picky 4.19.3 → 4.19.4

data/lib/picky/splitters/automatic.rb

@@ -56,18 +56,25 @@ module Picky
         end
       end
       
+      def segment text, use_partial = false
+        segments, score = segment_recursively text, use_partial
+        [segments, score && score-text.size+segments.size]
+      end
+      
       # Segments the given text recursively.
       #
-      def segment text, use_partial = false
+      def segment_recursively text, use_partial = false
         (use_partial ? @partial_memo : @exact_memo)[text] ||= splits(text).inject([[], nil]) do |(current, heaviest), (head, tail)|
           tail_weight = use_partial ? @partial.weight(tail) : @exact.weight(tail)
+          tail_weight && tail_weight += (tail.size-1)
           
-          segments, head_weight = segment head
+          segments, head_weight = segment_recursively head, use_partial
           
           weight = (head_weight && tail_weight &&
                    (head_weight + tail_weight) ||
                    tail_weight || head_weight)
-          if (weight || -1) > (heaviest || 0)
+                   
+          if (weight || -1) >= (heaviest || 0)
             [tail_weight ? segments + [tail] : segments, weight]
           else
             [current, heaviest]

data/spec/functional/automatic_segmentation_spec.rb

@@ -21,6 +21,19 @@ describe "automatic splitting" do
     
     index
   end
+
+  context 'splitting the text automatically' do
+    let(:automatic_splitter) { Picky::Splitters::Automatic.new index[:text] }
+    
+    # It splits the text correctly.
+    #
+    it do
+      automatic_splitter.segment('purplerainbow').should == [
+        ['purple', 'rain', 'bow'],
+        2.078999999999999
+      ]
+    end
+  end
   
   context 'splitting the text automatically' do
     let(:automatic_splitter) { Picky::Splitters::Automatic.new index[:text] }
@@ -56,6 +69,12 @@ describe "automatic splitting" do
     it { automatic_splitter.split('purplerain').should == ['purple', 'rain'] }
     it { automatic_splitter.split('purple').should == ['purple'] }
     
+    # Creates the right queries (see below).
+    #
+    it { automatic_splitter.split('colorpurple').should == ['color', 'purple'] }
+    it { automatic_splitter.split('bownew').should == ['bow', 'new'] }
+    it { automatic_splitter.split('spainisking').should == ['spain', 'is', 'king'] }
+    
     # When it can't, it splits it using the partial index (correctly).
     #
     it { automatic_splitter.split('purplerainbo').should == ['purple', 'rain', 'bo'] }

data/spec/functional/automatic_segmentation_with_small_partials_spec.rb

@@ -0,0 +1,52 @@
+# encoding: utf-8
+#
+require 'spec_helper'
+
+describe "partial automatic splitting with small partials" do
+  
+  let(:index) do
+    index = Picky::Index.new :automatic_text_splitting do
+      indexing removes_characters: /[^a-z\s]/i,
+               stopwords: /\b(in|a)\b/
+      category :text,
+                partial: Picky::Partial::Postfix.new(from: 1)
+    end
+    index.replace_from id: 1, text: 'Rainbow'
+    index
+  end
+
+  context 'splitting the text automatically' do
+    let(:automatic_splitter) {
+      Picky::Splitters::Automatic.new index[:text], partial: true }
+    
+    # It splits the text correctly.
+    #
+    it do
+      automatic_splitter.segment('rainbow', true).should == [
+        ['rainbow'],
+        0.0
+      ]
+    end
+  end
+  
+  context 'splitting the text automatically' do
+    let(:automatic_splitter) { Picky::Splitters::Automatic.new index[:text], partial: true }
+    
+    # It splits the text correctly.
+    #
+    it { automatic_splitter.split('rainbowrainbow').should == ['rainbow', 'rainbow'] }
+    it { automatic_splitter.split('rainbowrain').should == ['rainbow', 'rain'] }
+    it { automatic_splitter.split('rain').should == ['rain'] }
+    
+    # When it can't, it splits it using the partial index (correctly).
+    #
+    it { automatic_splitter.split('r').should == ['r'] }
+    it { automatic_splitter.split('rr').should == ['r', 'r'] }
+    it { automatic_splitter.split('rrr').should == ['r', 'r', 'r'] }
+    it { automatic_splitter.split('rrrr').should  == ['r', 'r', 'r', 'r'] }
+    
+    it { automatic_splitter.split('rarara').should == ['ra', 'ra', 'ra'] }
+    it { automatic_splitter.split('rainrairar').should  == ['rain', 'rai', 'ra', 'r'] }
+  end
+
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: picky
 version: !ruby/object:Gem::Version
-  version: 4.19.3
+  version: 4.19.4
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-12-01 00:00:00.000000000 Z
+date: 2013-12-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec
@@ -50,7 +50,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 4.19.3
+        version: 4.19.4
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -58,7 +58,7 @@ dependencies:
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: 4.19.3
+        version: 4.19.4
 - !ruby/object:Gem::Dependency
   name: text
   requirement: !ruby/object:Gem::Requirement
@@ -284,6 +284,7 @@ files:
 - spec/functional/allocations_uniq_by_definition_spec.rb
 - spec/functional/arrays_as_ids_spec.rb
 - spec/functional/automatic_segmentation_spec.rb
+- spec/functional/automatic_segmentation_with_small_partials_spec.rb
 - spec/functional/backends/file_spec.rb
 - spec/functional/backends/memory_bundle_realtime_spec.rb
 - spec/functional/backends/memory_json_utf8_spec.rb
@@ -461,6 +462,7 @@ test_files:
 - spec/functional/allocations_uniq_by_definition_spec.rb
 - spec/functional/arrays_as_ids_spec.rb
 - spec/functional/automatic_segmentation_spec.rb
+- spec/functional/automatic_segmentation_with_small_partials_spec.rb
 - spec/functional/backends/file_spec.rb
 - spec/functional/backends/memory_bundle_realtime_spec.rb
 - spec/functional/backends/memory_json_utf8_spec.rb