origami 1.2.7 → 2.0.0

data/lib/origami/metadata.rb

@@ -1,25 +1,20 @@
 =begin
 
-= File
-	metadata.rb
-
-= Info
-	This file is part of Origami, PDF manipulation framework for Ruby
-	Copyright (C) 2010	Guillaume Delugré <guillaume AT security-labs DOT org>
-	All right reserved.
-	
-  Origami is free software: you can redistribute it and/or modify
-  it under the terms of the GNU Lesser General Public License as published by
-  the Free Software Foundation, either version 3 of the License, or
-  (at your option) any later version.
-
-  Origami is distributed in the hope that it will be useful,
-  but WITHOUT ANY WARRANTY; without even the implied warranty of
-  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-  GNU Lesser General Public License for more details.
-
-  You should have received a copy of the GNU Lesser General Public License
-  along with Origami.  If not, see <http://www.gnu.org/licenses/>.
+    This file is part of Origami, PDF manipulation framework for Ruby
+    Copyright (C) 2016	Guillaume Delugré.
+
+    Origami is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Lesser General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    Origami is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
+
+    You should have received a copy of the GNU Lesser General Public License
+    along with Origami.  If not, see <http://www.gnu.org/licenses/>.
 
 =end
 
@@ -27,155 +22,151 @@ require 'rexml/document'
 
 module Origami
 
-  class PDF
+    class PDF
+        #
+        # Returns true if the document has a document information dictionary.
+        #
+        def document_info?
+            trailer_key? :Info
+        end
 
-    #
-    # Returns true if the document has a document information dictionary.
-    #
-    def has_document_info?
-      has_attr? :Info 
-    end
+        #
+        # Returns the document information dictionary if present.
+        #
+        def document_info
+            trailer_key :Info
+        end
 
-    #
-    # Returns true if the document has a catalog metadata stream.
-    #
-    def has_metadata?
-      self.Catalog.Metadata.is_a?(Stream)
-    end
+        def title; get_document_info_field(:Title) end
+        def author; get_document_info_field(:Author) end
+        def subject; get_document_info_field(:Subject) end
+        def keywords; get_document_info_field(:Keywords) end
+        def creator; get_document_info_field(:Creator) end
+        def producer; get_document_info_field(:Producer) end
+        def creation_date; get_document_info_field(:CreationDate) end
+        def mod_date; get_document_info_field(:ModDate) end
+
+        #
+        # Returns true if the document has a catalog metadata stream.
+        #
+        def metadata?
+            self.Catalog.Metadata.is_a?(Stream)
+        end
 
-    #
-    # Returns the document information dictionary if present.
-    #
-    def get_document_info
-      get_doc_attr :Info
-    end
+        #
+        # Returns a Hash of the information found in the metadata stream
+        #
+        def metadata
+            metadata_stm = self.Catalog.Metadata
 
-    def title; get_document_info_field(:Title) end
-    def author; get_document_info_field(:Author) end
-    def subject; get_document_info_field(:Subject) end
-    def keywords; get_document_info_field(:Keywords) end
-    def creator; get_document_info_field(:Creator) end
-    def producer; get_document_info_field(:Producer) end
-    def creation_date; get_document_info_field(:CreationDate) end
-    def mod_date; get_document_info_field(:ModDate) end
+            if metadata_stm.is_a?(Stream)
+                doc = REXML::Document.new(metadata_stm.data)
+                info = {}
 
-    #
-    # Returns a Hash of the information found in the metadata stream
-    #
-    def get_metadata
-      metadata_stm = self.Catalog.Metadata
+                doc.elements.each('*/*/rdf:Description') do |description|
 
-      if metadata_stm.is_a?(Stream)
-        doc = REXML::Document.new(metadata_stm.data)
+                    description.attributes.each_attribute do |attr|
+                        case attr.prefix
+                        when 'pdf','xap'
+                            info[attr.name] = attr.value
+                        end
+                    end
 
-        info = {}
+                    description.elements.each('*') do |element|
+                        value = (element.elements['.//rdf:li'] || element).text
+                        info[element.name] = value.to_s
+                    end
+                end
 
-        doc.elements.each('*/*/rdf:Description') do |description|
-          
-          description.attributes.each_attribute do |attr|
-            case attr.prefix
-              when 'pdf','xap'
-                info[attr.name] = attr.value
+                info
             end
-          end
-
-          description.elements.each('*') do |element|
-            value = (element.elements['.//rdf:li'] || element).text
-            info[element.name] = value.to_s
-          end
-
         end
 
-        info
-      end
-    end
+        #
+        # Modifies or creates a metadata stream.
+        #
+        def create_metadata(info = {})
+            skeleton = <<-XMP
+            <?packet begin="#{"\xef\xbb\xbf"}" id="W5M0MpCehiHzreSzNTczkc9d"?>
+              <x:xmpmeta xmlns:x="adobe:ns:meta/">
+                <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+                  <rdf:Description rdf:about="" xmlns:pdf="http://ns.adobe.com/pdf/1.3/">
+                  </rdf:Description>
+                </rdf:RDF>
+              </x:xmpmeta>
+            <?xpacket end="w"?>
+            XMP
+
+            xml =
+                if self.Catalog.Metadata.is_a?(Stream)
+                    self.Catalog.Metadata.data
+                else
+                    skeleton
+                end
+
+            doc = REXML::Document.new(xml)
+            desc = doc.elements['*/*/rdf:Description']
+
+            info.each do |name, value|
+                elt = REXML::Element.new "pdf:#{name}"
+                elt.text = value
+
+                desc.elements << elt
+            end
 
-    #
-    # Modifies or creates a metadata stream.
-    #
-    def create_metadata(info = {})
-      skeleton = <<-XMP
-<?packet begin="#{"\xef\xbb\xbf"}" id="W5M0MpCehiHzreSzNTczkc9d"?>
-  <x:xmpmeta xmlns:x="adobe:ns:meta/">
-    <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
-      <rdf:Description rdf:about="" xmlns:pdf="http://ns.adobe.com/pdf/1.3/">
-      </rdf:Description>
-    </rdf:RDF>
-  </x:xmpmeta>
-<?xpacket end="w"?>
-      XMP
-
-      xml =
-        if self.Catalog.Metadata.is_a?(Stream)
-          self.Catalog.Metadata.data
-        else
-          skeleton
-        end
+            xml = ""; doc.write(xml, 4)
 
-      doc = REXML::Document.new(xml)
-      desc = doc.elements['*/*/rdf:Description']
-  
-      info.each do |name, value|
-        elt = REXML::Element.new "pdf:#{name}"
-        elt.text = value
+            if self.Catalog.Metadata.is_a?(Stream)
+                self.Catalog.Metadata.data = xml
+            else
+               self.Catalog.Metadata = Stream.new(xml)
+            end
 
-        desc.elements << elt
-      end
+            self.Catalog.Metadata
+        end
 
-      xml = ""; doc.write(xml, 3)
+        private
 
-      if self.Catalog.Metadata.is_a?(Stream)
-        self.Catalog.Metadata.data = xml
-      else
-        self.Catalog.Metadata = Stream.new(xml)
-      end
+        def get_document_info_field(field) #:nodoc:
+            if self.document_info?
+                doc_info = self.document_info
 
-      self.Catalog.Metadata
+                if doc_info.key?(field)
+                    case obj = doc_info[field].solve
+                    when String then obj.value
+                    when Stream then obj.data
+                    end
+                end
+            end
+        end
     end
 
-    private
+    #
+    # Class representing an information Dictionary, containing title, author, date of creation and the like.
+    #
+    class Metadata < Dictionary
+        include StandardObject
+
+        field   :Title,                   :Type => String, :Version => "1.1"
+        field   :Author,                  :Type => String
+        field   :Subject,                 :Type => String, :Version => "1.1"
+        field   :Keywords,                :Type => String, :Version => "1.1"
+        field   :Creator,                 :Type => String
+        field   :Producer,                :Type => String
+        field   :CreationDate,            :Type => String
+        field   :ModDate,                 :Type => String, :Version => "1.1"
+        field   :Trapped,                 :Type => Name, :Default => :Unknown, :Version => "1.3"
+    end
 
-    def get_document_info_field(field) #:nodoc:
-      if has_document_info?
-        doc_info = get_document_info
+    #
+    # Class representing a metadata Stream.
+    # This stream can contain the same information as the Metadata dictionary, but is storing in XML data.
+    #
+    class MetadataStream < Stream
+        include StandardObject
 
-        if doc_info.has_key?(field)
-          case obj = get_document_info[field].solve
-            when String then obj.value
-            when Stream then obj.data
-          end
-        end
-      end
+        field   :Type,                    :Type => Name, :Default => :Metadata, :Required => true
+        field   :Subtype,                 :Type => Name, :Default =>:XML, :Required => true
     end
 
-  end
-
-  #
-  # Class representing an information Dictionary, containing title, author, date of creation and the like.
-  #
-  class Metadata < Dictionary
-    include StandardObject
-
-    field   :Title,                   :Type => String, :Version => "1.1"
-    field   :Author,                  :Type => String
-    field   :Subject,                 :Type => String, :Version => "1.1"
-    field   :Keywords,                :Type => String, :Version => "1.1"
-    field   :Creator,                 :Type => String
-    field   :Producer,                :Type => String
-    field   :CreationDate,            :Type => ByteString
-    field   :ModDate,                 :Type => ByteString, :Version => "1.1"
-    field   :Trapped,                 :Type => Name, :Default => :Unknown, :Version => "1.3"
-  end
-  
-  #
-  # Class representing a metadata Stream.
-  # This stream can contain the same information as the Metadata dictionary, but is storing in XML data.
-  #
-  class MetadataStream < Stream
-    include StandardObject
-   
-    field   :Type,                    :Type => Name, :Default => :Metadata, :Required => true
-    field   :Subtype,                 :Type => Name, :Default =>:XML, :Required => true
-  end
-
 end

data/lib/origami/name.rb

@@ -1,170 +1,134 @@
 =begin
 
-= File
-	name.rb
-
-= Info
-	This file is part of Origami, PDF manipulation framework for Ruby
-	Copyright (C) 2010	Guillaume Delugré <guillaume AT security-labs DOT org>
-	All right reserved.
-	
-  Origami is free software: you can redistribute it and/or modify
-  it under the terms of the GNU Lesser General Public License as published by
-  the Free Software Foundation, either version 3 of the License, or
-  (at your option) any later version.
-
-  Origami is distributed in the hope that it will be useful,
-  but WITHOUT ANY WARRANTY; without even the implied warranty of
-  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-  GNU Lesser General Public License for more details.
-
-  You should have received a copy of the GNU Lesser General Public License
-  along with Origami.  If not, see <http://www.gnu.org/licenses/>.
+    This file is part of Origami, PDF manipulation framework for Ruby
+    Copyright (C) 2016	Guillaume Delugré.
 
-=end
+    Origami is free software: you can redistribute it and/or modify
+    it under the terms of the GNU Lesser General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
 
-if RUBY_VERSION < '1.9'
-  class EmptySymbol
-    def ==(sym)
-      sym.is_a?(EmptySymbol)
-    end
+    Origami is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU Lesser General Public License for more details.
 
-    def id2name
-      ""
-    end
-    alias to_s id2name
+    You should have received a copy of the GNU Lesser General Public License
+    along with Origami.  If not, see <http://www.gnu.org/licenses/>.
 
-    def to_sym
-      self
-    end
+=end
 
-    def to_o
-      Name.new("")
-    end
+module Origami
 
-    def inspect
-      ":"
-    end
-  end
-end
+    REGULARCHARS = "([^ \\t\\r\\n\\0\\[\\]<>()%\\/]|#[a-fA-F0-9][a-fA-F0-9])*" #:nodoc:
 
-module Origami
+    class InvalidNameObjectError < InvalidObjectError #:nodoc:
+    end
 
-  REGULARCHARS = "([^ \\t\\r\\n\\0\\[\\]<>()%\\/]|#[a-fA-F0-9][a-fA-F0-9])*" #:nodoc:
-
-  class InvalidNameObjectError < InvalidObjectError #:nodoc:
-  end
-
-  #
-  # Class representing a Name Object.
-  # Name objects are strings which identify some PDF file inner structures.
-  #
-  class Name #< DelegateClass(Symbol)
-    
-    include Origami::Object
-    
-    TOKENS = %w{ / } #:nodoc:
-    
-    @@regexp = Regexp.new(WHITESPACES + TOKENS.first + "(" + REGULARCHARS + ")" + WHITESPACES) #:nodoc
-    
     #
-    # Creates a new Name.
-    # _name_:: A symbol representing the new Name value.
+    # Class representing a Name Object.
+    # Name objects are strings which identify some PDF file inner structures.
     #
-    def initialize(name = "")
-      unless name.is_a?(Symbol) or name.is_a?(::String)
-        raise TypeError, "Expected type Symbol or String, received #{name.class}."
-      end
-      
-      @value = name.to_s
-      
-      super()
-    end
+    class Name #< DelegateClass(Symbol)
+        include Origami::Object
 
-    if RUBY_VERSION < '1.9'
-      def value   
-        ( @value.empty? ) ? EmptySymbol.new : @value.to_sym
-      end
-    else
-      def value   
-        @value.to_sym
-      end
-    end
+        TOKENS = %w{ / } #:nodoc:
 
-    def ==(object) #:nodoc:
-      self.eql?(object) or @value.to_sym == object
-    end
-    
-    def eql?(object) #:nodoc:
-      object.is_a?(Name) and self.to_s == object.to_s
-    end
-    
-    def hash #:nodoc:
-      @value.hash
-    end
-    
-    def to_s #:nodoc:
-      super(TOKENS.first + Name.expand(@value))
-    end
-    
-    def self.parse(stream, parser = nil) #:nodoc:
-
-      offset = stream.pos
-      
-      name = 
-        if stream.scan(@@regexp).nil?
-          raise InvalidNameObjectError, "Bad name format"
-        else
-          value = stream[2]
-          
-          Name.new(value.include?('#') ? contract(value) : value)
+        @@regexp = Regexp.new(WHITESPACES + TOKENS.first + "(?<name>#{REGULARCHARS})" + WHITESPACES) #:nodoc
+
+        #
+        # Creates a new Name.
+        # _name_:: A symbol representing the new Name value.
+        #
+        def initialize(name = "")
+            unless name.is_a?(Symbol) or name.is_a?(::String)
+                raise TypeError, "Expected type Symbol or String, received #{name.class}."
+            end
+
+            @value = name.to_s
+
+            super()
         end
 
-      name.file_offset = offset
+        def value
+            @value.to_sym
+        end
 
-      name
-    end
-    
-    def self.contract(name) #:nodoc:
-     
-      i = 0
-      name = name.dup
-
-      while i < name.length
-
-        if name[i,1] == "#"
-          digits = name[i+1, 2]
-          
-          unless /^[A-Za-z0-9]{2}$/ === digits
-            raise InvalidNameObjectError, "Irregular use of # token"
-          end
-          
-          char = digits.hex.chr
-          
-          if char == "\0"
-            raise InvalidNameObjectError, "Null byte forbidden inside name definition"
-          end
-          
-          name[i, 3] = char
+        def <=>(name)
+            return unless name.is_a?(Name)
+
+            self.value <=> name.value
         end
-          
-        i = i + 1
-      end
 
-      name
-    end
-    
-    def self.expand(name) #:nodoc:
-      
-      forbiddenchars = /[ #\t\r\n\0\[\]<>()%\/]/
-      
-      name.gsub(forbiddenchars) do |c|
-        "#" + c[0].ord.to_s(16).rjust(2,"0")
-      end
-    end
-    
-    def self.native_type ; Name end
+        def ==(object) #:nodoc:
+            self.eql?(object) or @value.to_sym == object
+        end
 
-  end
+        def eql?(object) #:nodoc:
+            object.is_a?(Name) and self.value.eql?(object.value)
+        end
+
+        def hash #:nodoc:
+            @value.hash
+        end
+
+        def to_s #:nodoc:
+            super(TOKENS.first + Name.expand(@value))
+        end
+
+        def self.parse(stream, parser = nil) #:nodoc:
+            offset = stream.pos
+
+            name =
+                if stream.scan(@@regexp).nil?
+                    raise InvalidNameObjectError, "Bad name format"
+                else
+                    value = stream['name']
+
+                    Name.new(value.include?('#') ? contract(value) : value)
+                end
+
+            name.file_offset = offset
+
+            name
+        end
+
+        def self.contract(name) #:nodoc:
+            i = 0
+            name = name.dup
+
+            while i < name.length
+                if name[i] == "#"
+                    digits = name[i+1, 2]
+
+                    unless /^[A-Za-z0-9]{2}$/ === digits
+                        raise InvalidNameObjectError, "Irregular use of # token"
+                    end
+
+                    char = digits.hex.chr
+
+                    if char == "\0"
+                        raise InvalidNameObjectError, "Null byte forbidden inside name definition"
+                    end
+
+                    name[i, 3] = char
+                end
+
+                i = i + 1
+            end
+
+            name
+        end
+
+        def self.expand(name) #:nodoc:
+            forbiddenchars = /[ #\t\r\n\0\[\]<>()%\/]/
+
+            name.gsub(forbiddenchars) do |c|
+                "#" + c.ord.to_s(16).rjust(2,"0")
+            end
+        end
+
+        def self.native_type ; Name end
+    end
 
 end