nokogiri 1.2.3-x86-mswin32-60 → 1.4.5-x86-mswin32-60

data/lib/nokogiri/xml/pp.rb

@@ -0,0 +1,2 @@
+require 'nokogiri/xml/pp/node'
+require 'nokogiri/xml/pp/character_data'

data/lib/nokogiri/xml/pp/character_data.rb

@@ -0,0 +1,18 @@
+module Nokogiri
+  module XML
+    module PP
+      module CharacterData
+        def pretty_print pp # :nodoc:
+          nice_name = self.class.name.split('::').last
+          pp.group(2, "#(#{nice_name} ", ')') do
+            pp.pp text
+          end
+        end
+
+        def inspect # :nodoc:
+          "#<#{self.class.name}:#{sprintf("0x%x",object_id)} #{text.inspect}>"
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/pp/node.rb

@@ -0,0 +1,56 @@
+module Nokogiri
+  module XML
+    module PP
+      module Node
+        def inspect # :nodoc:
+          attributes = inspect_attributes.reject { |x|
+            begin
+              attribute = send x
+              !attribute || (attribute.respond_to?(:empty?) && attribute.empty?)
+            rescue NoMethodError
+              true
+            end
+          }.map { |attribute|
+            "#{attribute.to_s.sub(/_\w+/, 's')}=#{send(attribute).inspect}"
+          }.join ' '
+          "#<#{self.class.name}:#{sprintf("0x%x", object_id)} #{attributes}>"
+        end
+
+        def pretty_print pp # :nodoc:
+          nice_name = self.class.name.split('::').last
+          pp.group(2, "#(#{nice_name}:#{sprintf("0x%x", object_id)} {", '})') do
+
+            pp.breakable
+            attrs = inspect_attributes.map { |t|
+              [t, send(t)] if respond_to?(t)
+            }.compact.find_all { |x|
+              if x.last
+                if [:attribute_nodes, :children].include? x.first
+                  !x.last.empty?
+                else
+                  true
+                end
+              end
+            }
+
+            pp.seplist(attrs) do |v|
+              if [:attribute_nodes, :children].include? v.first
+                pp.group(2, "#{v.first.to_s.sub(/_\w+$/, 's')} = [", "]") do
+                  pp.breakable
+                  pp.seplist(v.last) do |item|
+                    pp.pp item
+                  end
+                end
+              else
+                pp.text "#{v.first} = "
+                pp.pp v.last
+              end
+            end
+            pp.breakable
+
+          end
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/processing_instruction.rb

@@ -1,6 +1,8 @@
 module Nokogiri
   module XML
     class ProcessingInstruction < Node
+      def initialize document, name, content
+      end
     end
   end
 end

data/lib/nokogiri/xml/reader.rb

@@ -1,27 +1,112 @@
 module Nokogiri
   module XML
+    ###
+    # Nokogiri::XML::Reader parses an XML document similar to the way a cursor
+    # would move.  The Reader is given an XML document, and yields nodes
+    # to an each block.
+    #
+    # Here is an example of usage:
+    #
+    #   reader = Nokogiri::XML::Reader(<<-eoxml)
+    #     <x xmlns:tenderlove='http://tenderlovemaking.com/'>
+    #       <tenderlove:foo awesome='true'>snuggles!</tenderlove:foo>
+    #     </x>
+    #   eoxml
+    #
+    #   reader.each do |node|
+    #
+    #     # node is an instance of Nokogiri::XML::Reader
+    #     puts node.name
+    #
+    #   end
+    #
+    # Note that Nokogiri::XML::Reader#each can only be called once!!  Once
+    # the cursor moves through the entire document, you must parse the
+    # document again.  So make sure that you capture any information you
+    # need during the first iteration.
+    #
+    # The Reader parser is good for when you need the speed of a SAX parser,
+    # but do not want to write a Document handler.
     class Reader
       include Enumerable
+
+      TYPE_NONE = 0
+      # Element node type
+      TYPE_ELEMENT = 1
+      # Attribute node type
+      TYPE_ATTRIBUTE = 2
+      # Text node type
+      TYPE_TEXT = 3
+      # CDATA node type
+      TYPE_CDATA = 4
+      # Entity Reference node type
+      TYPE_ENTITY_REFERENCE = 5
+      # Entity node type
+      TYPE_ENTITY = 6
+      # PI node type
+      TYPE_PROCESSING_INSTRUCTION = 7
+      # Comment node type
+      TYPE_COMMENT = 8
+      # Document node type
+      TYPE_DOCUMENT = 9
+      # Document Type node type
+      TYPE_DOCUMENT_TYPE = 10
+      # Document Fragment node type
+      TYPE_DOCUMENT_FRAGMENT = 11
+      # Notation node type
+      TYPE_NOTATION = 12
+      # Whitespace node type
+      TYPE_WHITESPACE = 13
+      # Significant Whitespace node type
+      TYPE_SIGNIFICANT_WHITESPACE = 14
+      # Element end node type
+      TYPE_END_ELEMENT = 15
+      # Entity end node type
+      TYPE_END_ENTITY = 16
+      # XML Declaration node type
+      TYPE_XML_DECLARATION = 17
+
+      # A list of errors encountered while parsing
       attr_accessor :errors
+
+      # The encoding for the document
       attr_reader :encoding
 
-      def initialize url = nil, encoding = nil
-        @errors = []
+      # The XML source
+      attr_reader :source
+
+      alias :self_closing? :empty_element?
+
+      def initialize source, url = nil, encoding = nil # :nodoc:
+        @source   = source
+        @errors   = []
         @encoding = encoding
       end
+      private :initialize
 
+      ###
+      # Get a list of attributes for the current node.
       def attributes
-        Hash[*(attribute_nodes.map { |node|
+        Hash[attribute_nodes.map { |node|
           [node.name, node.to_s]
-        }.flatten)].merge(namespaces || {})
+        }].merge(namespaces || {})
+      end
+
+      ###
+      # Get a list of attributes for the current node
+      def attribute_nodes
+        nodes = attr_nodes
+        nodes.each { |v| v.instance_variable_set(:@_r, self) }
+        nodes
       end
 
-      def each(&block)
-        while node = self.read
-          block.call(node)
+      ###
+      # Move the cursor through the document yielding the cursor to the block
+      def each
+        while cursor = self.read
+          yield cursor
         end
       end
-      private :initialize
     end
   end
 end

data/lib/nokogiri/xml/relax_ng.rb

@@ -0,0 +1,32 @@
+module Nokogiri
+  module XML
+    class << self
+      ###
+      # Create a new Nokogiri::XML::RelaxNG document from +string_or_io+.
+      # See Nokogiri::XML::RelaxNG for an example.
+      def RelaxNG string_or_io
+        RelaxNG.new(string_or_io)
+      end
+    end
+
+    ###
+    # Nokogiri::XML::RelaxNG is used for validating XML against a
+    # RelaxNG schema.
+    #
+    # == Synopsis
+    #
+    # Validate an XML document against a RelaxNG schema.  Loop over the errors
+    # that are returned and print them out:
+    #
+    #   schema  = Nokogiri::XML::RelaxNG(File.open(ADDRESS_SCHEMA_FILE))
+    #   doc     = Nokogiri::XML(File.open(ADDRESS_XML_FILE))
+    #
+    #   schema.validate(doc).each do |error|
+    #     puts error.message
+    #   end
+    #
+    # The list of errors are Nokogiri::XML::SyntaxError objects.
+    class RelaxNG < Nokogiri::XML::Schema
+    end
+  end
+end

data/lib/nokogiri/xml/sax.rb

@@ -1,10 +1,4 @@
 require 'nokogiri/xml/sax/document'
+require 'nokogiri/xml/sax/parser_context'
 require 'nokogiri/xml/sax/parser'
 require 'nokogiri/xml/sax/push_parser'
-
-module Nokogiri
-  module XML
-    module SAX
-    end
-  end
-end

data/lib/nokogiri/xml/sax/document.rb

@@ -1,7 +1,78 @@
 module Nokogiri
   module XML
+    ###
+    # SAX Parsers are event driven parsers.  Nokogiri provides two different
+    # event based parsers when dealing with XML.  If you want to do SAX style
+    # parsing using HTML, check out Nokogiri::HTML::SAX.
+    #
+    # The basic way a SAX style parser works is by creating a parser,
+    # telling the parser about the events we're interested in, then giving
+    # the parser some XML to process.  The parser will notify you when
+    # it encounters events you said you would like to know about.
+    #
+    # To register for events, you simply subclass Nokogiri::XML::SAX::Document,
+    # and implement the methods for which you would like notification.
+    #
+    # For example, if I want to be notified when a document ends, and when an
+    # element starts, I would write a class like this:
+    #
+    #   class MyDocument < Nokogiri::XML::SAX::Document
+    #     def end_document
+    #       puts "the document has ended"
+    #     end
+    #
+    #     def start_element name, attributes = []
+    #       puts "#{name} started"
+    #     end
+    #   end
+    #
+    # Then I would instantiate a SAX parser with this document, and feed the
+    # parser some XML
+    #
+    #   # Create a new parser
+    #   parser = Nokogiri::XML::SAX::Parser.new(MyDocument.new)
+    #
+    #   # Feed the parser some XML
+    #   parser.parse(File.read(ARGV[0], 'rb'))
+    #
+    # Now my document handler will be called when each node starts, and when
+    # the document ends.  To see what kinds of events are available, take
+    # a look at Nokogiri::XML::SAX::Document.
+    #
+    # Two SAX parsers for XML are available, a parser that reads from a string
+    # or IO object as it feels necessary, and a parser that lets you spoon
+    # feed it XML.  If you want to let Nokogiri deal with reading your XML,
+    # use the Nokogiri::XML::SAX::Parser.  If you want to have fine grain
+    # control over the XML input, use the Nokogiri::XML::SAX::PushParser.
     module SAX
+      ###
+      # This class is used for registering types of events you are interested
+      # in handling.  All of the methods on this class are available as
+      # possible events while parsing an XML document.  To register for any
+      # particular event, just subclass this class and implement the methods
+      # you are interested in knowing about.
+      #
+      # To only be notified about start and end element events, write a class
+      # like this:
+      #
+      #   class MyDocument < Nokogiri::XML::SAX::Document
+      #     def start_element name, attrs = []
+      #       puts "#{name} started!"
+      #     end
+      #
+      #     def end_element name
+      #       puts "#{name} ended"
+      #     end
+      #   end
+      #
+      # You can use this event handler for any SAX style parser included with
+      # Nokogiri.  See Nokogiri::XML::SAX, and Nokogiri::HTML::SAX.
       class Document
+        ###
+        # Called when an XML declaration is parsed
+        def xmldecl version, encoding, standalone
+        end
+
         ###
         # Called when document starts parsing
         def start_document
@@ -14,7 +85,9 @@ module Nokogiri
 
         ###
         # Called at the beginning of an element
-        # +name+ is the name of the tag with +attrs+ as attributes
+        # * +name+ is the name of the tag
+        # * +attrs+ are an assoc list of namespaces and attributes, e.g.:
+        #     [ ["xmlns:foo", "http://sample.net"], ["size", "large"] ]
         def start_element name, attrs = []
         end
 
@@ -25,7 +98,39 @@ module Nokogiri
         end
 
         ###
-        # Characters read between a tag
+        # Called at the beginning of an element
+        # +name+ is the element name
+        # +attrs+ is a list of attributes
+        # +prefix+ is the namespace prefix for the element
+        # +uri+ is the associated namespace URI
+        # +ns+ is a hash of namespace prefix:urls associated with the element
+        def start_element_namespace name, attrs = [], prefix = nil, uri = nil, ns = []
+          ###
+          # Deal with SAX v1 interface
+          name = [prefix, name].compact.join(':')
+          attributes = ns.map { |ns_prefix,ns_uri|
+            [['xmlns', ns_prefix].compact.join(':'), ns_uri]
+          } + attrs.map { |attr|
+            [[attr.prefix, attr.localname].compact.join(':'), attr.value]
+          }
+          start_element name, attributes
+        end
+
+        ###
+        # Called at the end of an element
+        # +name+ is the element's name
+        # +prefix+ is the namespace prefix associated with the element
+        # +uri+ is the associated namespace URI
+        def end_element_namespace name, prefix = nil, uri = nil
+          ###
+          # Deal with SAX v1 interface
+          end_element [prefix, name].compact.join(':')
+        end
+
+        ###
+        # Characters read between a tag.  This method might be called multiple
+        # times given one contiguous string of characters.
+        #
         # +string+ contains the character data
         def characters string
         end

data/lib/nokogiri/xml/sax/parser.rb

@@ -1,7 +1,39 @@
 module Nokogiri
   module XML
     module SAX
+      ###
+      # This parser is a SAX style parser that reads it's input as it
+      # deems necessary.  The parser takes a Nokogiri::XML::SAX::Document,
+      # an optional encoding, then given an XML input, sends messages to
+      # the Nokogiri::XML::SAX::Document.
+      #
+      # Here is an example of using this parser:
+      #
+      #   # Create a subclass of Nokogiri::XML::SAX::Document and implement
+      #   # the events we care about:
+      #   class MyDoc < Nokogiri::XML::SAX::Document
+      #     def start_element name, attrs = []
+      #       puts "starting: #{name}"
+      #     end
+      #
+      #     def end_element name
+      #       puts "ending: #{name}"
+      #     end
+      #   end
+      #
+      #   # Create our parser
+      #   parser = Nokogiri::XML::SAX::Parser.new(MyDoc.new)
+      #
+      #   # Send some XML to the parser
+      #   parser.parse(File.read(ARGV[0]))
+      #
+      # For more information about SAX parsers, see Nokogiri::XML::SAX.  Also
+      # see Nokogiri::XML::SAX::Document for the available events.
       class Parser
+        class Attribute < Struct.new(:localname, :prefix, :uri, :value)
+        end
+
+        # Encodinds this parser supports
         ENCODINGS = {
           'NONE'        => 0, # No char encoding detected
           'UTF-8'       => 1, # UTF-8
@@ -28,20 +60,27 @@ module Nokogiri
           'ASCII'       => 22, # pure ASCII
         }
 
-        attr_accessor :document, :encoding
-        def initialize(doc = XML::SAX::Document.new, encoding = 'ASCII')
+        # The Nokogiri::XML::SAX::Document where events will be sent.
+        attr_accessor :document
+
+        # The encoding beings used for this document.
+        attr_accessor :encoding
+
+        # Create a new Parser with +doc+ and +encoding+
+        def initialize doc = Nokogiri::XML::SAX::Document.new, encoding = 'UTF-8'
           @encoding = encoding
           @document = doc
+          @warned   = false
         end
 
         ###
         # Parse given +thing+ which may be a string containing xml, or an
         # IO object.
-        def parse thing
+        def parse thing, &block
           if thing.respond_to?(:read) && thing.respond_to?(:close)
-            parse_io(thing)
+            parse_io(thing, &block)
           else
-            parse_memory(thing)
+            parse_memory(thing, &block)
           end
         end
 
@@ -49,15 +88,26 @@ module Nokogiri
         # Parse given +io+
         def parse_io io, encoding = 'ASCII'
           @encoding = encoding
-          native_parse_io io, ENCODINGS[@encoding] || ENCODINGS['ASCII']
+          ctx = ParserContext.io(io, ENCODINGS[encoding])
+          yield ctx if block_given?
+          ctx.parse_with self
         end
 
         ###
         # Parse a file with +filename+
         def parse_file filename
+          raise ArgumentError unless filename
           raise Errno::ENOENT unless File.exists?(filename)
           raise Errno::EISDIR if File.directory?(filename)
-          native_parse_file filename
+          ctx = ParserContext.file filename
+          yield ctx if block_given?
+          ctx.parse_with self
+        end
+
+        def parse_memory data
+          ctx = ParserContext.memory data
+          yield ctx if block_given?
+          ctx.parse_with self
         end
       end
     end