nokogiri 1.0.0 → 1.6.8.1

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

@@ -1,19 +1,50 @@
 module Nokogiri
   module HTML
+    ###
+    # Nokogiri lets you write a SAX parser to process HTML but get HTML
+    # correction features.
+    #
+    # See Nokogiri::HTML::SAX::Parser for a basic example of using a
+    # SAX parser with HTML.
+    #
+    # For more information on SAX parsers, see Nokogiri::XML::SAX
     module SAX
-      class Parser < XML::SAX::Parser
+      ###
+      # This class lets you perform SAX style parsing on HTML with HTML
+      # error correction.
+      #
+      # Here is a basic usage example:
+      #
+      #   class MyDoc < Nokogiri::XML::SAX::Document
+      #     def start_element name, attributes = []
+      #       puts "found a #{name}"
+      #     end
+      #   end
+      #
+      #   parser = Nokogiri::HTML::SAX::Parser.new(MyDoc.new)
+      #   parser.parse(File.read(ARGV[0], mode: 'rb'))
+      #
+      # For more information on SAX parsers, see Nokogiri::XML::SAX
+      class Parser < Nokogiri::XML::SAX::Parser
         ###
         # Parse html stored in +data+ using +encoding+
         def parse_memory data, encoding = 'UTF-8'
-          native_parse_memory(data, encoding)
+          raise ArgumentError unless data
+          return unless data.length > 0
+          ctx = ParserContext.memory(data, encoding)
+          yield ctx if block_given?
+          ctx.parse_with self
         end
 
         ###
         # Parse a file with +filename+
         def parse_file filename, encoding = 'UTF-8'
-          raise Errno::ENOENT unless File.exists?(filename)
+          raise ArgumentError unless filename
+          raise Errno::ENOENT unless File.exist?(filename)
           raise Errno::EISDIR if File.directory?(filename)
-          native_parse_file filename, encoding
+          ctx = ParserContext.file(filename, encoding)
+          yield ctx if block_given?
+          ctx.parse_with self
         end
       end
     end

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

@@ -0,0 +1,16 @@
+module Nokogiri
+  module HTML
+    module SAX
+      ###
+      # Context for HTML SAX parsers.  This class is usually not instantiated
+      # by the user.  Instead, you should be looking at
+      # Nokogiri::HTML::SAX::Parser
+      class ParserContext < Nokogiri::XML::SAX::ParserContext
+        def self.new thing, encoding = 'UTF-8'
+          [:read, :close].all? { |x| thing.respond_to?(x) } ?  super :
+            memory(thing, encoding)
+        end
+      end
+    end
+  end
+end

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

@@ -0,0 +1,36 @@
+module Nokogiri
+  module HTML
+    module SAX
+      class PushParser
+        
+        # The Nokogiri::HTML::SAX::Document on which the PushParser will be
+        # operating
+        attr_accessor :document
+        
+        def initialize(doc = HTML::SAX::Document.new, file_name = nil, encoding = 'UTF-8')
+          @document = doc
+          @encoding = encoding
+          @sax_parser = HTML::SAX::Parser.new(doc, @encoding)
+
+          ## Create our push parser context
+          initialize_native(@sax_parser, file_name, encoding)
+        end
+        
+        ###
+        # Write a +chunk+ of HTML to the PushParser.  Any callback methods
+        # that can be called will be called immediately.
+        def write chunk, last_chunk = false
+          native_write(chunk, last_chunk)
+        end
+        alias :<< :write
+
+        ###
+        # Finish the parsing.  This method is only necessary for
+        # Nokogiri::HTML::SAX::Document#end_document to be called.
+        def finish
+          write '', true
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html.rb

@@ -1,95 +1,37 @@
+require 'nokogiri/html/entity_lookup'
 require 'nokogiri/html/document'
+require 'nokogiri/html/document_fragment'
+require 'nokogiri/html/sax/parser_context'
 require 'nokogiri/html/sax/parser'
+require 'nokogiri/html/sax/push_parser'
+require 'nokogiri/html/element_description'
+require 'nokogiri/html/element_description_defaults'
 
 module Nokogiri
   class << self
-    def HTML thing, url = nil, encoding = nil, options = 2145
-      Nokogiri::HTML.parse(thing, url, encoding, options)
+    ###
+    # Parse HTML.  Convenience method for Nokogiri::HTML::Document.parse
+    def HTML thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block
+      Nokogiri::HTML::Document.parse(thing, url, encoding, options, &block)
     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
-      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)
+      ###
+      # Parse HTML.  Convenience method for Nokogiri::HTML::Document.parse
+      def parse thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block
+        Document.parse(thing, url, encoding, options, &block)
       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)
+      def fragment string, encoding = nil
+        HTML::DocumentFragment.parse string, encoding
       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}
+    # Instance of Nokogiri::HTML::EntityLookup
+    NamedCharacters = EntityLookup.new
   end
 end

data/lib/nokogiri/syntax_error.rb

@@ -0,0 +1,4 @@
+module Nokogiri
+  class SyntaxError < ::StandardError
+  end
+end

data/lib/nokogiri/version.rb

@@ -1,3 +1,108 @@
 module Nokogiri
-  VERSION = '1.0.0'
+  # The version of Nokogiri you are using
+  VERSION = '1.6.8.1'
+
+  class VersionInfo # :nodoc:
+    def jruby?
+      ::JRUBY_VERSION if RUBY_PLATFORM == "java"
+    end
+
+    def engine
+      defined?(RUBY_ENGINE) ? RUBY_ENGINE : 'mri'
+    end
+
+    def loaded_parser_version
+      LIBXML_PARSER_VERSION.scan(/^(\d+)(\d\d)(\d\d)(?!\d)/).first.collect{ |j|
+        j.to_i
+      }.join(".")
+    end
+
+    def compiled_parser_version
+      LIBXML_VERSION
+    end
+
+    def libxml2?
+      defined?(LIBXML_VERSION)
+    end
+
+    def libxml2_using_system?
+      ! libxml2_using_packaged?
+    end
+
+    def libxml2_using_packaged?
+      NOKOGIRI_USE_PACKAGED_LIBRARIES
+    end
+
+    def warnings
+      return [] unless libxml2?
+
+      if compiled_parser_version != loaded_parser_version
+        ["Nokogiri was built against LibXML version #{compiled_parser_version}, but has dynamically loaded #{loaded_parser_version}"]
+      else
+        []
+      end
+    end
+
+    def to_hash
+      hash_info = {}
+      hash_info['warnings']              = []
+      hash_info['nokogiri']              = Nokogiri::VERSION
+      hash_info['ruby']                  = {}
+      hash_info['ruby']['version']       = ::RUBY_VERSION
+      hash_info['ruby']['platform']      = ::RUBY_PLATFORM
+      hash_info['ruby']['description']   = ::RUBY_DESCRIPTION
+      hash_info['ruby']['engine']        = engine
+      hash_info['ruby']['jruby']         = jruby? if jruby?
+
+      if libxml2?
+        hash_info['libxml']              = {}
+        hash_info['libxml']['binding']   = 'extension'
+        if libxml2_using_packaged?
+          hash_info['libxml']['source']  = "packaged"
+          hash_info['libxml']['libxml2_path'] = NOKOGIRI_LIBXML2_PATH
+          hash_info['libxml']['libxslt_path'] = NOKOGIRI_LIBXSLT_PATH
+          hash_info['libxml']['libxml2_patches'] = NOKOGIRI_LIBXML2_PATCHES
+          hash_info['libxml']['libxslt_patches'] = NOKOGIRI_LIBXSLT_PATCHES
+        else
+          hash_info['libxml']['source']  = "system"
+        end
+        hash_info['libxml']['compiled']  = compiled_parser_version
+        hash_info['libxml']['loaded']    = loaded_parser_version
+        hash_info['warnings']            = warnings
+      elsif jruby?
+        hash_info['xerces']   = Nokogiri::XERCES_VERSION
+        hash_info['nekohtml'] = Nokogiri::NEKO_VERSION
+      end
+
+      hash_info
+    end
+
+    def to_markdown
+      begin
+        require 'psych'
+      rescue LoadError
+      end
+      require 'yaml'
+      "# Nokogiri (#{Nokogiri::VERSION})\n" +
+      YAML.dump(to_hash).each_line.map { |line| "    #{line}" }.join
+    end
+
+    # FIXME: maybe switch to singleton?
+    @@instance = new
+    @@instance.warnings.each do |warning|
+      warn "WARNING: #{warning}"
+    end
+    def self.instance; @@instance; end
+  end
+
+  # More complete version information about libxml
+  VERSION_INFO = VersionInfo.instance.to_hash
+
+  def self.uses_libxml? # :nodoc:
+    VersionInfo.instance.libxml2?
+  end
+
+  def self.jruby? # :nodoc:
+    VersionInfo.instance.jruby?
+  end
 end

data/lib/nokogiri/xml/attr.rb

@@ -0,0 +1,14 @@
+module Nokogiri
+  module XML
+    class Attr < Node
+      alias :value :content
+      alias :to_s :content
+      alias :content= :value=
+
+      private
+      def inspect_attributes
+        [:name, :namespace, :value]
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/attribute_decl.rb

@@ -0,0 +1,18 @@
+module Nokogiri
+  module XML
+    ###
+    # Represents an attribute declaration in a DTD
+    class AttributeDecl < Nokogiri::XML::Node
+      undef_method :attribute_nodes
+      undef_method :attributes
+      undef_method :content
+      undef_method :namespace
+      undef_method :namespace_definitions
+      undef_method :line if method_defined?(:line)
+
+      def inspect
+        "#<#{self.class.name}:#{sprintf("0x%x", object_id)} #{to_s.inspect}>"
+      end
+    end
+  end
+end