nokogiri 1.1.1-java

data/lib/nokogiri/html.rb

@@ -0,0 +1,105 @@
+require 'nokogiri/html/document'
+require 'nokogiri/html/sax/parser'
+
+module Nokogiri
+  class << self
+    ###
+    # Parse HTML.  +thing+ may be a String, or any object that
+    # responds to _read_ and _close_ such as an IO, or StringIO.
+    # +url+ is resource where this document is located.  +encoding+ is the
+    # encoding that should be used when processing the document. +options+
+    # is a number that sets options in the parser, such as
+    # Nokogiri::XML::PARSE_RECOVER.  See the constants in
+    # Nokogiri::XML.
+    def HTML thing, url = nil, encoding = nil, options = 2145
+      Nokogiri::HTML.parse(thing, url, encoding, options)
+    end
+  end
+
+  module HTML
+    # Parser options
+    PARSE_NOERROR   = 1 << 5  # No error reports
+    PARSE_NOWARNING = 1 << 6  # No warnings 
+    PARSE_PEDANTIC  = 1 << 7  # Pedantic errors
+    PARSE_NOBLANKS  = 1 << 8  # Remove blanks nodes
+    PARSE_NONET     = 1 << 11 # No network access
+
+    class << self
+      ###
+      # Parse HTML.  See Nokogiri.HTML.
+      def parse string_or_io, url = nil, encoding = nil, options = 2145
+        if string_or_io.respond_to?(:read)
+          url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
+          string_or_io = string_or_io.read
+        end
+
+        Document.read_memory(string_or_io, url, encoding, options)
+      end
+
+      ####
+      # Parse a fragment from +string+ in to a NodeSet.
+      def fragment string
+        doc = parse(string)
+        finder = lambda { |children, f|
+          children.each do |child|
+            return children if string =~ /<#{child.name}/
+            finder.call(child.children, f)
+          end
+        }
+        finder.call(doc.children, finder)
+      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}
+  end
+end

data/lib/nokogiri/html/builder.rb

@@ -0,0 +1,9 @@
+module Nokogiri
+  module HTML
+    class Builder < XML::Builder
+      def to_html
+        @doc.to_html
+      end
+    end
+  end
+end

data/lib/nokogiri/html/document.rb

@@ -0,0 +1,9 @@
+module Nokogiri
+  module HTML
+    class Document < XML::Document
+      def to_html
+        serialize
+      end
+    end
+  end
+end

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

@@ -0,0 +1,21 @@
+module Nokogiri
+  module HTML
+    module SAX
+      class Parser < XML::SAX::Parser
+        ###
+        # Parse html stored in +data+ using +encoding+
+        def parse_memory data, encoding = 'UTF-8'
+          native_parse_memory(data, encoding)
+        end
+
+        ###
+        # Parse a file with +filename+
+        def parse_file filename, encoding = 'UTF-8'
+          raise Errno::ENOENT unless File.exists?(filename)
+          raise Errno::EISDIR if File.directory?(filename)
+          native_parse_file filename, encoding
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/version.rb

@@ -0,0 +1,3 @@
+module Nokogiri
+  VERSION = '1.1.1'
+end

data/lib/nokogiri/xml.rb

@@ -0,0 +1,83 @@
+require 'nokogiri/xml/sax'
+require 'nokogiri/xml/before_handler'
+require 'nokogiri/xml/after_handler'
+require 'nokogiri/xml/node'
+require 'nokogiri/xml/attr'
+require 'nokogiri/xml/dtd'
+require 'nokogiri/xml/text'
+require 'nokogiri/xml/cdata'
+require 'nokogiri/xml/comment'
+require 'nokogiri/xml/document'
+require 'nokogiri/xml/node_set'
+require 'nokogiri/xml/xpath'
+require 'nokogiri/xml/xpath_context'
+require 'nokogiri/xml/builder'
+require 'nokogiri/xml/reader'
+require 'nokogiri/xml/syntax_error'
+require 'nokogiri/xml/notation'
+require 'nokogiri/xml/element'
+require 'nokogiri/xml/entity_declaration'
+
+module Nokogiri
+  class << self
+    ###
+    # Parse an XML file.  +thing+ may be a String, or any object that
+    # responds to _read_ and _close_ such as an IO, or StringIO.
+    # +url+ is resource where this document is located.  +encoding+ is the
+    # encoding that should be used when processing the document. +options+
+    # is a number that sets options in the parser, such as
+    # Nokogiri::XML::PARSE_RECOVER.  See the constants in
+    # Nokogiri::XML.
+    def XML thing, url = nil, encoding = nil, options = 1
+      Nokogiri::XML.parse(thing, url, encoding, options)
+    end
+  end
+
+  module XML
+    # Parser options
+    PARSE_RECOVER     = 1 << 0  # Recover from errors
+    PARSE_NOENT       = 1 << 1  # Substitute entities
+    PARSE_DTDLOAD     = 1 << 2  # Load external subsets
+    PARSE_DTDATTR     = 1 << 3  # Default DTD attributes
+    PARSE_DTDVALID    = 1 << 4  # validate with the DTD
+    PARSE_NOERROR     = 1 << 5  # suppress error reports
+    PARSE_NOWARNING   = 1 << 6  # suppress warning reports
+    PARSE_PEDANTIC    = 1 << 7  # pedantic error reporting
+    PARSE_NOBLANKS    = 1 << 8  # remove blank nodes
+    PARSE_SAX1        = 1 << 9  # use the SAX1 interface internally
+    PARSE_XINCLUDE    = 1 << 10 # Implement XInclude substitition
+    PARSE_NONET       = 1 << 11 # Forbid network access
+    PARSE_NODICT      = 1 << 12 # Do not reuse the context dictionnary
+    PARSE_NSCLEAN     = 1 << 13 # remove redundant namespaces declarations
+    PARSE_NOCDATA     = 1 << 14 # merge CDATA as text nodes
+    PARSE_NOXINCNODE  = 1 << 15 # do not generate XINCLUDE START/END nodes
+
+    class << self
+      ###
+      # Parse an XML document.  See Nokogiri.XML.
+      def parse string_or_io, url = nil, encoding = nil, options = 2159
+        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)
+        end
+
+        # read_memory pukes on empty docs
+        return Document.new if string_or_io.nil? or string_or_io.empty?
+
+        Document.read_memory(string_or_io, url, encoding, options)
+      end
+
+      ###
+      # Sets whether or not entities should be substituted.
+      def substitute_entities=(value = true)
+        Document.substitute_entities = value
+      end
+
+      ###
+      # Sets whether or not external subsets should be loaded
+      def load_external_subsets=(value = true)
+        Document.load_external_subsets = value
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/after_handler.rb

@@ -0,0 +1,18 @@
+module Nokogiri
+  module XML
+    class AfterHandler < BeforeHandler
+      attr_accessor :after_nodes
+
+      def initialize node, original_html
+        super
+        @after_nodes = []
+      end
+
+      def end_element name
+        return unless @original_html =~ /<#{name}/i
+        @after_nodes << @stack.last if @stack.length == 1
+        @stack.pop
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/attr.rb

@@ -0,0 +1,10 @@
+module Nokogiri
+  module XML
+    class Attr < Node
+      def value
+        children.first.to_s
+      end
+      alias :to_s :value
+    end
+  end
+end

data/lib/nokogiri/xml/before_handler.rb

@@ -0,0 +1,33 @@
+module Nokogiri
+  module XML
+    class BeforeHandler < Nokogiri::XML::SAX::Document # :nodoc:
+      def initialize node, original_html
+        @original_html = original_html
+        @node = node
+        @document = node.document
+        @stack = []
+      end
+
+      def start_element name, attrs = []
+        return unless @original_html =~ /<#{name}/i
+        node = Node.new(name, @document)
+        Hash[*attrs].each do |k,v|
+          node[k] = v
+        end
+        node.parent = @stack.last if @stack.length != 0
+        @stack << node
+      end
+
+      def characters string
+        node = @stack.last
+        node.content += string
+      end
+
+      def end_element name
+        return unless @original_html =~ /<#{name}/i
+        @node.add_previous_sibling @stack.last if @stack.length == 1
+        @stack.pop
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/builder.rb

@@ -0,0 +1,84 @@
+module Nokogiri
+  module XML
+    class Builder
+      attr_accessor :doc, :parent
+      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)
+        @parent = @doc
+      end
+
+      def text(string)
+        node = Nokogiri::XML::Text.new(string, @doc)
+        insert(node)
+      end
+
+      def cdata(string)
+        node = Nokogiri::XML::CDATA.new(@doc, string)
+        insert(node)
+      end
+
+      def to_xml
+        @doc.to_xml
+      end
+
+      def method_missing(method, *args, &block)
+        if @context.respond_to?(method)
+          @context.send(method, *args, &block)
+        else
+          node = Nokogiri::XML::Node.new(method.to_s, @doc) { |n|
+            if content = args.first
+              if content.is_a?(Hash)
+                content.each { |k,v| n[k.to_s] = v.to_s }
+              else
+                n.content = content
+              end
+            end
+          }
+          insert(node, &block)
+        end
+      end
+
+      private
+      def insert(node, &block)
+        node.parent = @parent
+        if block_given?
+          @parent = node
+          instance_eval(&block)
+          @parent = node.parent
+        end
+        NodeBuilder.new(node, self)
+      end
+
+      class NodeBuilder # :nodoc:
+        def initialize(node, doc_builder)
+          @node = node
+          @doc_builder = doc_builder
+        end
+
+        def method_missing(method, *args, &block)
+          case method.to_s
+          when /^(.*)!$/
+            @node['id'] = $1
+            @node.content = args.first if args.first
+          when /^(.*)=/
+            @node[$1] = args.first
+          else
+            @node['class'] = 
+              ((@node['class'] || '').split(/\s/) + [method.to_s]).join(' ')
+            @node.content = args.first if args.first
+          end
+          if block_given?
+            @doc_builder.parent = @node
+            return @doc_builder.instance_eval(&block)
+          end
+          self
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/cdata.rb

@@ -0,0 +1,9 @@
+module Nokogiri
+  module XML
+    class CDATA < Text
+      def name
+        'cdata-section'
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/comment.rb

@@ -0,0 +1,6 @@
+module Nokogiri
+  module XML
+    class Comment < Node
+    end
+  end
+end

data/lib/nokogiri/xml/document.rb

@@ -0,0 +1,55 @@
+module Nokogiri
+  module XML
+    class Document < Node
+      def name
+        'document'
+      end
+
+      def document
+        self
+      end
+
+      def decorators(key)
+        @decorators ||= Hash.new
+        @decorators[key] ||= []
+      end
+
+      ###
+      # Explore a document with shortcut methods.
+      def slop!
+        unless decorators(XML::Node).include? Nokogiri::Decorators::Slop
+          decorators(XML::Node) << Nokogiri::Decorators::Slop
+          decorate!
+        end
+
+        self
+      end
+
+      ###
+      # Apply any decorators to +node+
+      def decorate(node)
+        return unless @decorators
+        @decorators.each { |klass,list|
+          next unless node.is_a?(klass)
+          list.each { |moodule| node.extend(moodule) }
+        }
+      end
+
+      def node_cache
+        @node_cache ||= {}
+      end
+
+      def to_xml
+        serialize
+      end
+
+      def inner_html
+        serialize
+      end
+
+      def namespaces
+        root ? root.collect_namespaces : {}
+      end
+    end
+  end
+end