saxerator 0.7.1 → 0.9.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1f658aac7bdee282fb08e3b58640872e85736a2b
+  data.tar.gz: 59155cc7dfd7a43d3427fe2caa051a56bbf8b4d7
+SHA512:
+  metadata.gz: 78ced56c7b227e0eca9286e70653bbc4301e838ce944be43f8d6864c29139b8b02546b35108dee6bb655a284aa28c80e341efbcd56820c6c9e1577dadaa29607
+  data.tar.gz: 41987c42a7ade852213f0c63b5ede55e1a832432c30943bac211fe36bcc76fe3fadda3ff5d4b06625103075963b61c0ff96589691f869f906549589d3da92991

data/.gitignore

@@ -6,3 +6,5 @@ pkg/*
 .idea/
 coverage/
 .rvmrc
+.ruby-version
+.ruby-gemset

data/.travis.yml

@@ -2,14 +2,12 @@ script: "rspec spec"
 language: ruby
 bundler_args: --without coverage
 rvm:
-  - 1.8.7
+  - 2.0.0
   - 1.9.2
   - 1.9.3
-  - jruby-18mode
   - jruby-19mode
-  - rbx-18mode
-  - rbx-19mode
+  - rbx-2.2.1
 matrix:
   allow_failures:
-    - rvm: jruby-18mode
-    - rvm: jruby-19mode
+    - rvm: jruby-19mode
+    - rvm: rbx-2.2.1

data/README.md

@@ -1,4 +1,4 @@
-Saxerator [![Build Status](https://secure.travis-ci.org/soulcutter/saxerator.png?branch=master)](http://travis-ci.org/soulcutter/saxerator)
+Saxerator [![Build Status](https://secure.travis-ci.org/soulcutter/saxerator.png?branch=master)](http://travis-ci.org/soulcutter/saxerator) [![Code Climate](https://codeclimate.com/github/soulcutter/saxerator.png)](https://codeclimate.com/github/soulcutter/saxerator)
 =========
 
 Saxerator is a streaming xml-to-hash parser designed for working with very large xml files by
@@ -80,11 +80,11 @@ end
 Configuration
 -------------
 
-Certain options are available at parser initialization.
+Certain options are available via a configuration block at parser initialization.
 
 ```ruby
-Saxerator.parse(xml) do |config|
-  # config object has accessors for various settings
+Saxerator.parser(xml) do |config|
+  config.output_type = :xml
 end
 ```
 
@@ -92,6 +92,8 @@ end
 |:------------------|:--------|-----------------|------------
 | `output_type`     | `:hash` | `:hash`, `:xml` | The type of object generated by Saxerator's parsing. `:hash` should be self-explanatory, `:xml` generates a `Nokogiri::XML::Document`
 | `symbolize_keys!` | n/a     | n/a             | Call this method if you want the hash keys to be symbols rather than strings
+| `strip_namespaces!| n/a     | user-specified  | Called with no arguments this strips all namespaces, or you may specify an arbitrary number of namespaces to strip, i.e. `config.strip_namespaces! :rss, :soapenv`
+| `put_attributes_in_hash!` | n/a     | n/a             | Call this method if you want xml attributes included as elements of the output hash - only valid with `output_type = :hash`
 
 Known Issues
 ------------
@@ -121,4 +123,4 @@ Saxerator was inspired by - but not affiliated with - [nori](https://github.com/
 [Practicing Ruby](http://practicingruby.com/)
 
 #### Legal Stuff ####
-Copyright © Bradley Schaefer. MIT License (see LICENSE file).
+Copyright © Bradley Schaefer. MIT License (see LICENSE file).

data/lib/saxerator/builder/hash_builder.rb

@@ -5,7 +5,7 @@ module Saxerator
 
       def initialize(config, name, attributes)
         @config = config
-        @name = config.hash_key_generator.call(name)
+        @name = config.generate_key_for(name)
         @attributes = attributes
         @children = []
         @text = false
@@ -27,23 +27,37 @@ module Saxerator
           name = child.name
           element = child.block_variable
 
-          if hash[name]
-            if !hash[name].is_a?(Array)
-              hash[name] = ArrayElement[hash[name]]
-              hash[name].name = name
+          add_to_hash_element( hash, name, element)
+        end
+
+        if @config.put_attributes_in_hash?
+
+          @attributes.each do |attribute|
+            attribute.each_slice(2) do |name, element|
+              add_to_hash_element( hash, name, element)
             end
-            hash[name] << element
-          else
-            hash[name] = element
           end
         end
 
         hash
       end
 
+      def add_to_hash_element( hash, name, element)
+        name = @config.generate_key_for(name)
+        if hash[name]
+          if !hash[name].is_a?(Array)
+            hash[name] = ArrayElement[hash[name]]
+            hash[name].name = name
+          end
+          hash[name] << element
+        else
+          hash[name] = element
+        end
+      end
+
       def block_variable
         @text ? to_s : to_hash
       end
     end
   end
-end
+end

data/lib/saxerator/configuration.rb

@@ -5,19 +5,53 @@ module Saxerator
 
     def initialize
       @output_type = :hash
+      @put_attributes_in_hash = false
     end
 
     def output_type=(val)
       raise ArgumentError.new("Unknown output_type '#{val.inspect}'") unless Builder.valid?(val)
       @output_type = val
+      raise_error_if_using_put_attributes_in_hash_with_xml
+    end
+
+    def generate_key_for(val)
+      hash_key_generator.call val
+    end
+
+    def hash_key_normalizer
+      @hash_key_normalizer ||= lambda { |x| x.to_s }
     end
 
     def hash_key_generator
-      @hash_key_generator ||= lambda { |x| x.to_s }
+      @hash_key_generator || hash_key_normalizer
     end
 
     def symbolize_keys!
-      @hash_key_generator = lambda { |x| x.to_sym }
+      @hash_key_generator = lambda { |x| hash_key_normalizer.call(x).to_sym }
+    end
+
+    def strip_namespaces!(*namespaces)
+      if namespaces.any?
+        matching_group = namespaces.join('|')
+        @hash_key_normalizer = lambda { |x| x.to_s.gsub(/(#{matching_group}):/, '') }
+      else
+        @hash_key_normalizer = lambda { |x| x.to_s.gsub(/\w+:/, '') }
+      end
+    end
+
+    def put_attributes_in_hash!
+      @put_attributes_in_hash = true
+      raise_error_if_using_put_attributes_in_hash_with_xml
+    end
+
+    def put_attributes_in_hash?
+      @put_attributes_in_hash
+    end
+
+    def raise_error_if_using_put_attributes_in_hash_with_xml
+      if @output_type != :hash && @put_attributes_in_hash
+        raise ArgumentError.new("put_attributes_in_hash! is only valid when using output_type = :hash (the default)'")
+      end
     end
   end
-end
+end

data/lib/saxerator/dsl.rb

@@ -1,7 +1,7 @@
 module Saxerator
   module DSL
-    def for_tag(tag)
-      for_tags([tag])
+    def for_tag(*tags)
+      for_tags(tags)
     end
 
     def for_tags(tags)
@@ -41,4 +41,4 @@ module Saxerator
       DocumentFragment.new(@source, @config, @latches + [predicate])
     end
   end
-end
+end

data/lib/saxerator/version.rb

@@ -1,3 +1,3 @@
 module Saxerator
-  VERSION = "0.7.1"
+  VERSION = "0.9.0"
 end

data/spec/lib/dsl/all_spec.rb

@@ -17,4 +17,15 @@ describe "Saxerator::FullDocument#all" do
   it "should allow you to parse an entire document" do
     parser.all.should == {'blurb' => ['one', 'two', 'three'], 'notablurb' => 'four'}
   end
+  
+  context "with_put_attributes_in_hash" do
+    subject(:parser) do
+      Saxerator.parser(xml) { |config| config.put_attributes_in_hash! }
+    end
+        
+    it "should allow you to parse an entire document" do
+      parser.all.should == {'blurb' => ['one', 'two', 'three'], 'notablurb' => 'four'}
+    end
+  end
+  
 end

data/spec/lib/saxerator_spec.rb

@@ -62,7 +62,77 @@ describe Saxerator do
       end
 
       specify { parser.all.should == { :bar => 'baz' } }
+      specify { parser.all.name.should == :foo }
+    end
+
+    context "with strip namespaces" do
+      let(:xml) { "<ns1:foo><ns3:bar>baz</ns3:bar></ns1:foo>" }
+      subject(:parser) do
+        Saxerator.parser(xml) { |config| config.strip_namespaces! }
+      end
+
+      specify { parser.all.should == {'bar' => 'baz'} }
+      specify { parser.all.name.should == 'foo' }
+
+      context "combined with symbolize keys" do
+        subject(:parser) do
+          Saxerator.parser(xml) do |config|
+            config.strip_namespaces!
+            config.symbolize_keys!
+          end
+        end
+
+        specify { parser.all.should == {:bar => 'baz'} }
+      end
+
+      context "for specific namespaces" do
+        let(:xml) do
+          <<-XML.gsub /^ {10}/, ''
+          <ns1:foo>
+            <ns2:bar>baz</ns2:bar>
+            <ns3:bar>biz</ns3:bar>
+          </ns1:foo>
+          XML
+        end
+        subject(:parser) do
+          Saxerator.parser(xml) { |config| config.strip_namespaces! :ns1, :ns3 }
+        end
+
+        specify { parser.all.should == {'ns2:bar' => 'baz', 'bar' => 'biz'} }
+        specify { parser.all.name.should == 'foo' }
+      end
+    end
+
+  end
+
+  context "configuration with put_attributes_in_hash!" do
+    let(:xml) { '<foo foo="bar"><bar>baz</bar></foo>' }
+
+    subject(:parser) do
+      Saxerator.parser(xml) do |config|
+        config.put_attributes_in_hash!
+      end
+    end
+
+    it "should be able to parse it" do
+      parser.all.should == { 'bar' => 'baz', 'foo' => 'bar' }
+    end
+
+  end
+
+  context "configuration with put_attributes_in_hash! and config.output_type = :xml" do
+    let(:xml) { '<foo foo="bar"><bar>baz</bar></foo>' }
+
+    subject(:parser) do
+      Saxerator.parser(xml) do |config|
+        config.put_attributes_in_hash!
+        config.output_type = :xml
+      end
+    end
+
+    context "should raise error with " do
+      specify { expect { parser }.to raise_error(ArgumentError) }
     end
-    
   end
-end
+
+end

metadata

@@ -1,51 +1,46 @@
 --- !ruby/object:Gem::Specification
 name: saxerator
 version: !ruby/object:Gem::Version
-  version: 0.7.1
-  prerelease: 
+  version: 0.9.0
 platform: ruby
 authors:
 - Bradley Schaefer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-11-29 00:00:00.000000000 Z
+date: 2013-11-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.4.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 1.4.0
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 2.11.0
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: 2.11.0
-description: ! "    Saxerator is a streaming xml-to-hash parser designed for working
-  with very large xml files by\n    giving you Enumerable access to manageable chunks
-  of the document.\n"
+description: |2
+      Saxerator is a streaming xml-to-hash parser designed for working with very large xml files by
+      giving you Enumerable access to manageable chunks of the document.
 email:
 - bradley.schaefer@gmail.com
 executables: []
@@ -99,27 +94,26 @@ files:
 homepage: https://github.com/soulcutter/saxerator
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: saxerator
-rubygems_version: 1.8.24
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: A SAX-based XML-to-hash parser for parsing large files into manageable chunks
 test_files:
 - spec/fixtures/flat_blurbs.xml