lorax 0.1.0 → 0.2.0

data/README.rdoc

@@ -15,6 +15,8 @@ generates deltas in less than O(n * log n) time, accepting some
 tradeoffs in the size of the delta set. You can find his paper at
 http://gregory.cobena.free.fr/www/Publications/thesis.html.
 
+"I am the Lorax, I speak for the trees."
+
 == Features / Problems
 
 * Detect differences between documents, or tell whether two documents are the same.

data/Rakefile

@@ -5,6 +5,7 @@ gem 'hoe', '>= 2.5.0'
 require 'hoe'
 
 Hoe.plugin :git
+Hoe.plugin :gemspec
 
 Hoe.spec 'lorax' do
   developer "Mike Dalessio", "mike.dalessio@gmail.com"

data/TODO

@@ -1,13 +1,8 @@
 # -*-org-*-
-Diffaroo TODO
+Lorax TODO
 
-* gem
-*** gemspec
-*** license
-*** gemcutter
 * docs
 *** rdocs
-*** readme
 *** class description notes
     - Signature: calculate and persist signatures and weights for nodes in a single document
     - Match:     represents a match between two nodes

data/lib/lorax.rb

@@ -1,7 +1,7 @@
 require 'nokogiri'
 
 module Lorax
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
   REQUIRED_NOKOGIRI_VERSION = "1.4.0"
   raise LoadError, "lorax requires Nokogiri version #{REQUIRED_NOKOGIRI_VERSION} or higher" unless Nokogiri::VERSION >= REQUIRED_NOKOGIRI_VERSION
 end

data/lib/lorax/signature.rb

@@ -19,7 +19,7 @@ module Lorax
     end
 
     def nodes(sig=nil)
-      sig ? @nodes[sig] : @node
+      sig ? @nodes[sig] : [@node]
     end
 
     def size
@@ -30,12 +30,19 @@ module Lorax
       return @signatures[node] if @signatures.key?(node)
       raise ArgumentError, "signature expects a Node, but received #{node.inspect}" unless node.is_a?(Nokogiri::XML::Node)
 
-      if node.text? || node.cdata? || node.comment?
+      if node.text?
+        content = node.content.strip
+        if content.empty?
+          return nil
+        else
+          monogram     = signature = hashify(content)
+        end
+      elsif node.cdata? || node.comment?
         monogram     = signature = hashify(node.content)
       elsif node.type == Nokogiri::XML::Node::ENTITY_REF_NODE
         monogram     = signature = hashify(node.to_html)
       elsif node.element?
-        children_sig = hashify(node.children       .collect { |child| signature(child) })
+        children_sig = hashify(node.children       .collect { |child| signature(child) }.compact)
         attr_sig     = hashify(node.attributes.sort.collect { |k,v|   [k, v.value]     }.flatten)
         monogram     = hashify(node.name, attr_sig)
         signature    = hashify(node.name, attr_sig, children_sig)
@@ -55,16 +62,22 @@ module Lorax
       return @weights[node] if @weights.key?(node)
       raise ArgumentError, "weight expects a Node, but received #{node.inspect}" unless node.is_a?(Nokogiri::XML::Node)
 
-      calculated_weight = \
-        if node.text? || node.cdata? || node.comment?
-          1 + Math.log(node.content.length)
-        elsif node.type == Nokogiri::XML::Node::ENTITY_REF_NODE
-          1
-        elsif node.element?
-          node.children.inject(1) { |sum, child| sum += weight(child) }
-        else
-          raise ArgumentError, "weight expects an element, text, cdata or comment node, but received #{node.class}"
+      if node.text?
+        content = node.content.strip
+        if content.empty?
+          calculated_weight = 0
+        else          
+          calculated_weight = 1 + Math.log(content.length)
         end
+      elsif node.cdata? || node.comment?
+        calculated_weight = 1 + Math.log(node.content.length)
+      elsif node.type == Nokogiri::XML::Node::ENTITY_REF_NODE
+        calculated_weight = 1
+      elsif node.element?
+        calculated_weight = node.children.inject(1) { |sum, child| sum += weight(child) }
+      else
+        raise ArgumentError, "weight expects an element, text, cdata or comment node, but received #{node.class}"
+      end
 
       @weights[node] = calculated_weight
     end

data/spec/unit/signature_spec.rb

@@ -1,6 +1,8 @@
 require File.expand_path(File.dirname(__FILE__) + '/../spec_helper')
 
 describe Lorax::Signature do
+  WHITESPACES = ["\n"," ","\t","\r","\f"]
+
   def assert_node_signature_equal(node1, node2)
     Lorax::Signature.new(node1).signature.should == Lorax::Signature.new(node2).signature
   end
@@ -46,6 +48,18 @@ describe Lorax::Signature do
       node_sig = Lorax::Signature.new(nodes.first)
       doc_sig.nodes(node_sig.signature).should =~ nodes.to_a
     end
+
+    it "returns the node if I pass nil" do
+      doc = xml { root {
+          a1 "hello1"
+          a1 "hello2"
+          a1 "hello3"
+        } }
+      nodes    = doc.css("a1")
+      doc_sig  = Lorax::Signature.new(doc.root)
+      node_sig = Lorax::Signature.new(nodes.first)
+      doc_sig.nodes(nil).should == [doc.root]
+    end
   end
 
   describe "#size" do
@@ -166,24 +180,46 @@ describe Lorax::Signature do
       sig.signature(node)
     end
 
-    context "identical text nodes" do
-      it "have equal signatures" do
+    context "passed a text Node" do
+      it "returns equal signatures for identical text nodes" do
         doc = xml { root {
             span "hello"
             span "hello"
           } }
         assert_node_signature_equal(*doc.css("span").collect { |n| n.children.first })
       end
-    end
 
-    context "different text nodes" do
-      it "have inequal signatures" do
+      it "returns inequal signatures for different text nodes" do
         doc = xml { root {
             span "hello"
             span "goodbye"
           } }
         assert_node_signature_not_equal(*doc.css("span").collect { |n| n.children.first })
       end
+
+      it "ignores leading whitespace" do
+        doc = xml { root {
+            span "hello"
+            span "#{WHITESPACES.join}hello"
+          } }
+        assert_node_signature_equal(*doc.css("span").collect { |n| n.children.first })
+      end
+
+      it "ignores trailing whitespace" do
+        doc = xml { root {
+            span "hello"
+            span "hello#{WHITESPACES.join}"
+          } }
+        assert_node_signature_equal(*doc.css("span").collect { |n| n.children.first })
+      end
+
+      it "treats empty text nodes the same as no text node" do
+        doc = xml { root {
+            span WHITESPACES.join
+            span
+          } }
+        assert_node_signature_equal(*doc.css("span"))
+      end
     end
 
     context "elements with same name (with no attributes and no content)" do

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: lorax
 version: !ruby/object:Gem::Version 
+  hash: 23
   prerelease: false
   segments: 
   - 0
-  - 1
+  - 2
   - 0
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Mike Dalessio
@@ -17,34 +18,36 @@ cert_chain:
   -----BEGIN CERTIFICATE-----
   MIIDPDCCAiSgAwIBAgIBADANBgkqhkiG9w0BAQUFADBEMRYwFAYDVQQDDA1taWtl
   LmRhbGVzc2lvMRUwEwYKCZImiZPyLGQBGRYFZ21haWwxEzARBgoJkiaJk/IsZAEZ
-  FgNjb20wHhcNMDkwODExMDU0MjQ5WhcNMTAwODExMDU0MjQ5WjBEMRYwFAYDVQQD
+  FgNjb20wHhcNMTAwOTMwMDYyNjQ3WhcNMTEwOTMwMDYyNjQ3WjBEMRYwFAYDVQQD
   DA1taWtlLmRhbGVzc2lvMRUwEwYKCZImiZPyLGQBGRYFZ21haWwxEzARBgoJkiaJ
-  k/IsZAEZFgNjb20wggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQDANjr7
-  lZ1DKtK8YvNp+5kBzIpwrpClHRrosqo01qmWfGBxZckQUtrJUwGPxpzvIHVq1VKp
-  a9FXU/QWYek/1S0vhkOf9XGmFBnVCtbJhwGeyzsQFFSoQIfs2hd5gO0dSRpuKdi3
-  slfJAXzFKg1u/7OCVPgrY/mkdh34MzL5p0gSDzPt7vLPibctHg0GoepYT5Fh1tMQ
-  luzgrN0weTw/QoEWTMQcNk6CyUpzv0pOe7d0qEPQ9Lx7Lz64gIym3f0pKFpWLfME
-  l7PFLeR95zw2zsuZQwCR5ma5zjXD3mo2jk1mVqiI8qplOL1u30FU7hRhTV5n/Qe9
-  elDQoZW9Xz0R5JGDAgMBAAGjOTA3MAkGA1UdEwQCMAAwCwYDVR0PBAQDAgSwMB0G
-  A1UdDgQWBBRXWlUJZXcR1jkZPE24+mjUTCqNxjANBgkqhkiG9w0BAQUFAAOCAQEA
-  jDh5M41sg1MZKG1DXzQmo/IADeWRmXyb3EZaED9lhFFpoQqaralgpgmvuc0GswvO
-  QIZijh03tPQz8lgp1U1OFZod2ZwbEVTtVZpxs1ssjMraOA6KzlsNROH0XonIiy6j
-  r2Q0UF35ax8pvr3D5Y6AKzIW1F3aeiREylUDJlb/i1dPQ2PVK0yRrSQoK2epwM9E
-  zoczlHTTJc/tRvH5Up3Agcv9y+J0U9a1Af9NRsnHPVBdo2H32MsJ99x5NRDWJmJg
-  ohH37UR7njcc6j4fo22IwTqXaaXJdtVdAWjXP/xs5B3cPYSP6uqFnR46Jf86Iqj1
-  FlqnTjy13J3nD30uxy9a1g==
+  k/IsZAEZFgNjb20wggEiMA0GCSqGSIb3DQEBAQUAA4IBDwAwggEKAoIBAQDLv4nl
+  BGRtliYy5s5MhlFO88UvkkETFcS79OCaGFKorxPTmcfDrR2/2x0mAySXJ6I1uPEU
+  WSAWaPb1at61NEOvp5kRNzUNdwGakBA/fd1vZ1N2rwHRtjk/8t6DX8yiflr6T761
+  9ZMYPE+t85NvlPt0/WpT778imNZXwGQNcQJwNESDiBTgyjN8bOWpvRrVADVdOCme
+  DW3AfJnF/kdMYuSiUuFMZpyOlULEbOsrvOfUoEKjoFaVNv7FJ28/kLH1UgmtucOD
+  m5bZ/qy5b2+CWzzsmUfysaGnLQ4LjvAFpmgZGAjIE9TnyjU0jw+2e7dq8uRjdnFJ
+  gfWQlnJuwAlZXR1nAgMBAAGjOTA3MAkGA1UdEwQCMAAwCwYDVR0PBAQDAgSwMB0G
+  A1UdDgQWBBRbc4XnK6it228clp2DjyqaVjKW+DANBgkqhkiG9w0BAQUFAAOCAQEA
+  xPtSPtMl9qsgNGcnSDLSTjwGouwsjOB19IbtdODFTabUpRPCk7OFHeYGdJik4iiZ
+  fk10t3vzr6uWMAyOfwpWWFRnEYAvy9ZaMGDIZPKD8xWxaRTLwmi+pQsS8Lo2IpDC
+  Lb+l0lUiRiYS3/Ez7tA6pS122cvuQroWfuqh5Mi3pNAi1nuBTlhCNJuR5XUaOjqs
+  DAoZLfYEEW+4bmkAb6ky2TPUslaln56PO3/JG+IfWZwCvTFFVdKRBKXqLaAxO9rv
+  7nflCv7xpUSUGGZ6hoPG8dil+Mp/kKV8cb1kxZz+C8660hC93dJ3FQ3adX30ylvZ
+  C4THW+6HEQDCdOkiArif8A==
   -----END CERTIFICATE-----
 
-date: 2010-03-09 00:00:00 -05:00
+date: 2010-10-14 00:00:00 -04:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
   name: nokogiri
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 7
         segments: 
         - 1
         - 4
@@ -56,72 +59,66 @@ dependencies:
   name: rubyforge
   prerelease: false
   requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 7
         segments: 
         - 2
         - 0
-        - 3
-        version: 2.0.3
+        - 4
+        version: 2.0.4
   type: :development
   version_requirements: *id002
-- !ruby/object:Gem::Dependency 
-  name: gemcutter
-  prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 3
-        - 0
-        version: 0.3.0
-  type: :development
-  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: rspec
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 13
         segments: 
         - 1
         - 2
         - 9
         version: 1.2.9
   type: :development
-  version_requirements: *id004
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: rr
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 63
         segments: 
         - 0
         - 10
         - 4
         version: 0.10.4
   type: :development
-  version_requirements: *id005
+  version_requirements: *id004
 - !ruby/object:Gem::Dependency 
   name: hoe
   prerelease: false
-  requirement: &id006 !ruby/object:Gem::Requirement 
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
+        hash: 21
         segments: 
         - 2
-        - 5
-        - 0
-        version: 2.5.0
+        - 6
+        - 1
+        version: 2.6.1
   type: :development
-  version_requirements: *id006
+  version_requirements: *id005
 description: |-
   The Lorax is a full diff and patch library for XML/HTML documents, based on Nokogiri.
   
@@ -133,6 +130,8 @@ description: |-
   generates deltas in less than O(n * log n) time, accepting some
   tradeoffs in the size of the delta set. You can find his paper at
   http://gregory.cobena.free.fr/www/Publications/thesis.html.
+  
+  "I am the Lorax, I speak for the trees."
 email: 
 - mike.dalessio@gmail.com
 executables: 
@@ -192,23 +191,27 @@ rdoc_options:
 require_paths: 
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
   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 
+      hash: 3
       segments: 
       - 0
       version: "0"
 requirements: []
 
 rubyforge_project: lorax
-rubygems_version: 1.3.6
+rubygems_version: 1.3.7
 signing_key: 
 specification_version: 3
 summary: The Lorax is a full diff and patch library for XML/HTML documents, based on Nokogiri