diffxml 0.1.3 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ad594b1f585f2afc514092865831361f97bfd81d
-  data.tar.gz: 1c14e5f16aef2c40f9448a1fc74e9884328452c5
+  metadata.gz: 26d733a1a7c9f08ef8c081456aacb00972a54558
+  data.tar.gz: a8d24b26f97175818bd199436c3df76b2dbc962a
 SHA512:
-  metadata.gz: 0f091b0a49c9c1e17601ac1e23b721aaaf0616988b149d020de420b4b709bce1c77c31df1f342817425ba2fce4f600b6162beb5b2034878793b708a8f2b2b7fc
-  data.tar.gz: a8cff8e5e6f9088628407b25aa9fc6e9c0f9ff6c5cc8eaf720afba6e5c1993af3ed56393096d8776fbdc12aa1f0defaf6c6b8777926315b5cbca8f3609250cd5
+  metadata.gz: f5578ee34dd1776e2dcdc9ab9b1afacba42208702b6f858edd7d7de3be98f274627640289cb2e691f490a9d1cf46e1ed757aaca049b34a246ac136d2502b59fc
+  data.tar.gz: 4ba3c68fba21b859e1985445b826cb093685926998eb32fc9da3fa0e0d18b5a146baa4a5da028001218d9e9d4e22078491e733672d3cda8a2ac603c0b4eb0d4f

data/README.md

@@ -39,12 +39,14 @@ the returned value will be an array with the XPaths of all nodes that were not m
 * Plans to return the values of both nodes that are at the XPath in the array, as well as the XPath location are in the works.
 * General upkeep and a more rigorous test set are also planned.
 * RDoc implementation for documentation.
-* optimize searches
+* optimize searches: the memory handling has been improved, however, the search still does not differentiate between nodes with the same path, meaning xmls in different orders may report false negatives(untested)
+because it just compares the string of the node set as opposed to comparing each node in the set individually.
 * Add ignore capabilities for XPaths
 * Refactor Utility methods into seperate file
 
 ## Known Issues
-* With large XML documents, specifically with tested documents over 1500 elements, but possibly fewer, the gem will reach a point where it cannot allocate memory.
+* ~~With large XML documents, specifically with tested documents over 1500 elements, but possibly fewer, the gem will reach a point where it cannot allocate memory.~~
+  * Fixed in latest commit, will be applied with version 0.2.0 release, optimization of the compare is still needed. HUGE increase in speed when only collecting namespaces once 5500 seconds to 55 seconds!
 
 ## Contributing
 

data/diffxml.gemspec

@@ -4,7 +4,7 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 
 Gem::Specification.new do |spec|
   spec.name          = "diffxml"
-  spec.version       = '0.1.3'
+  spec.version       = '0.2.0'
   spec.authors       = ["Jake Bubnar"]
   spec.email         = ["jake@pjbapps.com"]
   spec.licenses       = ["MIT"]

data/lib/diffxml.rb

@@ -3,12 +3,16 @@ require 'Nokogiri'
 module DiffXML
   @xpathArray = []
   def self.compareXML(doc1, doc2)
+    @namespaces = doc1.collect_namespaces
     if doc1.class == Nokogiri::XML::Document
       collectXPaths(doc1.root)
     else
       collectXPaths(doc1)
     end
-    @xpathArray.delete_if {|element| compareToPath(element,doc1, doc2)}
+    @xpathArray.delete_if.with_index do |element, i|
+      puts "iteration #{i} and #{element}"
+      compareToPath(element, doc1, doc2)
+    end
   end
 
   def self.getPath(node, path = nil)
@@ -24,7 +28,7 @@ module DiffXML
   end
 
   def self.compareToPath(path, doc1, doc2)
-    doc2.search(path, doc1.collect_namespaces).to_s == doc1.search(path, doc1.collect_namespaces).to_s
+    doc2.search(path, @namespaces).to_s == doc1.search(path, @namespaces).to_s
   end
 
   def self.collectXPaths(doc)

data/rspec/diffXML_spec.rb

@@ -1,7 +1,7 @@
 require 'nokogiri'
 require 'rspec'
 require 'rspec/matchers'
-require_relative '../lib/diffXML/diffxml'
+require_relative '../lib/diffxml'
 
 describe DiffXML do
   xml1 = Nokogiri::XML("<doc xmlns='foo:bar'><first>foo  bar baz</first><second>things</second><third>
@@ -41,4 +41,10 @@ describe DiffXML do
     expect(DiffXML.getXPathArray[0].to_s).to eql 'doc/third/firstthird/finalChild'
   end
 
+  it 'should handle large xml documents without running out of memory' do
+    largeXML1 = Nokogiri::XML(File.read('./wikimediaxml_test.xml'))
+    largeXML2 = Nokogiri::XML(File.read('./wikimediaxml_test.xml'))
+    expect(DiffXML.compareXML(largeXML1,largeXML2).size).to be 0
+  end
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: diffxml
 version: !ruby/object:Gem::Version
-  version: 0.1.3
+  version: 0.2.0
 platform: ruby
 authors:
 - Jake Bubnar
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-23 00:00:00.000000000 Z
+date: 2016-03-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler