nori 2.5.0 → 2.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 5734d4c7a672d830ea4199339b869da468bc2eab
-  data.tar.gz: d590616887899c0c17739e95b4f46e64ba12a367
+SHA256:
+  metadata.gz: 6515a0d2251bf29125e62c2d84f2af5a8476bd61e034366a5a648e50cf828f82
+  data.tar.gz: 68cff0141890e2bbc25318a6661a0b575d8920728455db6140cc17857434a798
 SHA512:
-  metadata.gz: ce4642320270373612e945d7912269e45541954ca9b1f163c81e9527333994aa6f1c2f289d11fc61c3768aea76dffcd3d64923f830e2439e995c2d305a6140e5
-  data.tar.gz: 0f3b03f4ffda5f874fd5a5780de08bbb891167351ea67c69d2f8b86f49e0a65f8b11582e0070343731398641afda5ae9b881f6ea308556f9ff1bdb98af3576b6
+  metadata.gz: 54053888a425e88dc43628927d911e3eb1c087d86d5140febe0ca0a3acc21eacb156a9ae43a1e609b20a89d83eb13f360c15ecb7bc3d70208b00088ea92e7b4c
+  data.tar.gz: 3d3c2eb4b821d260198fa223dfd1c186d17e821cbeea1741284af38216b397a1ac6c6e49f9d18963c0638ed09163e300f2f017dca718aa3bda07704d1d30dc5a

data/.devcontainer/devcontainer.json

@@ -0,0 +1,19 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/ruby
+{
+	"name": "Ruby",
+	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+	"image": "mcr.microsoft.com/devcontainers/ruby:0-3-bullseye"
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

data/.github/dependabot.yml

@@ -0,0 +1,12 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for more information:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# https://containers.dev/guide/dependabot
+
+version: 2
+updates:
+ - package-ecosystem: "devcontainers"
+   directory: "/"
+   schedule:
+     interval: weekly

data/.github/workflows/test.yml

@@ -0,0 +1,26 @@
+name: CI
+
+on: [push, pull_request]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    
+    strategy:
+      matrix:
+        ruby-version:
+          - '3.0'
+          - '3.1'
+          - '3.2'
+          - '3.3'
+          - 'head'
+          - jruby-9.4.5.0
+    steps:
+    - uses: actions/checkout@v4
+    - name: Set up Ruby ${{ matrix.ruby-version }}
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby-version }}
+        bundler-cache: true # runs 'bundle install' and caches installed gems automatically        
+    - name: Run tests
+      run: bundle exec rake

data/CHANGELOG.md

@@ -1,3 +1,14 @@
+# 2.7.0 (2024-02-13)
+
+* Added support for ruby 3.1, 3.2, 3.3. Dropped support for ruby 2.7 and below.
+* Feature: `Nori::Parser` has a new option, `:scrub_xml`, which defaults to true, for scrubbing invalid characters ([#72](https://github.com/savonrb/nori/pull/72)). This should allow documents containing invalid characters to still be parsed.
+* Fix: REXML parser changes `&lt;` inside CDATA to `<` ([#94](https://github.com/savonrb/nori/pull/94))
+* Change: `Object#blank?` is no longer patched in.
+
+# 2.6.0 (2015-05-06)
+
+* Feature: [#69](https://github.com/savonrb/nori/pull/69) Add option to convert empty tags to a value other than nil.
+
 # 2.5.0 (2015-03-31)
 
 * Formally drop support for ruby 1.8.7. Installing Nori from rubygems for that version should no longer attempt to install versions that will not work.

data/Gemfile

@@ -1,9 +1,6 @@
 source 'https://rubygems.org'
 gemspec
 
-platform :rbx do
-  gem 'json'
-  gem 'racc'
-  gem 'rubysl'
-  gem 'rubinius-coverage'
+if RUBY_VERSION >= "3"
+  gem "rexml", "~> 3.2"
 end

data/README.md

@@ -1,21 +1,11 @@
 Nori
 ====
 
-[![Build Status](https://secure.travis-ci.org/savonrb/nori.png)](http://travis-ci.org/savonrb/nori)
-[![Gem Version](https://badge.fury.io/rb/nori.png)](http://badge.fury.io/rb/nori)
-[![Code Climate](https://codeclimate.com/github/savonrb/nori.png)](https://codeclimate.com/github/savonrb/nori)
-[![Coverage Status](https://coveralls.io/repos/savonrb/nori/badge.png?branch=master)](https://coveralls.io/r/savonrb/nori)
+[![CI](https://github.com/savonrb/nori/actions/workflows/test.yml/badge.svg)](https://github.com/savonrb/nori/actions/workflows/test.yml)
+[![Gem Version](https://badge.fury.io/rb/nori.svg)](http://badge.fury.io/rb/nori)
+[![Code Climate](https://codeclimate.com/github/savonrb/nori.svg)](https://codeclimate.com/github/savonrb/nori)
 
-
-Really simple XML parsing ripped from Crack which ripped it from Merb.  
-Nori was created to bypass the stale development of Crack, improve its XML parser  
-and fix certain issues.
-
-``` ruby
-parser = Nori.new
-parser.parse("<tag>This is the contents</tag>")
-# => { 'tag' => 'This is the contents' }
-```
+Really simple XML parsing ripped from Crack, which ripped it from Merb.  
 
 Nori supports pluggable parsers and ships with both REXML and Nokogiri implementations.  
 It defaults to Nokogiri since v2.0.0, but you can change it to use REXML via:
@@ -24,64 +14,96 @@ It defaults to Nokogiri since v2.0.0, but you can change it to use REXML via:
 Nori.new(:parser => :rexml)  # or :nokogiri
 ```
 
-Make sure Nokogiri is in your LOAD_PATH when parsing XML, because Nori tries to load it  
-when it's needed.
+Make sure Nokogiri is in your LOAD_PATH when parsing XML, because Nori tries to load it when it's needed.
 
+# Examples
 
-Typecasting
------------
+```ruby
+Nori.new.parse("<tag>This is the content</tag>")
+# => {"tag"=>"This is the content"}
 
-Besides regular typecasting, Nori features somewhat "advanced" typecasting:
+Nori.new.parse('<foo />')
+#=> {"foo"=>nil}
 
-* "true" and "false" String values are converted to `TrueClass` and `FalseClass`.
-* String values matching xs:time, xs:date and xs:dateTime are converted
-  to `Time`, `Date` and `DateTime` objects.
+Nori.new.parse('<foo bar />')
+#=> {}
 
-You can disable this feature via:
+Nori.new.parse('<foo bar="baz"/>')
+#=> {"foo"=>{"@bar"=>"baz"}}
 
-``` ruby
-Nori.new(:advanced_typecasting => false)
+Nori.new.parse('<foo bar="baz">Content</foo>')
+#=> {"foo"=>"Content"}
 ```
 
+## Nori::StringWithAttributes
 
-Namespaces
-----------
+You can access a string node's attributes via `attributes`.
 
-Nori can strip the namespaces from your XML tags. This feature might raise  
-problems and is therefore disabled by default. Enable it via:
+```ruby
+result = Nori.new.parse('<foo bar="baz">Content</foo>')
+#=> {"foo"=>"Content"}
 
-``` ruby
-Nori.new(:strip_namespaces => true)
+result["foo"].class
+# => Nori::StringWithAttributes
+
+result["foo"].attributes
+# => {"bar"=>"baz"}
 ```
 
+## advanced_typecasting
+
+Nori can automatically convert string values to `TrueClass`, `FalseClass`, `Time`, `Date`, and `DateTime`:
+
+```ruby
+# "true" and "false" String values are converted to `TrueClass` and `FalseClass`.
+Nori.new.parse("<value>true</value>")
+# => {"value"=>true}
 
-XML tags -> Hash keys
----------------------
+# String values matching xs:time, xs:date and xs:dateTime are converted to `Time`, `Date` and `DateTime` objects.
+Nori.new.parse("<value>09:33:55.7Z</value>")
+# => {"value"=>2022-09-29 09:33:55.7 UTC
 
-Nori lets you specify a custom formula to convert XML tags to Hash keys.  
-Let me give you an example:
+# disable with advanced_typecasting: false
+Nori.new(advanced_typecasting: false).parse("<value>true</value>")
+# => {"value"=>"true"}
+
+```
+
+## strip_namespaces
+
+Nori can strip the namespaces from your XML tags. This feature is disabled by default.
 
 ``` ruby
-parser = Nori.new(:convert_tags_to => lambda { |tag| tag.snakecase.to_sym })
+Nori.new.parse('<soap:Envelope xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"></soap:Envelope>')
+# => {"soap:Envelope"=>{"@xmlns:soap"=>"http://schemas.xmlsoap.org/soap/envelope/"}}
 
-xml = '<userResponse><accountStatus>active</accountStatus></userResponse>'
-parser.parse(xml)  # => { :user_response => { :account_status => "active" }
+Nori.new(:strip_namespaces => true).parse('<soap:Envelope xmlns:soap="http://schemas.xmlsoap.org/soap/envelope/"></soap:Envelope>')
+# => {"Envelope"=>{"@xmlns:soap"=>"http://schemas.xmlsoap.org/soap/envelope/"}}
 ```
 
-Dashes and underscores
-----------------------
+## convert_tags_to
 
-Nori will automatically convert dashes in tag names to underscores.
-For example:
+Nori lets you specify a custom formula to convert XML tags to Hash keys using `convert_tags_to`.
 
-```ruby
-parser = Nori.new
-parser.parse('<any-tag>foo bar</any-tag>')  # => { "any_tag" => "foo bar" }
+``` ruby
+Nori.new.parse('<userResponse><accountStatus>active</accountStatus></userResponse>')
+# => {"userResponse"=>{"accountStatus"=>"active"}}
+
+parser = Nori.new(:convert_tags_to => lambda { |tag| tag.snakecase.to_sym })
+parser.parse('<userResponse><accountStatus>active</accountStatus></userResponse>')
+# => {:user_response=>{:account_status=>"active"}}
 ```
 
-You can control this behavior with the `:convert_dashes_to_underscores` option:
+## convert_dashes_to_underscores
+
+By default, Nori will automatically convert dashes in tag names to underscores.
 
 ```ruby
+Nori.new.parse('<any-tag>foo bar</any-tag>')
+# => {"any_tag"=>"foo bar"}
+
+# disable with convert_dashes_to_underscores
 parser = Nori.new(:convert_dashes_to_underscores => false)
-parser.parse('<any-tag>foo bar</any-tag>') # => { "any-tag" => "foo bar" }
+parser.parse('<any-tag>foo bar</any-tag>')
+# => {"any-tag"=>"foo bar"}
 ```

data/lib/nori/core_ext.rb

@@ -1,3 +1,2 @@
-require "nori/core_ext/object"
 require "nori/core_ext/string"
 require "nori/core_ext/hash"

data/lib/nori/parser/rexml.rb

@@ -15,7 +15,8 @@ class Nori
         parser = ::REXML::Parsers::BaseParser.new(xml)
 
         while true
-          event = unnormalize(parser.pull)
+          raw_data = parser.pull
+          event = unnormalize(raw_data)
           case event[0]
           when :end_document
             break
@@ -28,15 +29,17 @@ class Nori
               temp = stack.pop
               stack.last.add_node(temp)
             end
-          when :text, :cdata
+          when :text
             stack.last.add_node(event[1]) unless event[1].strip.length == 0 || stack.empty?
+          when :cdata
+            stack.last.add_node(raw_data[1]) unless raw_data[1].strip.length == 0 || stack.empty?
           end
         end
         stack.length > 0 ? stack.pop.to_hash : {}
       end
 
       def self.unnormalize(event)
-        event.map! do |el|
+        event.map do |el|
           if el.is_a?(String)
             ::REXML::Text.unnormalize(el)
           elsif el.is_a?(Hash)

data/lib/nori/version.rb

@@ -1,3 +1,3 @@
 class Nori
-  VERSION = '2.5.0'
+  VERSION = '2.7.0'
 end

data/lib/nori/xml_utility_node.rb

@@ -171,7 +171,7 @@ class Nori
             end
           end
           out.merge! prefixed_attributes unless attributes.empty?
-          out = out.empty? ? nil : out
+          out = out.empty? ? @options[:empty_tag_value] : out
         end
 
         if @type && out.nil?
@@ -247,7 +247,7 @@ class Nori
     end
     alias to_s to_html
 
-  private
+    private
     def try_to_convert(value, &block)
       block.call(value)
     rescue ArgumentError

data/lib/nori.rb

@@ -15,13 +15,15 @@ class Nori
 
   def initialize(options = {})
     defaults = {
-      :strip_namespaces             => false,
-      :delete_namespace_attributes  => false,
-      :convert_tags_to              => nil,
-      :convert_attributes_to        => nil,
-      :advanced_typecasting         => true,
+      :strip_namespaces              => false,
+      :delete_namespace_attributes   => false,
+      :convert_tags_to               => nil,
+      :convert_attributes_to         => nil,
+      :empty_tag_value               => nil,
+      :advanced_typecasting          => true,
       :convert_dashes_to_underscores => true,
-      :parser                       => :nokogiri
+      :scrub_xml                     => true,
+      :parser                        => :nokogiri
     }
 
     validate_options! defaults.keys, options.keys
@@ -39,7 +41,7 @@ class Nori
   end
 
   def parse(xml)
-    cleaned_xml = xml.strip
+    cleaned_xml = scrub_xml(xml).strip
     return {} if cleaned_xml.empty?
 
     parser = load_parser @options[:parser]
@@ -76,4 +78,22 @@ class Nori
     nil
   end
 
+  def scrub_xml(string)
+    if @options[:scrub_xml]
+      if string.respond_to? :scrub
+        string.scrub
+      else
+        if string.valid_encoding?
+          string
+        else
+          enc = string.encoding
+          mid_enc = (["UTF-8", "UTF-16BE"].map { |e| Encoding.find(e) } - [enc]).first
+          string.encode(mid_enc, undef: :replace, invalid: :replace).encode(enc)
+        end
+      end
+    else
+      string 
+    end
+  end
+
 end

data/nori.gemspec

@@ -10,14 +10,17 @@ Gem::Specification.new do |s|
   s.homepage    = "https://github.com/savonrb/nori"
   s.summary     = "XML to Hash translator"
   s.description = s.summary
-  s.required_ruby_version = '>= 1.9.2'
+  s.required_ruby_version = '>= 3.0'
 
-  s.rubyforge_project = "nori"
   s.license = "MIT"
 
-  s.add_development_dependency "rake",     "~> 10.0"
+  s.add_dependency "bigdecimal"
+
+  s.add_development_dependency "rake",     "~> 12.3.3"
   s.add_development_dependency "nokogiri", ">= 1.4.0"
-  s.add_development_dependency "rspec",    "~> 2.12"
+  s.add_development_dependency "rspec",    "~> 3.11.0"
+
+  s.metadata["rubygems_mfa_required"] = "true"
 
   s.files         = `git ls-files`.split("\n")
   s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")

data/spec/nori/api_spec.rb

@@ -108,13 +108,6 @@ describe Nori do
       expect(Nori::Parser::Nokogiri).to receive(:parse).and_return({})
       nori.parse("<any>thing</any>")
     end
-
-    it "strips the XML" do
-      xml = double("xml")
-      expect(xml).to receive(:strip).and_return("<any>thing</any>")
-
-      expect(nori.parse(xml)).to eq({ "any" => "thing" })
-    end
   end
 
   context "#parse without :advanced_typecasting" do
@@ -163,15 +156,22 @@ describe Nori do
   end
 
   context "#parse with :convert_dashes_to_underscores" do
-    it "can be configured to skip dash to underscope conversion" do
-      xml = '<any-tag>foo bar</any-tag'
+    it "can be configured to skip dash to underscore conversion" do
+      xml = '<any-tag>foo bar</any-tag>'
       hash = nori(:convert_dashes_to_underscores => false).parse(xml)
       expect(hash).to eq({'any-tag' => 'foo bar'})
     end
   end
 
+  context "#parse with :empty_tag_value set to empty string" do
+    it "can be configured to convert empty tags to given value" do
+      xml = "<parentTag><tag/></parentTag>"
+      hash = nori(:empty_tag_value => "").parse(xml)
+      expect(hash).to eq("parentTag" => { "tag" => "" })
+    end
+  end
+
   def nori(options = {})
     Nori.new(options)
   end
-
 end

data/spec/nori/nori_spec.rb

@@ -21,11 +21,16 @@ describe Nori do
         xml = <<-END
           <tag>
           <![CDATA[
-            text inside cdata
+            text inside cdata &lt; test
           ]]>
           </tag>
         END
-        expect(parse(xml)["tag"].strip).to eq("text inside cdata")
+        expect(parse(xml)["tag"].strip).to eq("text inside cdata &lt; test")
+      end
+
+      it "should scrub bad characters" do
+        xml = "<tag>a\xfbc</tag>".force_encoding('UTF-8')
+        expect(parse(xml)["tag"]).to eq("a\uFFFDc")
       end
 
       it "should transform a simple tag with attributes" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nori
 version: !ruby/object:Gem::Version
-  version: 2.5.0
+  version: 2.7.0
 platform: ruby
 authors:
 - Daniel Harrington
@@ -10,22 +10,36 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-01 00:00:00.000000000 Z
+date: 2024-02-13 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: bigdecimal
+  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: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 12.3.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 12.3.3
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
@@ -46,23 +60,25 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.12'
+        version: 3.11.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.12'
+        version: 3.11.0
 description: XML to Hash translator
 email: me@rubiii.com
 executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".devcontainer/devcontainer.json"
+- ".github/dependabot.yml"
+- ".github/workflows/test.yml"
 - ".gitignore"
 - ".rspec"
-- ".travis.yml"
 - CHANGELOG.md
 - Gemfile
 - LICENSE
@@ -73,7 +89,6 @@ files:
 - lib/nori.rb
 - lib/nori/core_ext.rb
 - lib/nori/core_ext/hash.rb
-- lib/nori/core_ext/object.rb
 - lib/nori/core_ext/string.rb
 - lib/nori/parser/nokogiri.rb
 - lib/nori/parser/rexml.rb
@@ -84,14 +99,14 @@ files:
 - nori.gemspec
 - spec/nori/api_spec.rb
 - spec/nori/core_ext/hash_spec.rb
-- spec/nori/core_ext/object_spec.rb
 - spec/nori/core_ext/string_spec.rb
 - spec/nori/nori_spec.rb
 - spec/spec_helper.rb
 homepage: https://github.com/savonrb/nori
 licenses:
 - MIT
-metadata: {}
+metadata:
+  rubygems_mfa_required: 'true'
 post_install_message: 
 rdoc_options: []
 require_paths:
@@ -100,22 +115,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.2
+      version: '3.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: nori
-rubygems_version: 2.2.2
+rubygems_version: 3.4.10
 signing_key: 
 specification_version: 4
 summary: XML to Hash translator
-test_files:
-- spec/nori/api_spec.rb
-- spec/nori/core_ext/hash_spec.rb
-- spec/nori/core_ext/object_spec.rb
-- spec/nori/core_ext/string_spec.rb
-- spec/nori/nori_spec.rb
-- spec/spec_helper.rb
+test_files: []

data/.travis.yml

@@ -1,11 +0,0 @@
-# https://github.com/travis-ci/travis-ci/wiki/.travis.yml-options
-language: "ruby"
-script: "bundle exec rake"
-rvm:
-  - 1.9.2
-  - 1.9.3
-  - 2.0
-  - 2.1
-  - 2.2
-  - jruby-19mode
-  - rbx-2

data/lib/nori/core_ext/object.rb

@@ -1,13 +0,0 @@
-class Nori
-  module CoreExt
-    module Object
-
-      def blank?
-        respond_to?(:empty?) ? empty? : !self
-      end unless method_defined?(:blank?)
-
-    end
-  end
-end
-
-Object.send :include, Nori::CoreExt::Object

data/spec/nori/core_ext/object_spec.rb

@@ -1,19 +0,0 @@
-require "spec_helper"
-
-describe Object do
-
-  describe "#blank?" do
-    [nil, false, [], {}].each do |object|
-      it "should return true for: #{object.inspect}" do
-        expect(object.blank?).to be_true
-      end
-    end
-
-    [true, [nil], 1, "string", { :key => "value" }].each do |object|
-      it "should return false for: #{object.inspect}" do
-        expect(object.blank?).to be_false
-      end
-    end
-  end
-
-end