sax-machine 1.0.2 → 1.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 735fbe7eb7f0a9239d94c61a7c3be193b69aaed0
-  data.tar.gz: 976dc0eb6189bc6ecfbbb39073ddda7d56b7c025
+  metadata.gz: 70bbbc0d3143b8a3470722b16bd6ae18c7f20823
+  data.tar.gz: 2175ebaaa36b8d325d5bd2a67296edb8ad6c5b9b
 SHA512:
-  metadata.gz: 4519f0fc17c789c689bd10f9ebabfb5633a324861c026c12154bb51c4c40dbe7b1c3259e28f365f7c2bf277e8f5e4a2b21441ffe41a489d00afc5644079b91a8
-  data.tar.gz: ec7638ca60b7ec8290c9baa08aa2b3854ac988769175d4dfa3230f7154269d6960c3185bd9aac4aadc95c9fc57bc10cd35861069f9a17b8bd89e28654fb15ec6
+  metadata.gz: de8580d61bbfc9bba11ea486c2eac3796a74b882c61d9fade5c14073b38f684b80c3d48489e6d9f520e0d77d3c8af34c0538fa5b125de33e2708c6b93a41b8de
+  data.tar.gz: 6f642b324f6f39c6662e5112fced199d8bd976d968fd228a530e497a0fd695df5232e25c64a34151a5399b00154de0f97878026c34fe8320f89db8728370d3e2

data/HISTORY.md

@@ -1,5 +1,12 @@
 # HEAD
 
+# 1.0.3
+
+* Remove missed `nokogiri` reference [[#54](https://github.com/pauldix/sax-machine/pull/54)]
+* Add support for `Symbol` data type conversion [[#57](https://github.com/pauldix/sax-machine/pull/57)]
+* Add specs for multiple elements with the same alias [[#53](https://github.com/pauldix/sax-machine/pull/53)]
+* Various code and documentation enhancements
+
 # 1.0.2
 
 * Make sure SAXConfig getters do not modify internal vars. Prevent race conditions

data/README.md

@@ -137,6 +137,26 @@ class X < ActiveRecord::Base
 end
 ```
 
+Multiple elements can be mapped to the same alias:
+
+```ruby
+class RSSEntry
+  include SAXMachine
+  # ...
+  element :pubDate, as: :published
+  element :pubdate, as: :published
+  element :"dc:date", as: :published
+  element :"dc:Date", as: :published
+  element :"dcterms:created", as: :published
+end
+```
+
+If more than one of these elements exists in the source, the value from the *last one* is used. The order of
+the `element` declarations in the code is unimportant. The order they are encountered while parsing the 
+document determines the value assigned to the alias. 
+
+If an element is defined in the source but is blank (e.g., `<pubDate></pubDate>`), it is ignored, and non-empty one is picked.
+
 ## Contributing
 
 1. Fork it

data/lib/sax-machine/config/sax_attribute.rb

@@ -1,23 +1,6 @@
 module SAXMachine
   class SAXConfig
-    class AttributeConfig
-      attr_reader :name, :setter
-
-      def initialize(name, options)
-        @name     = name.to_s
-        @as       = options[:as]
-        @setter   = "#{@as}="
-        @required = options[:required]
-      end
-
-      def column
-        @as || @name.to_sym
-      end
-
-      def required?
-        !!@required
-      end
-
+    class AttributeConfig < ElementValueConfig
       def value_from_attrs(attrs)
         attrs.fetch(@name, nil)
       end

data/lib/sax-machine/handlers/sax_abstract_handler.rb

@@ -12,6 +12,10 @@ module SAXMachine
       end
     end
 
+    def sax_parse(xml_text)
+      raise NotImplementedError
+    end
+
     def _initialize(object, on_error = nil, on_warning = nil)
       @stack = [ StackNode.new(object) ]
       @parsed_configs = {}
@@ -60,6 +64,7 @@ module SAXMachine
             case element_config.data_class.to_s
             when "Integer" then 0
             when "Float"   then 0.0
+            when "Symbol"  then nil
             when "Time"    then Time.at(0)
             when ""        then object
             else
@@ -107,6 +112,12 @@ module SAXMachine
             when "String"  then value != NO_BUFFER ? value.to_s : value
             when "Integer" then value != NO_BUFFER ? value.to_i : value
             when "Float"   then value != NO_BUFFER ? value.to_f : value
+            when "Symbol"  then
+              if value != NO_BUFFER
+                value.to_s.empty? ? nil : value.to_s.downcase.to_sym
+              else
+                value
+              end
             # Assumes that time elements will be string-based and are not
             # something else, e.g. seconds since epoch
             when "Time"    then value != NO_BUFFER ? Time.parse(value.to_s) : value

data/lib/sax-machine/handlers/sax_nokogiri_handler.rb

@@ -5,6 +5,13 @@ module SAXMachine
   class SAXNokogiriHandler < Nokogiri::XML::SAX::Document
     include SAXAbstractHandler
 
+    def sax_parse(xml_text)
+      parser = Nokogiri::XML::SAX::Parser.new(self)
+      parser.parse(xml_text) do |ctx|
+        ctx.replace_entities = true
+      end
+    end
+
     alias_method :initialize, :_initialize
     alias_method :characters, :_characters
     alias_method :cdata_block, :_characters

data/lib/sax-machine/handlers/sax_ox_handler.rb

@@ -10,6 +10,14 @@ module SAXMachine
       _reset_element
     end
 
+    def sax_parse(xml_text)
+      Ox.sax_parse(self, StringIO.new(xml_text),
+        symbolize: false,
+        convert_special: true,
+        skip: :skip_return,
+      )
+    end
+
     def attr(name, str)
       @attrs[name] = str
     end

data/lib/sax-machine/sax_config.rb

@@ -1,5 +1,5 @@
-require "sax-machine/config/sax_attribute"
 require "sax-machine/config/sax_element_value"
+require "sax-machine/config/sax_attribute"
 require "sax-machine/config/sax_element"
 require "sax-machine/config/sax_collection"
 require "sax-machine/config/sax_ancestor"

data/lib/sax-machine/sax_document.rb

@@ -1,5 +1,3 @@
-require "nokogiri"
-
 module SAXMachine
   def self.included(base)
     base.send(:include, InstanceMethods)
@@ -7,23 +5,10 @@ module SAXMachine
   end
 
   def parse(xml_text, on_error = nil, on_warning = nil)
-    if SAXMachine.handler == :ox
-      Ox.sax_parse(
-        SAXOxHandler.new(self, on_error, on_warning),
-        StringIO.new(xml_text),
-        {
-          symbolize: false,
-          convert_special: true,
-          skip: :skip_return,
-        }
-      )
-    else
-      handler = SAXNokogiriHandler.new(self, on_error, on_warning)
-      parser = Nokogiri::XML::SAX::Parser.new(handler)
-      parser.parse(xml_text) do |ctx|
-        ctx.replace_entities = true
-      end
-    end
+    handler_klass = SAXMachine.const_get("SAX#{SAXMachine.handler.capitalize}Handler")
+
+    handler = handler_klass.new(self, on_error, on_warning)
+    handler.sax_parse(xml_text)
 
     self
   end

data/lib/sax-machine/version.rb

@@ -1,3 +1,3 @@
 module SAXMachine
-  VERSION = "1.0.2"
+  VERSION = "1.0.3"
 end

data/spec/sax-machine/sax_document_spec.rb

@@ -182,6 +182,16 @@ describe "SAXMachine" do
           document = @klass.parse("<time>1994-02-04T06:20:00Z</time>")
           expect(document.time).to eq(Time.utc(1994, 2, 4, 6, 20, 0, 0))
         end
+
+        it "handles a Symbol class" do
+          @klass = Class.new do
+            include SAXMachine
+            element :symbol, class: Symbol
+          end
+
+          document = @klass.parse("<symbol>MY_SYMBOL_VALUE</symbol>")
+          expect(document.symbol).to eq(:my_symbol_value)
+        end
       end
 
       describe "the default attribute" do
@@ -914,6 +924,58 @@ describe "SAXMachine" do
     end
   end
 
+  describe "with multiple elements with the same alias" do
+    let(:item) { ItemElement5.parse(xml) }
+
+    before do
+      class ItemElement5
+        include SAXMachine
+        element :pubDate, as: :published
+        element :"dc:date", as: :published
+      end
+    end
+
+    describe "only first defined" do
+      let(:xml) { "<item xmlns:dc='http://www.example.com'><pubDate>first value</pubDate></item>" }
+
+      it "has first value" do
+        expect(item.published).to eq("first value")
+      end
+    end
+
+    describe "only last defined" do
+      let(:xml) { "<item xmlns:dc='http://www.example.com'><dc:date>last value</dc:date></item>" }
+
+      it "has last value" do
+        expect(item.published).to eq("last value")
+      end
+    end
+
+    describe "both defined" do
+      let(:xml) { "<item xmlns:dc='http://www.example.com'><pubDate>first value</pubDate><dc:date>last value</dc:date></item>" }
+
+      it "has last value" do
+        expect(item.published).to eq("last value")
+      end
+    end
+
+    describe "both defined but order is reversed" do
+      let(:xml) { "<item xmlns:dc='http://www.example.com'><dc:date>last value</dc:date><pubDate>first value</pubDate></item>" }
+
+      it "has first value" do
+        expect(item.published).to eq("first value")
+      end
+    end
+
+    describe "both defined but last is empty" do
+      let(:xml) { "<item xmlns:dc='http://www.example.com'><pubDate>first value</pubDate><dc:date></dc:date></item>" }
+
+      it "has first value" do
+        expect(item.published).to eq("first value")
+      end
+    end
+  end
+
   describe "with error handling" do
     before do
       @xml = %[

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sax-machine
 version: !ruby/object:Gem::Version
-  version: 1.0.2
+  version: 1.0.3
 platform: ruby
 authors:
 - Paul Dix
@@ -11,7 +11,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-25 00:00:00.000000000 Z
+date: 2014-11-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rspec