jruby-stemmer 0.0.1-java

data/.gitignore

@@ -0,0 +1,23 @@
+*.bundle
+*.gem
+*.jar
+*.o
+*.rbc
+*.so
+.bundle
+.config
+.DS_Store
+.yardoc
+coverage
+doc/
+Gemfile.lock
+InstalledFiles
+lib/bundler/man
+Makefile
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+_yardoc

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in jruby-stemmer.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,27 @@
+Excluding ext/java-stemmer/Stemmer.java -
+  see http://www.tartarus.org/~martin/PorterStemmer for that code
+
+
+
+Copyright (c) 2013 Caius Durling
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,32 @@
+# JRuby::Stemmer
+
+Easily stem words in ruby, using a native java implementation of the porter stemming algorithm for speed. (Java equivalent of the fast-stemmer gem for MRI.)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'jruby-stemmer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install jruby-stemmer
+
+## Usage
+
+You can either call the wrapper method yourself, or use the mixed in helper method `String#stem`.
+
+    JRuby::Stemmer.stem("apple") # => "appl"
+    "apple".stem # => "appl"
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,7 @@
+spec = Gem::Specification.load("jruby-stemmer.gemspec")
+
+require "rubygems/package_task"
+Gem::PackageTask.new(spec) {}
+
+require "rake/javaextensiontask"
+Rake::JavaExtensionTask.new("java-stemmer", spec)

data/ext/java-stemmer/Stemmer.java

@@ -0,0 +1,427 @@
+package org.tartarus.martin.porter_stemmer;
+
+/*
+
+   Porter stemmer in Java. The original paper is in
+
+       Porter, 1980, An algorithm for suffix stripping, Program, Vol. 14,
+       no. 3, pp 130-137,
+
+   See also http://www.tartarus.org/~martin/PorterStemmer
+
+   History:
+
+   Release 1
+
+   Bug 1 (reported by Gonzalo Parra 16/10/99) fixed as marked below.
+   The words 'aed', 'eed', 'oed' leave k at 'a' for step 3, and b[k-1]
+   is then out outside the bounds of b.
+
+   Release 2
+
+   Similarly,
+
+   Bug 2 (reported by Steve Dyrdahl 22/2/00) fixed as marked below.
+   'ion' by itself leaves j = -1 in the test for 'ion' in step 5, and
+   b[j] is then outside the bounds of b.
+
+   Release 3
+
+   Considerably revised 4/9/00 in the light of many helpful suggestions
+   from Brian Goetz of Quiotix Corporation (brian@quiotix.com).
+
+   Release 4
+
+*/
+
+import java.io.*;
+
+/**
+  * Stemmer, implementing the Porter Stemming Algorithm
+  *
+  * The Stemmer class transforms a word into its root form.  The input
+  * word can be provided a character at time (by calling add()), or at once
+  * by calling one of the various stem(something) methods.
+  */
+
+public class Stemmer
+{  private char[] b;
+   private int i,     /* offset into b */
+               i_end, /* offset to end of stemmed word */
+               j, k;
+   private static final int INC = 50;
+                     /* unit of size whereby b is increased */
+   public Stemmer()
+   {  b = new char[INC];
+      i = 0;
+      i_end = 0;
+   }
+
+   /**
+    * Add a character to the word being stemmed.  When you are finished
+    * adding characters, you can call stem(void) to stem the word.
+    */
+
+   public void add(char ch)
+   {  if (i == b.length)
+      {  char[] new_b = new char[i+INC];
+         for (int c = 0; c < i; c++) new_b[c] = b[c];
+         b = new_b;
+      }
+      b[i++] = ch;
+   }
+
+
+   /** Adds wLen characters to the word being stemmed contained in a portion
+    * of a char[] array. This is like repeated calls of add(char ch), but
+    * faster.
+    */
+
+   public void add(char[] w, int wLen)
+   {  if (i+wLen >= b.length)
+      {  char[] new_b = new char[i+wLen+INC];
+         for (int c = 0; c < i; c++) new_b[c] = b[c];
+         b = new_b;
+      }
+      for (int c = 0; c < wLen; c++) b[i++] = w[c];
+   }
+
+   /**
+    * After a word has been stemmed, it can be retrieved by toString(),
+    * or a reference to the internal buffer can be retrieved by getResultBuffer
+    * and getResultLength (which is generally more efficient.)
+    */
+   public String toString() { return new String(b,0,i_end); }
+
+   /**
+    * Returns the length of the word resulting from the stemming process.
+    */
+   public int getResultLength() { return i_end; }
+
+   /**
+    * Returns a reference to a character buffer containing the results of
+    * the stemming process.  You also need to consult getResultLength()
+    * to determine the length of the result.
+    */
+   public char[] getResultBuffer() { return b; }
+
+   /* cons(i) is true <=> b[i] is a consonant. */
+
+   private final boolean cons(int i)
+   {  switch (b[i])
+      {  case 'a': case 'e': case 'i': case 'o': case 'u': return false;
+         case 'y': return (i==0) ? true : !cons(i-1);
+         default: return true;
+      }
+   }
+
+   /* m() measures the number of consonant sequences between 0 and j. if c is
+      a consonant sequence and v a vowel sequence, and <..> indicates arbitrary
+      presence,
+
+         <c><v>       gives 0
+         <c>vc<v>     gives 1
+         <c>vcvc<v>   gives 2
+         <c>vcvcvc<v> gives 3
+         ....
+   */
+
+   private final int m()
+   {  int n = 0;
+      int i = 0;
+      while(true)
+      {  if (i > j) return n;
+         if (! cons(i)) break; i++;
+      }
+      i++;
+      while(true)
+      {  while(true)
+         {  if (i > j) return n;
+               if (cons(i)) break;
+               i++;
+         }
+         i++;
+         n++;
+         while(true)
+         {  if (i > j) return n;
+            if (! cons(i)) break;
+            i++;
+         }
+         i++;
+       }
+   }
+
+   /* vowelinstem() is true <=> 0,...j contains a vowel */
+
+   private final boolean vowelinstem()
+   {  int i; for (i = 0; i <= j; i++) if (! cons(i)) return true;
+      return false;
+   }
+
+   /* doublec(j) is true <=> j,(j-1) contain a double consonant. */
+
+   private final boolean doublec(int j)
+   {  if (j < 1) return false;
+      if (b[j] != b[j-1]) return false;
+      return cons(j);
+   }
+
+   /* cvc(i) is true <=> i-2,i-1,i has the form consonant - vowel - consonant
+      and also if the second c is not w,x or y. this is used when trying to
+      restore an e at the end of a short word. e.g.
+
+         cav(e), lov(e), hop(e), crim(e), but
+         snow, box, tray.
+
+   */
+
+   private final boolean cvc(int i)
+   {  if (i < 2 || !cons(i) || cons(i-1) || !cons(i-2)) return false;
+      {  int ch = b[i];
+         if (ch == 'w' || ch == 'x' || ch == 'y') return false;
+      }
+      return true;
+   }
+
+   private final boolean ends(String s)
+   {  int l = s.length();
+      int o = k-l+1;
+      if (o < 0) return false;
+      for (int i = 0; i < l; i++) if (b[o+i] != s.charAt(i)) return false;
+      j = k-l;
+      return true;
+   }
+
+   /* setto(s) sets (j+1),...k to the characters in the string s, readjusting
+      k. */
+
+   private final void setto(String s)
+   {  int l = s.length();
+      int o = j+1;
+      for (int i = 0; i < l; i++) b[o+i] = s.charAt(i);
+      k = j+l;
+   }
+
+   /* r(s) is used further down. */
+
+   private final void r(String s) { if (m() > 0) setto(s); }
+
+   /* step1() gets rid of plurals and -ed or -ing. e.g.
+
+          caresses  ->  caress
+          ponies    ->  poni
+          ties      ->  ti
+          caress    ->  caress
+          cats      ->  cat
+
+          feed      ->  feed
+          agreed    ->  agree
+          disabled  ->  disable
+
+          matting   ->  mat
+          mating    ->  mate
+          meeting   ->  meet
+          milling   ->  mill
+          messing   ->  mess
+
+          meetings  ->  meet
+
+   */
+
+   private final void step1()
+   {  if (b[k] == 's')
+      {  if (ends("sses")) k -= 2; else
+         if (ends("ies")) setto("i"); else
+         if (b[k-1] != 's') k--;
+      }
+      if (ends("eed")) { if (m() > 0) k--; } else
+      if ((ends("ed") || ends("ing")) && vowelinstem())
+      {  k = j;
+         if (ends("at")) setto("ate"); else
+         if (ends("bl")) setto("ble"); else
+         if (ends("iz")) setto("ize"); else
+         if (doublec(k))
+         {  k--;
+            {  int ch = b[k];
+               if (ch == 'l' || ch == 's' || ch == 'z') k++;
+            }
+         }
+         else if (m() == 1 && cvc(k)) setto("e");
+     }
+   }
+
+   /* step2() turns terminal y to i when there is another vowel in the stem. */
+
+   private final void step2() { if (ends("y") && vowelinstem()) b[k] = 'i'; }
+
+   /* step3() maps double suffices to single ones. so -ization ( = -ize plus
+      -ation) maps to -ize etc. note that the string before the suffix must give
+      m() > 0. */
+
+   private final void step3() { if (k == 0) return; /* For Bug 1 */ switch (b[k-1])
+   {
+       case 'a': if (ends("ational")) { r("ate"); break; }
+                 if (ends("tional")) { r("tion"); break; }
+                 break;
+       case 'c': if (ends("enci")) { r("ence"); break; }
+                 if (ends("anci")) { r("ance"); break; }
+                 break;
+       case 'e': if (ends("izer")) { r("ize"); break; }
+                 break;
+       case 'l': if (ends("bli")) { r("ble"); break; }
+                 if (ends("alli")) { r("al"); break; }
+                 if (ends("entli")) { r("ent"); break; }
+                 if (ends("eli")) { r("e"); break; }
+                 if (ends("ousli")) { r("ous"); break; }
+                 break;
+       case 'o': if (ends("ization")) { r("ize"); break; }
+                 if (ends("ation")) { r("ate"); break; }
+                 if (ends("ator")) { r("ate"); break; }
+                 break;
+       case 's': if (ends("alism")) { r("al"); break; }
+                 if (ends("iveness")) { r("ive"); break; }
+                 if (ends("fulness")) { r("ful"); break; }
+                 if (ends("ousness")) { r("ous"); break; }
+                 break;
+       case 't': if (ends("aliti")) { r("al"); break; }
+                 if (ends("iviti")) { r("ive"); break; }
+                 if (ends("biliti")) { r("ble"); break; }
+                 break;
+       case 'g': if (ends("logi")) { r("log"); break; }
+   } }
+
+   /* step4() deals with -ic-, -full, -ness etc. similar strategy to step3. */
+
+   private final void step4() { switch (b[k])
+   {
+       case 'e': if (ends("icate")) { r("ic"); break; }
+                 if (ends("ative")) { r(""); break; }
+                 if (ends("alize")) { r("al"); break; }
+                 break;
+       case 'i': if (ends("iciti")) { r("ic"); break; }
+                 break;
+       case 'l': if (ends("ical")) { r("ic"); break; }
+                 if (ends("ful")) { r(""); break; }
+                 break;
+       case 's': if (ends("ness")) { r(""); break; }
+                 break;
+   } }
+
+   /* step5() takes off -ant, -ence etc., in context <c>vcvc<v>. */
+
+   private final void step5()
+   {   if (k == 0) return; /* for Bug 1 */ switch (b[k-1])
+       {  case 'a': if (ends("al")) break; return;
+          case 'c': if (ends("ance")) break;
+                    if (ends("ence")) break; return;
+          case 'e': if (ends("er")) break; return;
+          case 'i': if (ends("ic")) break; return;
+          case 'l': if (ends("able")) break;
+                    if (ends("ible")) break; return;
+          case 'n': if (ends("ant")) break;
+                    if (ends("ement")) break;
+                    if (ends("ment")) break;
+                    /* element etc. not stripped before the m */
+                    if (ends("ent")) break; return;
+          case 'o': if (ends("ion") && j >= 0 && (b[j] == 's' || b[j] == 't')) break;
+                                    /* j >= 0 fixes Bug 2 */
+                    if (ends("ou")) break; return;
+                    /* takes care of -ous */
+          case 's': if (ends("ism")) break; return;
+          case 't': if (ends("ate")) break;
+                    if (ends("iti")) break; return;
+          case 'u': if (ends("ous")) break; return;
+          case 'v': if (ends("ive")) break; return;
+          case 'z': if (ends("ize")) break; return;
+          default: return;
+       }
+       if (m() > 1) k = j;
+   }
+
+   /* step6() removes a final -e if m() > 1. */
+
+   private final void step6()
+   {  j = k;
+      if (b[k] == 'e')
+      {  int a = m();
+         if (a > 1 || a == 1 && !cvc(k-1)) k--;
+      }
+      if (b[k] == 'l' && doublec(k) && m() > 1) k--;
+   }
+
+   /** Stem the word placed into the Stemmer buffer through calls to add().
+    * Returns true if the stemming process resulted in a word different
+    * from the input.  You can retrieve the result with
+    * getResultLength()/getResultBuffer() or toString().
+    */
+   public void stem()
+   {  k = i - 1;
+      if (k > 1) { step1(); step2(); step3(); step4(); step5(); step6(); }
+      i_end = k+1; i = 0;
+   }
+
+   /** Test program for demonstrating the Stemmer.  It reads text from a
+    * a list of files, stems each word, and writes the result to standard
+    * output. Note that the word stemmed is expected to be in lower case:
+    * forcing lower case must be done outside the Stemmer class.
+    * Usage: Stemmer file-name file-name ...
+    */
+   public static void main(String[] args)
+   {
+      char[] w = new char[501];
+      Stemmer s = new Stemmer();
+      for (int i = 0; i < args.length; i++)
+      try
+      {
+         FileInputStream in = new FileInputStream(args[i]);
+
+         try
+         { while(true)
+
+           {  int ch = in.read();
+              if (Character.isLetter((char) ch))
+              {
+                 int j = 0;
+                 while(true)
+                 {  ch = Character.toLowerCase((char) ch);
+                    w[j] = (char) ch;
+                    if (j < 500) j++;
+                    ch = in.read();
+                    if (!Character.isLetter((char) ch))
+                    {
+                       /* to test add(char ch) */
+                       for (int c = 0; c < j; c++) s.add(w[c]);
+
+                       /* or, to test add(char[] w, int j) */
+                       /* s.add(w, j); */
+
+                       s.stem();
+                       {  String u;
+
+                          /* and now, to test toString() : */
+                          u = s.toString();
+
+                          /* to test getResultBuffer(), getResultLength() : */
+                          /* u = new String(s.getResultBuffer(), 0, s.getResultLength()); */
+
+                          System.out.print(u);
+                       }
+                       break;
+                    }
+                 }
+              }
+              if (ch < 0) break;
+              System.out.print((char)ch);
+           }
+         }
+         catch (IOException e)
+         {  System.out.println("error reading " + args[i]);
+            break;
+         }
+      }
+      catch (FileNotFoundException e)
+      {  System.out.println("file " + args[i] + " not found");
+         break;
+      }
+   }
+}

data/jruby-stemmer.gemspec

@@ -0,0 +1,26 @@
+# -*- encoding: utf-8 -*-
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'jruby-stemmer/version'
+
+Gem::Specification.new do |gem|
+  gem.name          = "jruby-stemmer"
+  gem.version       = JRuby::Stemmer::VERSION
+  gem.authors       = ["Caius Durling"]
+  gem.email         = ["dev@caius.name"]
+  gem.description   = %q{Native java implementation of a string stemming algorithm. JRuby replacement for `fast-stemmer` gem under MRI.}
+  gem.summary       = %q{Fast string stemming in JRuby}
+  gem.homepage      = "https://github.com/caius/jruby-stemmer"
+
+  gem.files         = `git ls-files`.split($/)
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.platform = "java"
+  gem.files << "lib/java-stemmer.jar"
+
+  gem.add_development_dependency "rake-compiler"
+  gem.add_development_dependency "rspec"
+
+end

data/lib/jruby-stemmer/version.rb

@@ -0,0 +1,5 @@
+module JRuby
+  module Stemmer
+    VERSION = "0.0.1"
+  end
+end

data/lib/jruby-stemmer.rb

@@ -0,0 +1,26 @@
+require "jruby-stemmer/version"
+
+# Mixes in String#stem using java implementation
+module JRuby
+  module Stemmer
+    require "jruby"
+    # include_package 'org.tartarus.martin.porter_stemmer'
+    require_relative "java-stemmer"
+
+    def self.stem string
+      stemmer = Java::OrgTartarusMartinPorter_Stemmer::Stemmer.new
+      java_string = string.to_java_string
+      stemmer.add java_string.toCharArray, java_string.length
+      stemmer.stem
+      stemmer.to_string
+    end
+
+    module StringStem
+      def stem
+        JRuby::Stemmer.stem(self)
+      end
+    end
+    String.__send__ :include, StringStem
+
+  end
+end

data/spec/stemmer_spec.rb

@@ -0,0 +1,17 @@
+require "jruby-stemmer"
+
+describe JRuby::Stemmer do
+  it "stems a string" do
+    result = JRuby::Stemmer.stem("apple")
+    expect(result).to be == "appl"
+  end
+end
+
+describe "String" do
+  it "has a #stem method" do
+    expect("").to respond_to(:stem)
+  end
+  it "stems a string" do
+    expect("apple".stem).to be == "appl"
+  end
+end

metadata

@@ -0,0 +1,95 @@
+--- !ruby/object:Gem::Specification
+name: jruby-stemmer
+version: !ruby/object:Gem::Version
+  prerelease:
+  version: 0.0.1
+platform: java
+authors:
+- Caius Durling
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2013-05-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake-compiler
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  prerelease: false
+  type: :development
+- !ruby/object:Gem::Dependency
+  name: rspec
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MA==
+    none: false
+  prerelease: false
+  type: :development
+description: Native java implementation of a string stemming algorithm. JRuby replacement for `fast-stemmer` gem under MRI.
+email:
+- dev@caius.name
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- ext/java-stemmer/Stemmer.java
+- jruby-stemmer.gemspec
+- lib/java-stemmer.jar
+- lib/jruby-stemmer.rb
+- lib/jruby-stemmer/version.rb
+- spec/stemmer_spec.rb
+homepage: https://github.com/caius/jruby-stemmer
+licenses: []
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: !binary |-
+        MA==
+  none: false
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: !binary |-
+        MA==
+  none: false
+requirements: []
+rubyforge_project:
+rubygems_version: 1.8.24
+signing_key:
+specification_version: 3
+summary: Fast string stemming in JRuby
+test_files:
+- spec/stemmer_spec.rb