nokogiri 1.2.1 → 1.2.2

data/lib/nokogiri/css/generated_tokenizer.rb

@@ -1,8 +1,8 @@
-#
+#--
 # DO NOT MODIFY!!!!
 # This file is automatically generated by rex 1.0.1
 # from lexical definition file "lib/nokogiri/css/tokenizer.rex".
-#
+#++
 
 module Nokogiri
 module CSS

data/lib/nokogiri/css/node.rb

@@ -11,6 +11,8 @@ module Nokogiri
         visitor.send(:"visit_#{type.to_s.downcase}", self)
       end
 
+      ###
+      # Convert this CSS node to xpath with +prefix+ using +visitor+
       def to_xpath prefix = '//', visitor = XPathVisitor.new
         self.preprocess!
         prefix + visitor.accept(self)

data/lib/nokogiri/css/parser.rb

@@ -52,14 +52,15 @@ module Nokogiri
       alias :parse :scan_str
 
       def xpath_for string, options={}
-        v = self.class[string]
+        key = string + options[:ns].to_s
+        v = self.class[key]
         return v if v
 
         args = [
           options[:prefix] || '//',
           options[:visitor] || XPathVisitor.new
         ]
-        self.class[string] = parse(string).map { |ast|
+        self.class[key] = parse(string).map { |ast|
           ast.to_xpath(*args)
         }
       end

data/lib/nokogiri/html.rb

@@ -1,3 +1,4 @@
+require 'nokogiri/html/entity_lookup'
 require 'nokogiri/html/document'
 require 'nokogiri/html/sax/parser'
 
@@ -28,6 +29,10 @@ module Nokogiri
       ###
       # Parse HTML.  See Nokogiri.HTML.
       def parse string_or_io, url = nil, encoding = nil, options = 2145
+        if string_or_io.respond_to?(:encoding)
+          encoding ||= string_or_io.encoding.name
+        end
+
         if string_or_io.respond_to?(:read)
           url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
           return Document.read_io(string_or_io, url, encoding, options)
@@ -43,6 +48,9 @@ module Nokogiri
         fragment = XML::DocumentFragment.new(doc)
         finder = lambda { |c, f|
           c.each do |child|
+            if string == child.content && child.name == 'text'
+              fragment.add_child(child)
+            end
             fragment.add_child(child) if string =~ /<#{child.name}/
           end
           return fragment if fragment.children.length > 0
@@ -55,57 +63,6 @@ module Nokogiri
         fragment
       end
     end
-
-  NamedCharacters =
-{"AElig"=>198, "Aacute"=>193, "Acirc"=>194, "Agrave"=>192, "Alpha"=>913,
- "Aring"=>197, "Atilde"=>195, "Auml"=>196, "Beta"=>914, "Ccedil"=>199,
- "Chi"=>935, "Dagger"=>8225, "Delta"=>916, "ETH"=>208, "Eacute"=>201,
- "Ecirc"=>202, "Egrave"=>200, "Epsilon"=>917, "Eta"=>919, "Euml"=>203,
- "Gamma"=>915, "Iacute"=>205, "Icirc"=>206, "Igrave"=>204, "Iota"=>921,
- "Iuml"=>207, "Kappa"=>922, "Lambda"=>923, "Mu"=>924, "Ntilde"=>209, "Nu"=>925,
- "OElig"=>338, "Oacute"=>211, "Ocirc"=>212, "Ograve"=>210, "Omega"=>937,
- "Omicron"=>927, "Oslash"=>216, "Otilde"=>213, "Ouml"=>214, "Phi"=>934,
- "Pi"=>928, "Prime"=>8243, "Psi"=>936, "Rho"=>929, "Scaron"=>352, "Sigma"=>931,
- "THORN"=>222, "Tau"=>932, "Theta"=>920, "Uacute"=>218, "Ucirc"=>219,
- "Ugrave"=>217, "Upsilon"=>933, "Uuml"=>220, "Xi"=>926, "Yacute"=>221,
- "Yuml"=>376, "Zeta"=>918, "aacute"=>225, "acirc"=>226, "acute"=>180,
- "aelig"=>230, "agrave"=>224, "alefsym"=>8501, "alpha"=>945, "amp"=>38,
- "and"=>8743, "ang"=>8736, "apos"=>39, "aring"=>229, "asymp"=>8776,
- "atilde"=>227, "auml"=>228, "bdquo"=>8222, "beta"=>946, "brvbar"=>166,
- "bull"=>8226, "cap"=>8745, "ccedil"=>231, "cedil"=>184, "cent"=>162,
- "chi"=>967, "circ"=>710, "clubs"=>9827, "cong"=>8773, "copy"=>169,
- "crarr"=>8629, "cup"=>8746, "curren"=>164, "dArr"=>8659, "dagger"=>8224,
- "darr"=>8595, "deg"=>176, "delta"=>948, "diams"=>9830, "divide"=>247,
- "eacute"=>233, "ecirc"=>234, "egrave"=>232, "empty"=>8709, "emsp"=>8195,
- "ensp"=>8194, "epsilon"=>949, "equiv"=>8801, "eta"=>951, "eth"=>240,
- "euml"=>235, "euro"=>8364, "exist"=>8707, "fnof"=>402, "forall"=>8704,
- "frac12"=>189, "frac14"=>188, "frac34"=>190, "frasl"=>8260, "gamma"=>947,
- "ge"=>8805, "gt"=>62, "hArr"=>8660, "harr"=>8596, "hearts"=>9829,
- "hellip"=>8230, "iacute"=>237, "icirc"=>238, "iexcl"=>161, "igrave"=>236,
- "image"=>8465, "infin"=>8734, "int"=>8747, "iota"=>953, "iquest"=>191,
- "isin"=>8712, "iuml"=>239, "kappa"=>954, "lArr"=>8656, "lambda"=>955,
- "lang"=>9001, "laquo"=>171, "larr"=>8592, "lceil"=>8968, "ldquo"=>8220,
- "le"=>8804, "lfloor"=>8970, "lowast"=>8727, "loz"=>9674, "lrm"=>8206,
- "lsaquo"=>8249, "lsquo"=>8216, "lt"=>60, "macr"=>175, "mdash"=>8212,
- "micro"=>181, "middot"=>183, "minus"=>8722, "mu"=>956, "nabla"=>8711,
- "nbsp"=>160, "ndash"=>8211, "ne"=>8800, "ni"=>8715, "not"=>172, "notin"=>8713,
- "nsub"=>8836, "ntilde"=>241, "nu"=>957, "oacute"=>243, "ocirc"=>244,
- "oelig"=>339, "ograve"=>242, "oline"=>8254, "omega"=>969, "omicron"=>959,
- "oplus"=>8853, "or"=>8744, "ordf"=>170, "ordm"=>186, "oslash"=>248,
- "otilde"=>245, "otimes"=>8855, "ouml"=>246, "para"=>182, "part"=>8706,
- "permil"=>8240, "perp"=>8869, "phi"=>966, "pi"=>960, "piv"=>982,
- "plusmn"=>177, "pound"=>163, "prime"=>8242, "prod"=>8719, "prop"=>8733,
- "psi"=>968, "quot"=>34, "rArr"=>8658, "radic"=>8730, "rang"=>9002,
- "raquo"=>187, "rarr"=>8594, "rceil"=>8969, "rdquo"=>8221, "real"=>8476,
- "reg"=>174, "rfloor"=>8971, "rho"=>961, "rlm"=>8207, "rsaquo"=>8250,
- "rsquo"=>8217, "sbquo"=>8218, "scaron"=>353, "sdot"=>8901, "sect"=>167,
- "shy"=>173, "sigma"=>963, "sigmaf"=>962, "sim"=>8764, "spades"=>9824,
- "sub"=>8834, "sube"=>8838, "sum"=>8721, "sup"=>8835, "sup1"=>185, "sup2"=>178,
- "sup3"=>179, "supe"=>8839, "szlig"=>223, "tau"=>964, "there4"=>8756,
- "theta"=>952, "thetasym"=>977, "thinsp"=>8201, "thorn"=>254, "tilde"=>732,
- "times"=>215, "trade"=>8482, "uArr"=>8657, "uacute"=>250, "uarr"=>8593,
- "ucirc"=>251, "ugrave"=>249, "uml"=>168, "upsih"=>978, "upsilon"=>965,
- "uuml"=>252, "weierp"=>8472, "xi"=>958, "yacute"=>253, "yen"=>165,
- "yuml"=>255, "zeta"=>950, "zwj"=>8205, "zwnj"=>8204}
+    NamedCharacters = EntityLookup.new
   end
 end

data/lib/nokogiri/html/document.rb

@@ -1,6 +1,8 @@
 module Nokogiri
   module HTML
     class Document < XML::Document
+      ####
+      # Serialize this Document with +encoding+ using +options+
       def serialize encoding = nil, options = XML::Node::SaveOptions::FORMAT |
         XML::Node::SaveOptions::AS_HTML |
         XML::Node::SaveOptions::NO_DECLARATION |

data/lib/nokogiri/html/entity_lookup.rb

@@ -0,0 +1,11 @@
+module Nokogiri
+  module HTML
+    class EntityDescription < Struct.new(:value, :name, :description); end
+
+    class EntityLookup
+      def [] name
+        (val = get(name)) && val.value
+      end
+    end
+  end
+end

data/lib/nokogiri/version.rb

@@ -1,4 +1,4 @@
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = '1.2.1'
+  VERSION = '1.2.2'
 end

data/lib/nokogiri/xml.rb

@@ -1,6 +1,5 @@
 require 'nokogiri/xml/sax'
-require 'nokogiri/xml/before_handler'
-require 'nokogiri/xml/after_handler'
+require 'nokogiri/xml/fragment_handler'
 require 'nokogiri/xml/node'
 require 'nokogiri/xml/attr'
 require 'nokogiri/xml/dtd'

data/lib/nokogiri/xml/builder.rb

@@ -1,14 +1,17 @@
 module Nokogiri
   module XML
     class Builder
-      attr_accessor :doc, :parent
+      attr_accessor :doc, :parent, :context
       def initialize(&block)
         namespace = self.class.name.split('::')
         namespace[-1] = 'Document'
         @doc = eval(namespace.join('::')).new
         @parent = @doc
-        @context = eval('self', block.binding)
-        instance_eval(&block)
+        @context = nil
+        if block_given?
+          @context = eval('self', block.binding)
+        end
+        instance_eval(&block) if block_given?
         @parent = @doc
       end
 
@@ -27,7 +30,7 @@ module Nokogiri
       end
 
       def method_missing(method, *args, &block)
-        if @context.respond_to?(method)
+        if @context && @context.respond_to?(method)
           @context.send(method, *args, &block)
         else
           node = Nokogiri::XML::Node.new(method.to_s, @doc) { |n|
@@ -61,6 +64,7 @@ module Nokogiri
         end
 
         def method_missing(method, *args, &block)
+          opts = args.last.is_a?(Hash) ? args.pop : {}
           case method.to_s
           when /^(.*)!$/
             @node['id'] = $1
@@ -72,9 +76,18 @@ module Nokogiri
               ((@node['class'] || '').split(/\s/) + [method.to_s]).join(' ')
             @node.content = args.first if args.first
           end
+
+          # Assign any extra options
+          opts.each do |k,v|
+            @node[k.to_s] = ((@node[k.to_s] || '').split(/\s/) + [v]).join(' ')
+          end
+
           if block_given?
+            old_parent = @doc_builder.parent
             @doc_builder.parent = @node
-            return @doc_builder.instance_eval(&block)
+            value = @doc_builder.instance_eval(&block)
+            @doc_builder.parent = old_parent
+            return value
           end
           self
         end

data/lib/nokogiri/xml/document.rb

@@ -1,16 +1,27 @@
 module Nokogiri
   module XML
+    ####
+    # Nokogiri::XML::Document is the main entry point for dealing with
+    # XML documents.  The Document is created by parsing an XML document.
+    # See Nokogiri.XML()
+    #
+    # For searching a Document, see Nokogiri::XML::Node#css and
+    # Nokogiri::XML::Node#xpath
     class Document < Node
+      # A list of Nokogiri::XML::SyntaxError found when parsing a document
       attr_accessor :errors
 
+      # The name of this document.  Always returns "document"
       def name
         'document'
       end
 
+      # A reference to +self+
       def document
         self
       end
 
+      # Get the list of decorators given +key+
       def decorators(key)
         @decorators ||= Hash.new
         @decorators[key] ||= []
@@ -37,16 +48,19 @@ module Nokogiri
         }
       end
 
-      def node_cache
+      def node_cache # :nodoc:
         @node_cache ||= {}
       end
 
       alias :to_xml :serialize
       alias :inner_html :serialize
 
+      # Get the hash of namespaces on the root Nokogiri::XML::Node
       def namespaces
         root ? root.collect_namespaces : {}
       end
+
+      undef_method :swap, :parent, :namespace
     end
   end
 end

data/lib/nokogiri/xml/fragment_handler.rb

@@ -0,0 +1,34 @@
+module Nokogiri
+  module XML
+    class FragmentHandler < Nokogiri::XML::SAX::Document # :nodoc:
+      def initialize node, original_html
+        @doc_started    = false
+        @original_html  = original_html
+        @document       = node.document
+        @stack          = [node]
+      end
+
+      def start_element name, attrs = []
+        @doc_started = true if @original_html =~ /^<#{name}/
+        return unless @doc_started
+
+        node = Node.new(name, @document)
+        Hash[*attrs].each do |k,v|
+          node[k] = v
+        end
+        @stack.last << node
+        @stack << node
+      end
+
+      def characters string
+        @doc_started = true if @original_html =~ /^\s*#{string}/
+        @stack.last << Nokogiri::XML::Text.new(string, @document)
+      end
+
+      def end_element name
+        return unless @stack.last.name == name
+        @stack.pop
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/node.rb

@@ -3,6 +3,36 @@ require 'nokogiri/xml/node/save_options'
 
 module Nokogiri
   module XML
+    ####
+    # Nokogiri::XML::Node is your window to the fun filled world of dealing
+    # with XML and HTML tags.  A Nokogiri::XML::Node may be treated similarly
+    # to a hash with regard to attributes.  For example (from irb):
+    #
+    #   irb(main):004:0> node
+    #   => <a href="#foo" id="link">link</a>
+    #   irb(main):005:0> node['href']
+    #   => "#foo"
+    #   irb(main):006:0> node.keys
+    #   => ["href", "id"]
+    #   irb(main):007:0> node.values
+    #   => ["#foo", "link"]
+    #   irb(main):008:0> node['class'] = 'green'
+    #   => "green"
+    #   irb(main):009:0> node
+    #   => <a href="#foo" id="link" class="green">link</a>
+    #   irb(main):010:0>
+    #
+    # See Nokogiri::XML::Node#[] and Nokogiri::XML#[]= for more information.
+    #
+    # Nokogiri::XML::Node also has methods that let you move around your
+    # tree.  For navigating your tree, see:
+    #
+    # * Nokogiri::XML::Node#parent
+    # * Nokogiri::XML::Node#children
+    # * Nokogiri::XML::Node#next
+    # * Nokogiri::XML::Node#previous
+    #
+    # You may search this node's subtree using Node#xpath and Node#css
     class Node
       ELEMENT_NODE =       1
       ATTRIBUTE_NODE =     2
@@ -56,10 +86,15 @@ module Nokogiri
       # optional hash of namespaces may be appended.
       # See Node#xpath and Node#css.
       def search *paths
-        ns = paths.last.is_a?(Hash) ? paths.pop : {}
+        ns = paths.last.is_a?(Hash) ? paths.pop :
+          (document.root ? document.root.namespaces : {})
         xpath(*(paths.map { |path|
           path = path.to_s
-          path =~ /^(\.\/|\/)/ ? path : CSS.xpath_for(path, :prefix => ".//")
+          path =~ /^(\.\/|\/)/ ? path : CSS.xpath_for(
+            path,
+            :prefix => ".//",
+            :ns     => ns
+          )
         }.flatten.uniq) + [ns])
       end
       alias :/ :search
@@ -88,9 +123,10 @@ module Nokogiri
           Hash, String, Symbol
         ].include?(paths.last.class) ? paths.pop : nil
 
-        ns = paths.last.is_a?(Hash) ? paths.pop : document.root.namespaces
+        ns = paths.last.is_a?(Hash) ? paths.pop :
+          (document.root ? document.root.namespaces : {})
 
-        return NodeSet.new(document) unless document.root
+        return NodeSet.new(document) unless document
 
         sets = paths.map { |path|
           ctx = XPathContext.new(self)
@@ -138,7 +174,8 @@ module Nokogiri
           Hash, String, Symbol
         ].include?(rules.last.class) ? rules.pop : nil
 
-        ns = rules.last.is_a?(Hash) ? rules.pop : document.root.namespaces
+        ns = rules.last.is_a?(Hash) ? rules.pop :
+          (document.root ? document.root.namespaces : {})
 
         rules = rules.map { |rule|
           CSS.xpath_for(rule, :prefix => ".//", :ns => ns)
@@ -150,15 +187,15 @@ module Nokogiri
       ###
       # Search for the first occurrence of +path+.
       # Returns nil if nothing is found, otherwise a Node.
-      def at path, ns = document.root.namespaces
+      def at path, ns = document.root ? document.root.namespaces : {}
         search(path, ns).first
       end
 
       ###
       # Get the attribute value for the attribute +name+
-      def [](name)
-        return nil unless key?(name)
-        get(name)
+      def [] name
+        return nil unless key?(name.to_s)
+        get(name.to_s)
       end
 
       alias :next           :next_sibling
@@ -215,32 +252,59 @@ module Nokogiri
       # Create nodes from +data+ and insert them before this node
       # (as a sibling).
       def before data
-        classes = document.class.name.split('::')
-        classes[-1] = 'SAX::Parser'
-
-        parser = eval(classes.join('::')).new(BeforeHandler.new(self, data))
-        parser.parse(data)
+        fragment(data).children.each do |node|
+          add_previous_sibling node
+        end
+        self
       end
 
       ####
       # Create nodes from +data+ and insert them after this node
       # (as a sibling).
       def after data
+        fragment(data).children.to_a.reverse.each do |node|
+          add_next_sibling node
+        end
+        self
+      end
+
+      ####
+      # Swap this Node for new nodes made from +data+
+      def swap data
+        before(data)
+        remove
+        self
+      end
+
+      ####
+      # Set the inner_html for this Node to +tags+
+      def inner_html= tags
+        children.each { |x| x.remove}
+
+        fragment(tags).children.to_a.reverse.each do |node|
+          add_child node
+        end
+        self
+      end
+
+      ####
+      # Create a Nokogiri::XML::DocumentFragment from +tags+
+      def fragment tags
         classes = document.class.name.split('::')
         classes[-1] = 'SAX::Parser'
 
-        handler = AfterHandler.new(self, data)
-        parser = eval(classes.join('::')).new(handler)
-        parser.parse(data)
-        handler.after_nodes.reverse.each do |sibling|
-          self.add_next_sibling sibling
-        end
+
+        fragment = DocumentFragment.new(self.document)
+        parser = eval(classes.join('::')).new(
+          FragmentHandler.new(fragment, tags)
+        )
+        parser.parse(tags)
+        fragment
       end
 
       ####
       # Set the content to +string+.
-      # If +encode+, encode any special characters first.
-      def content= string, encode = true
+      def content= string
         self.native_content = encode_special_chars(string)
       end
 
@@ -251,22 +315,27 @@ module Nokogiri
         parent_node
       end
 
+      # Returns true if this is a Comment
       def comment?
         type == COMMENT_NODE
       end
 
+      # Returns true if this is a CDATA
       def cdata?
         type == CDATA_SECTION_NODE
       end
 
+      # Returns true if this is an XML::Document node
       def xml?
         type == DOCUMENT_NODE
       end
 
+      # Returns true if this is an HTML::Document node
       def html?
         type == HTML_DOCUMENT_NODE
       end
 
+      # Returns true if this is a Text node
       def text?
         type == TEXT_NODE
       end
@@ -276,6 +345,7 @@ module Nokogiri
         [NOTATION_NODE, ENTITY_NODE, ENTITY_DECL].include?(type)
       end
 
+      # Returns true if this is an Element node
       def element?
         type == ELEMENT_NODE
       end
@@ -289,6 +359,7 @@ module Nokogiri
         children.map { |x| x.to_html }.join
       end
 
+      # Get the path to this node as a CSS expression
       def css_path
         path.split(/\//).map { |part|
           part.length == 0 ? nil : part.gsub(/\[(\d+)\]/, ':nth-of-type(\1)')
@@ -306,13 +377,12 @@ module Nokogiri
       ###
       # Get a list of ancestor Node for this Node
       def ancestors
-        parents = []
+        return [] unless respond_to?(:parent)
 
-        this_parent = self.parent
+        parents = [parent]
 
-        while this_parent != nil
-          parents << this_parent
-          this_parent = this_parent.parent
+        while parents.last.respond_to?(:parent)
+          parents << parents.last.parent
         end
         parents
       end
@@ -327,7 +397,7 @@ module Nokogiri
       ####
       #  replace node with the new node in the document.
       def replace(new_node)
-        if new_node.is_a?(Document)
+        if new_node.is_a?(Document) || !new_node.is_a?(XML::Node)
           raise ArgumentError, <<-EOERR
 Node.replace requires a Node argument, and cannot accept a Document.
 (You probably want to select a node from the Document with at() or search(), or create a new Node via Node.new().)
@@ -428,8 +498,13 @@ Node.replace requires a Node argument, and cannot accept a Document.
         write_to io, encoding, SaveOptions::FORMAT | SaveOptions::AS_XML
       end
 
+      # Create a new node from +string+
+      #
+      # THIS METHOD IS DEPRECATED
+      # This method is deprecated and will be removed in 1.3.0 or by
+      # March 1, 2009. Instead, use Nokogiri::XML::Node#fragment()
       def self.new_from_str string
-        $stderr.puts("This method is deprecated and will be removed in 1.2.0 or by March 1, 2009. Instead, use Nokogiri::HTML.fragment()")
+        $stderr.puts("This method is deprecated and will be removed in 1.3.0 or by March 1, 2009. Instead, use Nokogiri::XML::Node#fragment")
         Nokogiri::HTML.fragment(string).first
       end
     end