pms 0.0.5 → 0.0.6

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e737f3b6406adce6fe95366111056f19aa66a0a8
+  data.tar.gz: 08778e9a99a3c8097ae295f5d3602e8d45d34ad3
+SHA512:
+  metadata.gz: 5a35f3969576b684d09317f79a8bd11fc14b9ab7a1347fa0935ff81a3c0ee5564a1de7af8b6d5f3133a47ce63790a666d3a50c4cd78b49c4d2277c6d6a6b08d7
+  data.tar.gz: 9509b550351d1606f039a14a531dfe1b72b19d1e610140ad52ad796f12948020527591e07a70f613a21b8bfe4864b4c87fe22b75aded7aa0ccdcdcc3bcc4faa0

data/ChangeLog

@@ -1,5 +1,16 @@
+# markup: rd
+
 = Revision history for pms
 
+== 0.0.6 [2013-12-19]
+
+* Added LSI support.
+* Housekeeping and fixes.
+
+== 0.0.5 [2011-04-29]
+
+* Housekeeping.
+
 == 0.0.4 [2010-10-24]
 
 * Some code cleanup.

data/README

@@ -2,7 +2,7 @@
 
 == VERSION
 
-This documentation refers to pms version 0.0.5
+This documentation refers to pms version 0.0.6
 
 
 == DESCRIPTION
@@ -45,19 +45,19 @@ You can find more examples in the <tt>spec/</tt> directory.
 == LINKS
 
 <b></b>
-Documentation::     http://pms.rubyforge.org/
-Source code::       http://github.com/blackwinter/pms
-RubyForge project:: http://rubyforge.org/projects/pms
+Documentation:: http://blackwinter.github.com/pms
+Source code::   http://github.com/blackwinter/pms
+RubyGem::       http://rubygems.org/gems/pms
 
 
 == AUTHORS
 
-* Jens Wille <mailto:jens.wille@uni-koeln.de>
+* Jens Wille <mailto:jens.wille@gmail.com>
 
 
 == LICENSE AND COPYRIGHT
 
-Copyright (C) 2008-2011 Jens Wille
+Copyright (C) 2008-2013 Jens Wille
 
 pms is free software: you can redistribute it and/or modify it under the
 terms of the GNU Affero General Public License as published by the Free

data/Rakefile

@@ -4,15 +4,15 @@ begin
   require 'hen'
 
   Hen.lay! {{
-    :rubyforge => {
-      :project => %q{pms}
-    },
-
     :gem => {
-      :version => PMS::VERSION,
-      :summary => %q{Poor Man's Search},
-      :author  => %q{Jens Wille},
-      :email   => %q{jens.wille@uni-koeln.de}
+      :name         => %q{pms},
+      :version      => PMS::VERSION,
+      :summary      => %q{Poor Man's Search},
+      :author       => %q{Jens Wille},
+      :email        => %q{jens.wille@gmail.com},
+      :license      => %q{AGPL-3.0},
+      :homepage     => :blackwinter,
+      :dependencies => %w[unicode] << ['ruby-nuggets', '>= 0.9.4']
     }
   }}
 rescue LoadError => err

data/lib/pms.rb

@@ -3,10 +3,10 @@
 #                                                                             #
 # pms - Poor Man's Search.                                                    #
 #                                                                             #
-# Copyright (C) 2008-2011 Jens Wille                                          #
+# Copyright (C) 2008-2013 Jens Wille                                          #
 #                                                                             #
 # Authors:                                                                    #
-#     Jens Wille <jens.wille@uni-koeln.de>                                    #
+#     Jens Wille <jens.wille@gmail.com>                                       #
 #                                                                             #
 # pms is free software; you can redistribute it and/or modify it under the    #
 # terms of the GNU Affero General Public License as published by the Free     #
@@ -32,9 +32,9 @@ class PMS
 
   attr_reader :input, :index
 
-  def initialize(input)
+  def initialize(input, options = {})
     @input = input
-    @index = Index.new(input)
+    @index = Index.new(input, options)
   end
 
   def search(token = nil, &block)

data/lib/pms/ext.rb

@@ -3,10 +3,10 @@
 #                                                                             #
 # A component of pms, Poor Man's Search.                                      #
 #                                                                             #
-# Copyright (C) 2008-2011 Jens Wille                                          #
+# Copyright (C) 2008-2013 Jens Wille                                          #
 #                                                                             #
 # Authors:                                                                    #
-#     Jens Wille <jens.wille@uni-koeln.de>                                    #
+#     Jens Wille <jens.wille@gmail.com>                                       #
 #                                                                             #
 # pms is free software; you can redistribute it and/or modify it under the    #
 # terms of the GNU Affero General Public License as published by the Free     #

data/lib/pms/index.rb

@@ -3,10 +3,10 @@
 #                                                                             #
 # A component of pms, Poor Man's Search.                                      #
 #                                                                             #
-# Copyright (C) 2008-2011 Jens Wille                                          #
+# Copyright (C) 2008-2013 Jens Wille                                          #
 #                                                                             #
 # Authors:                                                                    #
-#     Jens Wille <jens.wille@uni-koeln.de>                                    #
+#     Jens Wille <jens.wille@gmail.com>                                       #
 #                                                                             #
 # pms is free software; you can redistribute it and/or modify it under the    #
 # terms of the GNU Affero General Public License as published by the Free     #
@@ -24,19 +24,23 @@
 ###############################################################################
 #++
 
+require 'unicode'
+
 class PMS
 
   class Index
 
     TOKEN_RE = %r{\w+}
 
+    DEFAULT_LSI = 0.05
+
     attr_reader :input, :index, :entries
 
-    def initialize(input)
-      raise ArgumentError, "input must implement #each" unless input.respond_to?(:each)
+    def initialize(input, options = {})
+      @input = input.respond_to?(:each) ? input : input.is_a?(String) ?
+        input.each_line : raise(ArgumentError, 'input must implement #each')
 
-      @input = input
-      build_index
+      build_index(options)
     end
 
     def doc_nums_with_positions(token)
@@ -53,7 +57,7 @@ class PMS
           res
         else
           raise TypeError, "expected String or Regexp, got #{token.class}"
-      end
+      end.each { |_, positions| positions.compact! }
     end
 
     alias_method :results_with_positions, :doc_nums_with_positions
@@ -64,7 +68,7 @@ class PMS
 
     alias_method :results, :doc_nums
 
-    def documents(doc_nums = default = Object.new)
+    def documents(doc_nums = default = true)
       @documents ||= get_documents
       default ? @documents : @documents.values_at(*doc_nums)
     end
@@ -79,7 +83,14 @@ class PMS
 
     private
 
-    def build_index
+    def build_index(options)
+      if lsi = options[:lsi]
+        require 'nuggets/lsi'
+
+        lsi = DEFAULT_LSI if lsi == true
+        map = Hash.new { |h, k| h[k] = [] }
+      end
+
       @documents, @entries, doc_num = nil, [], -1
       index = Hash.new { |h, k| h[k] = Hash.new { |i, j| i[j] = [] } }
 
@@ -88,10 +99,15 @@ class PMS
         pos = -1
 
         doc.scan(TOKEN_RE) { |token|
-          index[mangle_token(token)][doc_num] << pos += 1
+          index[term = mangle_token(token)][doc_num] << pos += 1
+          map[doc_num] << term if map
         }
       }
 
+      Nuggets::LSI.each_norm(map, :min => lsi, :new => true) { |d, k, _|
+        index[mangle_token(k)][d.key] << nil
+      } if lsi
+
       @index = index
     end
 
@@ -104,7 +120,7 @@ class PMS
     end
 
     def mangle_token(token)
-      token.downcase
+      Unicode.downcase(token)
     end
 
   end

data/lib/pms/proxy.rb

@@ -3,10 +3,10 @@
 #                                                                             #
 # A component of pms, Poor Man's Search.                                      #
 #                                                                             #
-# Copyright (C) 2008-2011 Jens Wille                                          #
+# Copyright (C) 2008-2013 Jens Wille                                          #
 #                                                                             #
 # Authors:                                                                    #
-#     Jens Wille <jens.wille@uni-koeln.de>                                    #
+#     Jens Wille <jens.wille@gmail.com>                                       #
 #                                                                             #
 # pms is free software; you can redistribute it and/or modify it under the    #
 # terms of the GNU Affero General Public License as published by the Free     #
@@ -131,6 +131,15 @@ class PMS
     alias_method :adj, :adjacent
     alias_method :^, :adjacent
 
+    private
+
+    def clone_with_results(results)
+      clone = super
+      clone.instance_variable_set(:@results_with_positions,
+        @results_with_positions.dup.delete_if { |k, _| !results.include?(k) })
+      clone
+    end
+
   end
 
 end

data/lib/pms/version.rb

@@ -4,7 +4,7 @@ class PMS
 
     MAJOR = 0
     MINOR = 0
-    TINY  = 5
+    TINY  = 6
 
     class << self
 

data/spec/pms/ext_spec.rb

@@ -44,7 +44,7 @@ shared_examples_for 'most Searchables' do
 
 end
 
-describe String, ' when extended by pms' do
+describe String, 'when extended by pms' do
 
   before :each do
     @searchable = File.read(FOX)
@@ -55,7 +55,7 @@ describe String, ' when extended by pms' do
 
 end
 
-describe IO, ' when extended by pms' do
+describe IO, 'when extended by pms' do
 
   before :each do
     @searchable = File.open(FOX)
@@ -66,7 +66,7 @@ describe IO, ' when extended by pms' do
 
 end
 
-describe Array, ' when extended by pms' do
+describe Array, 'when extended by pms' do
 
   before :each do
     @searchable = File.readlines(FOX)
@@ -77,7 +77,7 @@ describe Array, ' when extended by pms' do
 
 end
 
-describe File, ' when extended by pms' do
+describe File, 'when extended by pms' do
 
   before :each do
     @searchable = File

data/spec/pms/index_spec.rb

@@ -16,7 +16,7 @@ describe PMS::Index do
 
 end
 
-describe PMS::Index, ' with exhaustable input' do
+describe PMS::Index, 'with exhaustable input' do
 
   before :each do
     # already seeks to EOF in #build_index
@@ -28,3 +28,11 @@ describe PMS::Index, ' with exhaustable input' do
   end
 
 end
+
+describe PMS::Index, 'with invalid input' do
+
+  it 'should raise an error' do
+    lambda { PMS::Index.new(123) }.should raise_error(ArgumentError)
+  end
+
+end

data/spec/pms_spec.rb

@@ -107,3 +107,22 @@ describe PMS do
   end
 
 end
+
+describe PMS, 'with LSI' do
+
+  before :each do
+    @pms1 = PMS.new(File.read(FOX))
+    @pms2 = PMS.new(File.read(FOX), :lsi => true)
+  end
+
+  it 'should find more ducks' do
+    @pms1.search('ducks').results.should == [1]
+    @pms2.search('ducks').results.should == [1, 4, 5]
+  end
+
+  it 'should not report positions for LSI terms' do
+    @pms1.search('ducks').results_with_positions.values.flatten.should == [12]
+    @pms2.search('ducks').results_with_positions.values.flatten.should == [12]
+  end
+
+end

metadata

@@ -1,89 +1,104 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: pms
-version: !ruby/object:Gem::Version 
-  hash: 21
-  prerelease: 
-  segments: 
-  - 0
-  - 0
-  - 5
-  version: 0.0.5
+version: !ruby/object:Gem::Version
+  version: 0.0.6
 platform: ruby
-authors: 
+authors:
 - Jens Wille
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-04-29 00:00:00 Z
-dependencies: []
-
+date: 2013-12-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: unicode
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: ruby-nuggets
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.4
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.9.4
 description: Poor Man's Search
-email: jens.wille@uni-koeln.de
+email: jens.wille@gmail.com
 executables: []
-
 extensions: []
-
-extra_rdoc_files: 
+extra_rdoc_files:
 - README
 - COPYING
 - ChangeLog
-files: 
+files:
 - lib/pms.rb
+- lib/pms/ext.rb
 - lib/pms/index.rb
 - lib/pms/proxy.rb
-- lib/pms/ext.rb
 - lib/pms/version.rb
-- README
+- COPYING
 - ChangeLog
+- README
 - Rakefile
-- COPYING
-- spec/pms/index_spec.rb
+- spec/fox.txt
 - spec/pms/ext_spec.rb
+- spec/pms/index_spec.rb
 - spec/pms/proxy_spec.rb
+- spec/pms_spec.rb
 - spec/spec.opts
-- spec/fox.txt
 - spec/spec_helper.rb
-- spec/pms_spec.rb
-homepage: http://pms.rubyforge.org/
-licenses: []
+homepage: http://github.com/blackwinter/pms
+licenses:
+- AGPL-3.0
+metadata: {}
+post_install_message: |2+
 
-post_install_message: 
-rdoc_options: 
-- --line-numbers
-- --main
-- README
-- --charset
+  pms-0.0.6 [2013-12-19]:
+
+  * Added LSI support.
+  * Housekeeping and fixes.
+
+rdoc_options:
+- "--title"
+- pms Application documentation (v0.0.6)
+- "--charset"
 - UTF-8
-- --all
-- --title
-- pms Application documentation (v0.0.5)
-require_paths: 
+- "--line-numbers"
+- "--all"
+- "--main"
+- README
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
-  none: false
-  requirements: 
+required_ruby_version: !ruby/object:Gem::Requirement
+  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
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
   - - ">="
-    - !ruby/object:Gem::Version 
-      hash: 3
-      segments: 
-      - 0
-      version: "0"
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
-rubyforge_project: pms
-rubygems_version: 1.7.2
+rubyforge_project: 
+rubygems_version: 2.1.11
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Poor Man's Search
 test_files: []
-