sax_stream 0.2.0 → 0.2.1

data/README.markdown

@@ -74,8 +74,9 @@ The parser object must be supplied with a collector and an array of mapping clas
 
 ```ruby
 require 'sax_stream/parser'
+require 'sax_stream/collectors/naive_collector'
 
-collector = SaxStream::NaiveCollector.new
+collector = SaxStream::Collectors::NaiveCollector.new
 parser = SaxStream::Parser.new(collector, [Product])
 
 parser.parse_stream(File.open('products.xml'))
@@ -89,8 +90,10 @@ To get the full benefits of this library, supply a collector which does somethin
 
 I plan to supply a batching collector which will collect a certain number of objects before passing them off to another collector you supply, so you can save objects in batches of 100 or whatever is optimal for your application.
 
-## Author
+## Credits
 
-Craig Ambrose
+Author: [Craig Ambrose](http://www.craigambrose.com)
 
-http://www.craigambrose.com
+Initial development sponsored by: [List Globally](http://www.listglobally.com)
+
+Ideas taken from lots of other great libraries, including ROXML, Happymapper, Sax Machine, and of course very reliant on Nokogiri.

data/lib/sax_stream/collectors/block_collector.rb

@@ -0,0 +1,15 @@
+module SaxStream
+  module Collectors
+    # Initialise this collector with a block that handles one argument. This collector will yield each
+    # mapped object it collects immediately to the block. It will not keep a record of the objects.
+    class BlockCollector
+      def initialize(&block)
+        @block = block
+      end
+
+      def <<(value)
+        @block.call(value)
+      end
+    end
+  end
+end

data/lib/sax_stream/collectors/naive_collector.rb

@@ -0,0 +1,21 @@
+module SaxStream
+  module Collectors
+    class NaiveCollector
+      def initialize
+        @objects = []
+      end
+
+      def mapped_objects
+        @objects
+      end
+
+      def <<(value)
+        @objects << value
+      end
+
+      def for_type(klass)
+        mapped_objects.select { |object| object.class == klass }
+      end
+    end
+  end
+end

data/lib/sax_stream/internal/element_stack.rb

@@ -29,12 +29,14 @@ module SaxStream
         end
       end
 
-      def initialize
-        @elements = []
+      class RootElement < Element
+        def initialize
+          super(nil, [])
+        end
       end
 
-      def top_name
-        @elements.last.name if @elements.last
+      def initialize
+        @elements = []
       end
 
       def push(name, attrs)
@@ -42,18 +44,26 @@ module SaxStream
         # indented_puts "push element #{name}"
       end
 
-      def pop
+      def push_root
+        @elements.push(RootElement.new)
+      end
+
+      def pop(name = nil)
         raise ProgramError, "attempting to pop an empty ElementStack" if @elements.empty?
+        if name && @element_stack.top_name != name
+          raise ProgramError "received popping element for #{name.inspect} but currently processing #{path.inspect}"
+        end
         # indented_puts "pop element"
         @elements.pop
       end
 
       def empty?
-        @elements.empty?
+        @elements.length <= 1
       end
 
       def path
-        @elements.map(&:name).join('/')
+        return nil if @elements.empty?
+        @elements.map(&:name).compact.join('/')
       end
 
       def content
@@ -66,11 +76,17 @@ module SaxStream
 
       def record_characters(string)
         # indented_puts "  record: #{string.inspect}"
-        @elements.last.record_characters(string)
+        if @elements.last
+          @elements.last.record_characters(string)
+        end
       end
 
       private
 
+        def top_name
+          @elements.last.name if @elements.last
+        end
+
         def indented_puts(string)
           indent = ''
           @elements.length.times { indent << '  ' }

data/lib/sax_stream/internal/mapper_handler.rb

@@ -54,9 +54,7 @@ module SaxStream
       end
 
       def characters(string)
-        unless @element_stack.empty?
-          @element_stack.record_characters(string)
-        end
+        @element_stack.record_characters(string)
       end
 
       def current_object
@@ -71,6 +69,7 @@ module SaxStream
             attrs.each do |key, value|
               @mapper_class.map_attribute_onto_object(@current_object, key, value)
             end
+            @element_stack.push_root
             @current_object
           end
         end
@@ -91,7 +90,6 @@ module SaxStream
 
         def pop_element_stack(name)
           unless @element_stack.empty?
-            raise ProgramError "received end element event for #{name.inspect} but currently processing #{@element_stack.top_name.inspect}" unless @element_stack.top_name == name
             @mapper_class.map_element_stack_top_onto_object(@current_object, @element_stack)
             @element_stack.pop
           end
@@ -99,10 +97,12 @@ module SaxStream
 
         def end_current_object(name)
           raise ProgramError unless @current_object
-          raise ArgumentError, "received end element event for #{name.inspect} but currently processing #{@current_object.class.node_name.inspect}" unless @current_object.class.node_name == name
-          if @current_object.class.should_collect?
+          raise ArgumentError, "received end element event for #{name.inspect} but currently processing #{@current_object.node_name.inspect}" unless @current_object.node_name == name
+          @mapper_class.map_key_onto_object(@current_object, @element_stack.path, @element_stack.content)
+          if @current_object.should_collect?
             @collector << @current_object
           end
+          @element_stack.pop
           @stack.pop(self)
           @current_object = nil
         end

data/lib/sax_stream/mapper.rb

@@ -72,9 +72,11 @@ module SaxStream
       end
 
       def map_key_onto_object(object, key, value)
-        mapping = field_mapping(key)
-        if mapping
-          mapping.map_value_onto_object(object, value)
+        if value
+          mapping = field_mapping(key)
+          if mapping
+            mapping.map_value_onto_object(object, value)
+          end
         end
       end
 
@@ -148,6 +150,14 @@ module SaxStream
       @relations ||= build_empty_relations
     end
 
+    def node_name
+      self.class.node_name
+    end
+
+    def should_collect?
+      self.class.should_collect?
+    end
+
     private
 
       def build_empty_relations

data/lib/sax_stream/types/boolean.rb

@@ -0,0 +1,13 @@
+module SaxStream
+  module Types
+    class Boolean
+      def self.parse(value)
+        if value
+          value = value.strip
+          return nil if value == ''
+          !!(value =~ /^(yes|true|1)$/i)
+        end
+      end
+    end
+  end
+end

data/lib/sax_stream/types/decimal.rb

@@ -0,0 +1,13 @@
+module SaxStream
+  module Types
+    class Decimal
+      def self.parse(value)
+        if value
+          value = value.gsub(/[^\.0-9]/, '')
+          return nil if value == ''
+          Float(value)
+        end
+      end
+    end
+  end
+end

data/lib/sax_stream/types/integer.rb

@@ -0,0 +1,13 @@
+module SaxStream
+  module Types
+    class Integer
+      def self.parse(value)
+        if value
+          value = value.gsub(/[^\.0-9]/, '')
+          return nil if value == ''
+          Float(value).to_i
+        end
+      end
+    end
+  end
+end

data/lib/sax_stream/types.rb

@@ -0,0 +1,3 @@
+require 'sax_stream/types/integer'
+require 'sax_stream/types/decimal'
+require 'sax_stream/types/boolean'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: sax_stream
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,19 +9,19 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-04-09 00:00:00.000000000 Z
+date: 2012-04-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  requirement: &70267973114600 !ruby/object:Gem::Requirement
+  requirement: &70239061335640 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.4.0
+        version: 1.5.2
   type: :runtime
   prerelease: false
-  version_requirements: *70267973114600
+  version_requirements: *70239061335640
 description: A streaming XML parser which builds objects and passes them to a collecter
   as they are ready. Based upon Nokogiri SAX parsing functionality.
 email:
@@ -30,6 +30,8 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- lib/sax_stream/collectors/block_collector.rb
+- lib/sax_stream/collectors/naive_collector.rb
 - lib/sax_stream/errors.rb
 - lib/sax_stream/internal/child_mapping.rb
 - lib/sax_stream/internal/combined_handler.rb
@@ -40,8 +42,11 @@ files:
 - lib/sax_stream/internal/sax_handler.rb
 - lib/sax_stream/internal/singular_relationship_collector.rb
 - lib/sax_stream/mapper.rb
-- lib/sax_stream/naive_collector.rb
 - lib/sax_stream/parser.rb
+- lib/sax_stream/types/boolean.rb
+- lib/sax_stream/types/decimal.rb
+- lib/sax_stream/types/integer.rb
+- lib/sax_stream/types.rb
 - LICENSE
 - README.markdown
 homepage: http://github.com/craigambrose/sax_stream

data/lib/sax_stream/naive_collector.rb

@@ -1,19 +0,0 @@
-module SaxStream
-  class NaiveCollector
-    def initialize
-      @objects = []
-    end
-
-    def mapped_objects
-      @objects
-    end
-
-    def <<(value)
-      @objects << value
-    end
-
-    def for_type(klass)
-      mapped_objects.select { |object| object.class == klass }
-    end
-  end
-end