'e')
+
+    # plural change - this differs from Perl v1.03
+    @rules << ConcatenatingEndingRule.new('dying', 4, 58.2, 'ie')   # added by JMA
+    @rules << ExhaustiveConcatenatingEndingRule.new('lying', 4, 58.2, 'ie')   # added by JMA    (lying vs flying)
+    @rules << ConcatenatingEndingRule.new('tying', 4, 58.2, 'ie')   # added by JMA
+    @rules << EndingRule.new('thing', 0, 58.1)
+    @rules << EndingRule.new('things', 1, 58.1)
+    @rules << CustomRule.new(/.*\w\wings?$/, 3, 58)
+
+    @rules << ConcatenatingEndingRule.new('ies', 3, 59, 'y')
+    @rules << ConcatenatingEndingRule.new('lves', 3, 60.1, 'f')
+    @rules << EndingRule.new('ves', 1, 60)
+    @rules << EndingRule.new('aped', 1, 61.3)
+    @rules << EndingRule.new('uded', 1, 61.2)
+    @rules << EndingRule.new('oded', 1, 61.1)
+    @rules << EndingRule.new('ated', 1, 61)
+    @rules << CustomRule.new(/.*\w\weds?$/, 2, 62)
+    @rules << EndingRule.new('pes', 1, 63.8)
+    @rules << EndingRule.new('mes', 1, 63.7)
+    @rules << EndingRule.new('ones', 1, 63.6)
+    @rules << EndingRule.new('izes', 1, 63.5)
+    @rules << EndingRule.new('ures', 1, 63.4)
+    @rules << EndingRule.new('ines', 1, 63.3)
+    @rules << EndingRule.new('ides', 1, 63.2)
+    @rules << EndingRule.new('kes', 1, 63.1)
+    @rules << EndingRule.new('ges', 1, 63.1)
+    @rules << EndingRule.new('es', 2, 63)
+    @rules << ConcatenatingEndingRule.new('is', 2, 64, 'e')
+    @rules << EndingRule.new('ous', 0, 65)
+    @rules << EndingRule.new('ums', 0, 66)
+    @rules << EndingRule.new('us', 0, 67)
+    @rules << EndingRule.new('s', 1, 68)
+
+    @rules.each { |r| r.freeze }
+
+    nil
+  end
+
+  def problem_word?(word)
+    ['is', 'as', 'this', 'has', 'was', 'during', 'menses'].include?(word)
+  end
+
+end
+
+class DefaultUEAStemmer < UEAStemmer
+  include Singleton
+end

data/test/test_helper.rb

@@ -0,0 +1,10 @@
+require 'rubygems'
+require 'test/unit'
+require 'shoulda'
+
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+require 'uea-stemmer'
+
+class Test::Unit::TestCase
+end

data/test/uea_stemmer_test.rb

@@ -0,0 +1,156 @@
+require 'test_helper'
+
+class UeaStemmerTest < Test::Unit::TestCase
+  context "A default UEAStemmer instance" do
+    setup do
+      @stemmer = UEAStemmer.new
+    end
+
+    should "have max word and max acronym sizes equivalent to deoxyribonucleicacid and CAVASSOO respectively" do
+      assert @stemmer.max_word_length == 'deoxyribonucleicacid'.size
+      assert @stemmer.max_acronym_length == 'CAVASSOO'.size
+    end
+
+    context "stem method" do
+      should "stem words as Strings" do
+        assert @stemmer.stem('word').is_a?(String)
+      end
+
+      should "stem base words to just the base word" do
+        assert_equal @stemmer.stem('man'), 'man'
+        assert_equal @stemmer.stem('happiness'), 'happiness'
+      end
+
+      should "stem theses as thesis but not bases as basis" do
+        assert_equal @stemmer.stem('theses'), 'thesis'
+        assert_not_equal @stemmer.stem('bases'), 'basis'
+      end
+
+      should "stem preterite words ending in -ed without the -ed" do
+        assert_equal @stemmer.stem('ordained'), 'ordain'
+        assert_equal @stemmer.stem('killed'), 'kill'
+        assert_equal @stemmer.stem('liked'), 'like'
+        assert_equal @stemmer.stem('helped'), 'help'
+        assert_equal @stemmer.stem('scarred'), 'scar'
+        assert_equal @stemmer.stem('invited'), 'invite'
+        assert_equal @stemmer.stem('exited'), 'exit'
+        assert_equal @stemmer.stem('exited'), 'exit'
+        assert_equal @stemmer.stem('debited'), 'debit'
+        assert_equal @stemmer.stem('smited'), 'smite'
+      end
+
+      should "stem progressive verbs and gerunds without the -ing" do
+        assert_equal @stemmer.stem('running'), 'run'
+        assert_equal @stemmer.stem('settings'), 'set'
+        assert_equal @stemmer.stem('timing'), 'time'
+        assert_equal @stemmer.stem('dying'), 'die'
+        assert_equal @stemmer.stem('harping'), 'harp'
+        assert_equal @stemmer.stem('charring'), 'char'
+      end
+
+      should "stem various plural nouns and 3rd-pres verbs without the -s/-es" do
+        assert_equal @stemmer.stem('changes'), 'change'
+        assert_equal @stemmer.stem('deaths'), 'death'
+        assert_equal @stemmer.stem('shadows'), 'shadow'
+        assert_equal @stemmer.stem('flies'), 'fly'
+        assert_equal @stemmer.stem('things'), 'thing'
+        assert_equal @stemmer.stem('nothings'), 'nothing'   # as in 'sweet nothings'
+        assert_equal @stemmer.stem('witches'), 'witch'
+        assert_equal @stemmer.stem('makes'), 'make'
+        assert_equal @stemmer.stem('smokes'), 'smoke'
+      end
+
+      should "stem acronyms when pluralized otherwise they should be left alone" do
+        assert_equal @stemmer.stem('USA'), 'USA'
+        assert_equal @stemmer.stem('FLOSS'), 'FLOSS'
+        assert_equal @stemmer.stem('MREs'), 'MRE'
+        assert_equal @stemmer.stem('USAED'), 'USAED'
+      end
+    end
+
+    context "stem_with_rule method" do
+      should "return a Word instance" do
+        assert @stemmer.stem_with_rule('witches').is_a?(UEAStemmer::Word)
+      end
+
+      should "return a rule and the stemmed form" do
+        word = @stemmer.stem_with_rule('witches')
+        assert !word.rule.nil?
+        assert !word.word.nil?
+      end
+    end
+
+    context "other functionality" do
+      should "return the number of rules the stemmer is currently using" do
+        assert @stemmer.num_rules.is_a?(Numeric)
+      end
+    end
+  end
+
+  context "A modified UEAStemmer instance" do
+    setup do
+      @stemmer = UEAStemmer.new(5, 3)     # max word length = 5, max acronym length = 3
+    end
+
+    should "have modified max word and max acronym sizes" do
+      assert @stemmer.max_word_length == 5
+      assert @stemmer.max_acronym_length == 3
+    end
+
+    should "reject a longer word with rule 95" do
+      word = @stemmer.stem_with_rule('deoxyribonucleicacid')
+      assert_equal word.rule_num, 95
+    end
+
+    should "reject a longer acronym with rule 96" do
+      word = @stemmer.stem_with_rule('CAVASSOO')
+      assert_equal word.rule_num, 96
+    end
+  end
+
+  context "A Word instance" do
+    setup do
+      @word = UEAStemmer::Word.new('helpers', 68, UEAStemmer::EndingRule.new('s', 1, 68)) # sample word
+      @stemmer = UEAStemmer.new
+    end
+
+    should "return the rule used to derive the stem" do
+      assert @word.rule.kind_of?(UEAStemmer::Rule)
+    end
+
+    should "return the number of the rule used to derive the stem" do
+      assert @word.rule_num.kind_of?(Numeric)
+    end
+
+    should "return the stemmed word as a String" do
+      assert @word.word.kind_of?(String)
+    end
+  end
+
+  context "A Rule instance" do
+    setup do
+      @rule = UEAStemmer::Rule.new(/.*s$/i, 1, 555)
+    end
+
+    should "return the rule number" do
+      assert @rule.rule_num.kind_of?(Numeric)
+    end
+
+    should "return the pattern being matched" do
+      assert @rule.pattern.kind_of?(String) || @rule.pattern.kind_of?(Regexp)
+    end
+
+    should "return the size of the suffix that is being removed" do
+      assert @rule.suffix_size.kind_of?(Numeric)
+    end
+
+    should "return a stemmed word, a rule number, and a rule on a successful match" do
+      word, rule_num, tmp_rule = @rule.handle('helps')
+      assert word.is_a?(String) && rule_num.is_a?(Numeric) && tmp_rule.is_a?(UEAStemmer::Rule)
+    end
+
+    should "return nil when match is unsuccessful" do
+      assert @rule.handle('help').nil?
+    end
+  end
+end

data/uea-stemmer.gemspec

@@ -0,0 +1,53 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE
+# Instead, edit Jeweler::Tasks in Rakefile, and run `rake gemspec`
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{uea-stemmer}
+  s.version = "0.9.10"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Marie-Claire Jenkins", "Dan J. Smith", "Richard Churchill", "Jason Adams"]
+  s.date = %q{2009-09-30}
+  s.description = %q{Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.}
+  s.email = %q{jasonmadams@gmail.com}
+  s.extra_rdoc_files = [
+    "LICENSE",
+     "README.rdoc"
+  ]
+  s.files = [
+    ".document",
+     ".gitignore",
+     "LICENSE",
+     "README.rdoc",
+     "Rakefile",
+     "VERSION",
+     "lib/uea-stemmer.rb",
+     "lib/uea-stemmer/rule.rb",
+     "lib/uea-stemmer/string_helpers.rb",
+     "lib/uea-stemmer/word.rb",
+     "test/test_helper.rb",
+     "test/uea_stemmer_test.rb",
+     "uea-stemmer.gemspec"
+  ]
+  s.homepage = %q{http://github.com/ealdent/uea-stemmer}
+  s.rdoc_options = ["--charset=UTF-8"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.4}
+  s.summary = %q{Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.}
+  s.test_files = [
+    "test/test_helper.rb",
+     "test/uea_stemmer_test.rb"
+  ]
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

metadata

@@ -0,0 +1,72 @@
+--- !ruby/object:Gem::Specification 
+name: uea-stemmer
+version: !ruby/object:Gem::Version 
+  version: 0.9.10
+platform: ruby
+authors: 
+- Marie-Claire Jenkins
+- Dan J. Smith
+- Richard Churchill
+- Jason Adams
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-09-30 00:00:00 -04:00
+default_executable: 
+dependencies: []
+
+description: Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.
+email: jasonmadams@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: 
+- LICENSE
+- README.rdoc
+files: 
+- .document
+- .gitignore
+- LICENSE
+- README.rdoc
+- Rakefile
+- VERSION
+- lib/uea-stemmer.rb
+- lib/uea-stemmer/rule.rb
+- lib/uea-stemmer/string_helpers.rb
+- lib/uea-stemmer/word.rb
+- test/test_helper.rb
+- test/uea_stemmer_test.rb
+- uea-stemmer.gemspec
+has_rdoc: true
+homepage: http://github.com/ealdent/uea-stemmer
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --charset=UTF-8
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.4
+signing_key: 
+specification_version: 3
+summary: Port of UEA-Lite Stemmer to Ruby, a conservative stemmer for search and indexing.
+test_files: 
+- test/test_helper.rb
+- test/uea_stemmer_test.rb