treat 0.1.1

data/lib/treat/inflectors/declensors/en.rb

@@ -0,0 +1,18 @@
+silently { require 'english' }
+
+module Treat
+   module Inflectors
+      module Declensors
+         module En
+            def self.declense(entity, options)
+               string = entity.to_s
+               if options[:count] == :plural
+                 ::English.plural(string)
+               elsif options[:count] == :singular
+                 ::English.singular(string)
+               end
+            end
+         end
+      end
+   end
+end

data/lib/treat/inflectors/declensors/linguistics.rb

@@ -0,0 +1,30 @@
+module Treat
+  module Inflectors
+    module Declensors
+      silently { require 'linguistics' }
+      # Obtain word declensions in English using the
+      # ruby 'linguistics' gem.
+      class Linguistics
+        def self.declense(entity, options = {})
+          begin
+            l = entity.language.to_s.upcase
+            delegate = nil
+            silently { delegate = ::Linguistics.const_get(l) }
+          rescue RuntimeError
+            raise "Ruby Linguistics does not have a module " + 
+            " installed for the #{entity.language} language."
+          end
+          string = entity.to_s
+          if options[:count] == :plural
+            if entity.has?(:category) &&
+              [:noun, :adjective, :verb].include?(entity.category)
+              silently { delegate.send(:"plural_#{entity.category}", string) }
+            else
+              silently { delegate.plural(string) }
+            end
+          end
+        end
+      end
+    end
+  end
+end

data/lib/treat/inflectors/lemmatizers/e_lemma.rb

@@ -0,0 +1,12 @@
+module Treat
+  module Inflectors
+    module Lemmatizers
+      class ELemma
+        silently { require 'treat/inflectors/lemmatizers/elemma/elemma'}
+        def self.lemma(entity, options = nil)
+          ::ELemma::parse(word, entity.tag)
+        end
+      end
+    end
+  end
+end

data/lib/treat/inflectors/lemmatizers/e_lemma/Makefile

@@ -0,0 +1,213 @@
+
+SHELL = /bin/sh
+
+# V=0 quiet, V=1 verbose.  other values don't work.
+V = 0
+Q1 = $(V:1=)
+Q = $(Q1:0=@)
+n=$(NULLCMD)
+ECHO1 = $(V:1=@$n)
+ECHO = $(ECHO1:0=@echo)
+
+#### Start of system configuration section. ####
+
+srcdir = .
+topdir = /usr/local/include/ruby-1.9.1
+hdrdir = /usr/local/include/ruby-1.9.1
+arch_hdrdir = /usr/local/include/ruby-1.9.1/$(arch)
+VPATH = $(srcdir):$(arch_hdrdir)/ruby:$(hdrdir)/ruby
+prefix = $(DESTDIR)/usr/local
+exec_prefix = $(prefix)
+rubylibprefix = $(libdir)/$(RUBY_BASE_NAME)
+bindir = $(exec_prefix)/bin
+sbindir = $(exec_prefix)/sbin
+libexecdir = $(exec_prefix)/libexec
+datarootdir = $(prefix)/share
+datadir = $(datarootdir)
+sysconfdir = $(prefix)/etc
+sharedstatedir = $(prefix)/com
+localstatedir = $(prefix)/var
+includedir = $(prefix)/include
+oldincludedir = $(DESTDIR)/usr/include
+docdir = $(datarootdir)/doc/$(PACKAGE)
+infodir = $(datarootdir)/info
+htmldir = $(docdir)
+dvidir = $(docdir)
+pdfdir = $(docdir)
+psdir = $(docdir)
+libdir = $(exec_prefix)/lib
+localedir = $(datarootdir)/locale
+mandir = $(datarootdir)/man
+ridir = $(datarootdir)/$(RI_BASE_NAME)
+sitedir = $(rubylibprefix)/site_ruby
+vendordir = $(rubylibprefix)/vendor_ruby
+rubyhdrdir = $(includedir)/$(RUBY_BASE_NAME)-$(ruby_version)
+sitehdrdir = $(rubyhdrdir)/site_ruby
+vendorhdrdir = $(rubyhdrdir)/vendor_ruby
+rubylibdir = $(rubylibprefix)/$(ruby_version)
+archdir = $(rubylibdir)/$(arch)
+sitelibdir = $(sitedir)/$(ruby_version)
+sitearchdir = $(sitelibdir)/$(sitearch)
+vendorlibdir = $(vendordir)/$(ruby_version)
+vendorarchdir = $(vendorlibdir)/$(sitearch)
+
+NULLCMD = :
+
+CC = gcc-4.2
+CXX = g++-4.2
+LIBRUBY = $(LIBRUBY_SO)
+LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
+LIBRUBYARG_SHARED = -l$(RUBY_SO_NAME)
+LIBRUBYARG_STATIC = -l$(RUBY_SO_NAME)-static
+OUTFLAG = -o 
+COUTFLAG = -o 
+
+RUBY_EXTCONF_H = 
+cflags   =  $(optflags) $(debugflags) $(warnflags)
+optflags = -O3
+debugflags = -ggdb
+warnflags = -Wextra -Wno-unused-parameter -Wno-parentheses -Wno-long-long -Wno-missing-field-initializers -Wpointer-arith -Wwrite-strings -Wdeclaration-after-statement -Wshorten-64-to-32 -Wimplicit-function-declaration
+CFLAGS   = -fno-common -Wall -I/usr/local/WordNet-2.1/include/ 
+INCFLAGS = -I. -I$(arch_hdrdir) -I$(hdrdir)/ruby/backward -I$(hdrdir) -I$(srcdir)
+DEFS     = 
+CPPFLAGS =  -D_XOPEN_SOURCE -D_DARWIN_C_SOURCE $(DEFS) $(cppflags)
+CXXFLAGS = $(CFLAGS) $(cxxflags)
+ldflags  = -L. -L/usr/local/lib
+dldflags = -Wl,-undefined,dynamic_lookup -Wl,-multiply_defined,suppress -Wl,-flat_namespace
+ARCH_FLAG = 
+DLDFLAGS = $(ldflags) $(dldflags)
+LDSHARED = $(CC) -dynamic -bundle
+LDSHAREDXX = $(CXX) -dynamic -bundle
+AR = ar
+EXEEXT = 
+
+RUBY_BASE_NAME = ruby
+RUBY_INSTALL_NAME = ruby19
+RUBY_SO_NAME = ruby.1.9.1
+arch = x86_64-darwin11.0.0
+sitearch = $(arch)
+ruby_version = 1.9.1
+ruby = /usr/local/bin/ruby19
+RUBY = $(ruby)
+RM = rm -f
+RM_RF = $(RUBY) -run -e rm -- -rf
+RMDIRS = rmdir -p
+MAKEDIRS = mkdir -p
+INSTALL = /usr/bin/install -c
+INSTALL_PROG = $(INSTALL) -m 0755
+INSTALL_DATA = $(INSTALL) -m 644
+COPY = cp
+
+#### End of system configuration section. ####
+
+preload = 
+
+libpath = . $(libdir)
+LIBPATH =  -L. -L$(libdir)
+DEFFILE = 
+
+CLEANFILES = mkmf.log
+DISTCLEANFILES = 
+DISTCLEANDIRS = 
+
+extout = 
+extout_prefix = 
+target_prefix = 
+LOCAL_LIBS = -L/usr/local/WordNet-2.1/lib -lwn
+LIBS = $(LIBRUBYARG_SHARED)  -lpthread -ldl -lobjc 
+SRCS = elemma.c
+OBJS = elemma.o
+TARGET = elemma
+DLLIB = $(TARGET).bundle
+EXTSTATIC = 
+STATIC_LIB = 
+
+BINDIR        = $(bindir)
+RUBYCOMMONDIR = $(sitedir)$(target_prefix)
+RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
+RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
+HDRDIR        = $(rubyhdrdir)/ruby$(target_prefix)
+ARCHHDRDIR    = $(rubyhdrdir)/$(arch)/ruby$(target_prefix)
+
+TARGET_SO     = $(DLLIB)
+CLEANLIBS     = $(TARGET).bundle 
+CLEANOBJS     = *.o  *.bak
+
+all:    $(DLLIB)
+static: $(STATIC_LIB)
+.PHONY: all install static install-so install-rb
+.PHONY: clean clean-so clean-rb
+
+clean-rb-default::
+clean-rb::
+clean-so::
+clean: clean-so clean-rb-default clean-rb
+		@-$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES)
+
+distclean-rb-default::
+distclean-rb::
+distclean-so::
+distclean: clean distclean-so distclean-rb-default distclean-rb
+		@-$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
+		@-$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
+		@-$(RMDIRS) $(DISTCLEANDIRS) 2> /dev/null || true
+
+realclean: distclean
+install: install-so install-rb
+
+install-so: $(RUBYARCHDIR)
+install-so: $(RUBYARCHDIR)/$(DLLIB)
+$(RUBYARCHDIR)/$(DLLIB): $(DLLIB)
+	@-$(MAKEDIRS) $(@D)
+	$(INSTALL_PROG) $(DLLIB) $(@D)
+install-rb: pre-install-rb install-rb-default
+install-rb-default: pre-install-rb-default
+pre-install-rb: Makefile
+pre-install-rb-default: Makefile
+pre-install-rb-default:
+	$(ECHO) installing default elemma libraries
+$(RUBYARCHDIR):
+	$(Q) $(MAKEDIRS) $@
+
+site-install: site-install-so site-install-rb
+site-install-so: install-so
+site-install-rb: install-rb
+
+.SUFFIXES: .c .m .cc .mm .cxx .cpp .C .o
+
+.cc.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.mm.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.cxx.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.cpp.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.C.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) $(COUTFLAG)$@ -c $<
+
+.c.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -c $<
+
+.m.o:
+	$(ECHO) compiling $(<)
+	$(Q) $(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) $(COUTFLAG)$@ -c $<
+
+$(DLLIB): $(OBJS) Makefile
+	$(ECHO) linking shared-object $(DLLIB)
+	@-$(RM) $(@)
+	$(Q) $(LDSHARED) -o $@ $(OBJS) $(LIBPATH) $(DLDFLAGS) $(LOCAL_LIBS) $(LIBS)
+
+
+
+$(OBJS): $(hdrdir)/ruby.h $(hdrdir)/ruby/defines.h $(arch_hdrdir)/ruby/config.h

data/lib/treat/inflectors/lemmatizers/e_lemma/elemma.c

@@ -0,0 +1,68 @@
+#include "wn.h"
+#include "wnconsts.h"
+#include "ruby.h"
+
+/*
+
+Copyright (C) 2004 UTIYAMA Masao <mutiyama@crl.go.jp>
+
+This program 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.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABITreatY 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 this program; if not, write to the Free Software
+Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+*/
+
+static VALUE
+parse(VALUE klass, VALUE rb_word, VALUE rb_pos)
+{
+  char *word;
+  char *POS = STR2CSTR(rb_pos);
+  char *lemma;
+  int pos;
+  VALUE retval = rb_ary_new();
+  
+  word = malloc(strlen(STR2CSTR(rb_word))+1);
+  if(!word){rb_raise(rb_eStandardError, "malloc failed.\n");}
+  strcpy(word, STR2CSTR(rb_word));
+  
+  if(strcmp(POS,"noun")==0){pos = NOUN;}
+  else if(strcmp(POS,"verb")==0){pos = VERB;}
+  else if(strcmp(POS,"adj")==0){pos = ADJ;}
+  else if(strcmp(POS,"adv")==0){pos = ADV;}
+  else{
+    rb_raise(rb_eStandardError, "%s should be (noun|verb|adj|adv)\n", POS);
+  }
+  if(is_defined(word, pos)){
+    /*printf("* %s found as is.\n", word);*/
+    rb_ary_push(retval, rb_str_new2(word));
+  }
+  if((lemma=morphstr(word, pos))!=NULL){
+    do {
+      if(is_defined(lemma, pos)){
+	/*printf("* %s => %s found.\n", word, lemma);*/
+	rb_ary_push(retval, rb_str_new2(lemma));
+      }
+    } while((lemma=morphstr(NULL, pos))!=NULL);
+  }
+  free(word);
+  return retval;
+}
+
+void
+Init_elemma()
+{
+  VALUE mod = rb_define_module("ELemma");
+  rb_define_module_function(mod, "parse", parse, 2);
+  if(wninit()){
+    rb_raise(rb_eStandardError, "Cannot open WordNet database\n");
+  }
+}

data/lib/treat/inflectors/lemmatizers/e_lemma/extconf.rb

@@ -0,0 +1,6 @@
+require 'mkmf'
+
+$CFLAGS = "-Wall -I/usr/local/WordNet-2.1/include/"
+$LOCAL_LIBS = "-L/usr/local/WordNet-2.1/lib -lwn"
+
+create_makefile("elemma")

data/lib/treat/inflectors/ordinal_words/linguistics.rb

@@ -0,0 +1,21 @@
+module Treat
+  module Inflectors
+    module OrdinalWords
+      class Linguistics
+        silently { require 'linguistics' }
+        def self.ordinal_words(number, options = {})
+          begin
+            l = number.language.to_s.upcase
+            delegate = nil
+            silently { delegate = ::Linguistics.const_get(l) }
+          rescue RuntimeError
+            lang = Treat::Resources::Language.describe(number.language)
+            raise "Ruby Linguistics does not have a module " +
+            " installed for the #{lang} language."
+          end
+          silently { delegate.ordinate(number.to_s) }
+        end
+      end
+    end
+  end
+end

data/lib/treat/inflectors/stemmers/porter.rb

@@ -0,0 +1,158 @@
+module Treat
+  module Inflectors
+    module Stemmers
+      # Stem a word using a native Ruby implementation of the
+      # Porter stemming algorithm, ported to Ruby from the
+      # version coded up in Perl.
+      #
+      # Authored by Ray Pereda (raypereda@hotmail.com).
+      #
+      # Original paper: Porter, 1980. An algorithm for suffix stripping, 
+      # Program, Vol. 14, no. 3, pp 130-137,
+      # Original C implementation: http://www.tartarus.org/~martin/PorterStemmer.
+      class Porter
+        # Returns the stem of a word using a native Porter stemmer.
+        # Options: none.
+        def self.stem(word, options = {})
+          # Copy the word and convert it to a string.
+          w = word.to_s
+          return w if w.length < 3
+          # Map initial y to Y so that the patterns 
+          # never treat it as vowel.
+          w[0] = 'Y' if w[0] == ?y
+          # Step 1a
+          if w =~ /(ss|i)es$/
+            w = $` + $1
+          elsif w =~ /([^s])s$/
+            w = $` + $1
+          end
+          # Step 1b
+          if w =~ /eed$/
+            w.chop! if $` =~ MGR0
+          elsif w =~ /(ed|ing)$/
+            stem = $`
+            if stem =~ VOWEL_IN_STEM
+              w = stem
+              case w
+              when /(at|bl|iz)$/             then w << "e"
+              when /([^aeiouylsz])\1$/       then w.chop!
+              when /^#{CC}#{V}[^aeiouwxy]$/o then w << "e"
+              end
+            end
+          end
+          if w =~ /y$/
+            stem = $`
+            w = stem + "i" if stem =~ VOWEL_IN_STEM
+          end
+          # Step 2
+          if w =~ SUFFIX_1_REGEXP
+            stem = $`
+            suffix = $1
+            if stem =~ MGR0
+              w = stem + STEP_2_LIST[suffix]
+            end
+          end
+          # Step 3
+          if w =~ 
+            /(icate|ative|alize|iciti|ical|ful|ness)$/
+            stem = $`
+            suffix = $1
+            if stem =~ MGR0
+              w = stem + STEP_3_LIST[suffix]
+            end
+          end
+          # Step 4
+          if w =~ SUFFIX_2_REGEXP
+            stem = $`
+            if stem =~ MGR1
+              w = stem
+            end
+          elsif w =~ /(s|t)(ion)$/
+            stem = $` + $1
+            if stem =~ MGR1
+              w = stem
+            end
+          end
+          #  Step 5
+          if w =~ /e$/
+            stem = $`
+            if (stem =~ MGR1) ||
+              (stem =~ MEQ1 && stem !~ 
+              /^#{CC}#{V}[^aeiouwxy]$/o)
+              w = stem
+            end
+          end
+          if w =~ /ll$/ && w =~ MGR1
+            w.chop!
+          end
+          # and turn initial Y back to y
+          w[0] = 'y' if w[0] == ?Y
+          w
+        end
+
+        STEP_2_LIST = {
+          'ational'=>'ate', 'tional'=>'tion', 'enci'=>'ence', 'anci'=>'ance',
+          'izer'=>'ize', 'bli'=>'ble',
+          'alli'=>'al', 'entli'=>'ent', 'eli'=>'e', 'ousli'=>'ous',
+          'ization'=>'ize', 'ation'=>'ate',
+          'ator'=>'ate', 'alism'=>'al', 'iveness'=>'ive', 'fulness'=>'ful',
+          'ousness'=>'ous', 'anati'=>'al',
+          'iviti'=>'ive', 'binati'=>'ble', 'logi'=>'log'
+        }
+        STEP_3_LIST = {
+          'icate'=>'ic', 'ative'=>'', 'alize'=>'al', 'iciti'=>'ic',
+          'ical'=>'ic', 'ful'=>'', 'ness'=>''
+        }
+        SUFFIX_1_REGEXP = /(
+        ational  |
+        tional   |
+        enci     |
+        anci     |
+        izer     |
+        bli      |
+        alli     |
+        entli    |
+        eli      |
+        ousli    |
+        ization  |
+        ation    |
+        ator     |
+        alism    |
+        iveness  |
+        fulness  |
+        ousness  |
+        anati    |
+        iviti    |
+        binati   |
+        logi)$/x
+        SUFFIX_2_REGEXP = /(
+        al       |
+        ance     |
+        ence     |
+        er       |
+        ic       |
+        able     |
+        ible     |
+        ant      |
+        ement    |
+        ment     |
+        ent      |
+        ou       |
+        ism      |
+        ate      |
+        iti      |
+        ous      |
+        ive      |
+        ize)$/x
+        C = "[^aeiou]"         # consonant
+        V = "[aeiouy]"         # vowel
+        CC = "#{C}(?>[^aeiouy]*)"  # consonant sequence
+        VV = "#{V}(?>[aeiou]*)"    # vowel sequence
+        MGR0 = /^(#{CC})?#{VV}#{CC}/o                # [cc]vvcc... is m>0
+        MEQ1 = /^(#{CC})?#{VV}#{CC}(#{VV})?$/o       # [cc]vvcc[vv] is m=1
+        MGR1 = /^(#{CC})?#{VV}#{CC}#{VV}#{CC}/o      # [cc]vvccvvcc... is m>1
+        VOWEL_IN_STEM   = /^(#{CC})?#{V}/o                      # vowel in stem
+      end
+    end
+  end
+end