origami 1.1.1 → 1.1.2

data/README

@@ -14,9 +14,10 @@ VERSION
 
   1.1
 
-DEPENDENCIES
+OPTIONAL DEPENDENCIES
 
   - Ruby-GTK2 (only for GUI), http://ruby-gnome2.sourceforge.jp/
+  - Ruby with OpenSSL support
 
 INSTALL
 

data/bin/gui/walker.rb

@@ -61,13 +61,13 @@ module PDFWalker  #:nodoc:all
     attr_reader :config
     attr_reader :filename
 
-    def self.start
+    def self.start(file = nil)
       Gtk.init
-      Walker.new
+      Walker.new(file)
       Gtk.main
     end
 
-    def initialize
+    def initialize(target_file = nil)
       super("PDF Walker")
       
       @config = Walker::Config.new
@@ -115,7 +115,7 @@ module PDFWalker  #:nodoc:all
       #maximize
       show_all
       
-      open
+      open(target_file)
     end
     
     def error(msg)

data/bin/pdfwalker

@@ -3,5 +3,5 @@
 $:.unshift "#{File.dirname(__FILE__)}" if RUBY_VERSION >= '1.9'
 require 'gui/walker'
 
-PDFWalker::Walker.start
+PDFWalker::Walker.start(ARGV[0])
 

data/bin/shell/.irbrc

@@ -10,7 +10,9 @@ include Origami
 require 'console.rb'
 require 'readline'
 
-DEFAULT_BANNER = "Welcome to the PDF shell (Origami release #{Origami::VERSION})\n\n"
+OPENSSL_SUPPORT = (defined?(OpenSSL).nil?) ? 'no' : 'yes'
+JAVASCRIPT_SUPPORT = (defined?(PDF::JavaScript::Engine).nil?) ? 'no' : 'yes'
+DEFAULT_BANNER = "Welcome to the PDF shell (Origami release #{Origami::VERSION}) [OpenSSL: #{OPENSSL_SUPPORT}, JavaScript: #{JAVASCRIPT_SUPPORT}]\n\n"
 
 def set_completion
 

data/origami/encryption.rb

@@ -58,7 +58,7 @@ module Origami
       end
      
       encrypt_dict = get_doc_attr(:Encrypt)
-      handler = Encryption::Standard::Dictionary.new(encrypt_dict.copy)
+      handler = Encryption::Standard::Dictionary.new(encrypt_dict.dup)
 
       unless handler.Filter == :Standard
         raise EncryptionNotSupportedError, "Unknown security handler : '#{handler.Filter.to_s}'"

data/origami/javascript.rb

@@ -26,110 +26,304 @@
 module Origami
 
   class PDF
-    begin
-      require 'johnson'
-      
-      class JavaScriptEngine < Johnson::SpiderMonkey::Runtime
-        
-        class DocumentObject
-          attr_reader :author, :creator, :creationDate, :keywords, :modDate, :producer, :subject, :title
-
-          def initialize(pdf)
-            @pdf = pdf
-          
-            @author   = @pdf.author || ''
-            @creator  = @pdf.creator || ''
-            @keywords = @pdf.keywords || ''
-            @producer = @pdf.producer || ''
-            @subject  = @pdf.subject || ''
-          end
+  
+    module JavaScript
+
+      module Platforms
+        WINDOWS = "WIN"
+        UNIX = "UNIX"
+        MAC = "MAC"
+      end
+
+      module Viewers
+        ADOBE_READER = "Reader"
+      end
+
+      class AcrobatObject
+        #def to_s
+        #  "[object #{self.class.to_s.split('::').last}]"
+        #end
+      end
+
+      class Doc < AcrobatObject
+        attr_reader :info
+        attr_accessor :disclosed
+        attr_reader :hidden
 
-          def to_s
-            "[object Doc]"
+        class Info < AcrobatObject
+          def initialize(doc)
+            @doc = doc
+          end 
+
+          def title; @doc.title.to_s end
+          def author; @doc.author.to_s end
+          def subject; @doc.subject.to_s end
+          def keywords; @doc.keywords.to_s end
+          def creator; @doc.creator.to_s end
+          def creationDate; @doc.creation_date.to_s end
+          def modDate; @doc.mod_date.to_s end
+        end
+
+        def initialize(pdf)
+          @pdf = pdf
+          @disclosed = false
+          @hidden = false
+          @info = Info.new(pdf)
+        end
+
+        def numFields
+          fields = @pdf.fields
+          if fields.nil?
+            0
+          else
+            fields.size
           end
         end
 
-        class ApplicationObject
-          DEFAULT_VIEWER_VERSION = 9
+        def numPages; @pdf.pages.size end
 
-          attr_reader :viewerVersion
-          attr_reader :viewerVariation
+        def title; @info.title end
+        def author; @info.author end
+        def subject; @info.subject end
+        def keywords; @info.keywords end
+        def creator; @info.creator end
+        def creationDate; @info.creationDate end
+        def modDate; @info.modDate end
 
-          def initialize
-            @viewerVersion = DEFAULT_VIEWER_VERSION
-            @viewerVariation = @viewerType = "Reader"
-          end
+        def metadata
+          meta = @pdf.Catalog.Metadata
 
-          def to_s
-            "[object App]"
-          end
+          (meta.data if meta.is_a?(Stream)).to_s
         end
 
-        class ConsoleObject
-          def println(msg)
-            puts msg.to_s
+        def filesize; @pdf.original_filesize end
+        def path; @pdf.original_filename end
+        def documentFileName; File.basename(self.path) end   
+        def URL; "file://#{self.path}" end
+        def baseURL; '' end
+
+        def dataObjects
+          data_objs = []
+          @pdf.ls_names(Names::Root::EMBEDDEDFILES).each do |name, file_desc|
+            if file_desc
+              ef = file_desc[:EF].solve
+              if ef
+                f = ef[:F].solve
+                data_objs.push Data.new(name, f.data.size) if f.is_a?(Stream)
+              end
+            end
+
           end
+        
+          data_objs
+        end
 
-          def show; end
-          def clear; end
-          def hide; end
+        def getDataObject(cName)
+          file_desc = @pdf.resolve_name(Names::Root::EMBEDDEDFILES, cName)
 
-          def to_s
-            "[object Console]"
+          if file_desc
+            ef = file_desc[:EF].solve
+            if ef
+              f = ef[:F].solve
+              Data.new(cName, f.data.size) if f.is_a?(Stream)
+            end
           end
         end
 
-        class UtilObject
-          def to_s
-            "[object Util]"
+        def getDataObjectContents(cName, bAllowAuth = false)
+          file_desc = @pdf.resolve_name(Names::Root::EMBEDDEDFILES, cName)
+
+          if file_desc
+            ef = file_desc[:EF].solve
+            if ef
+              f = ef[:F].solve
+              ReadStream.new(f.data) if f.is_a?(Stream)
+            end
           end
         end
 
-        def initialize(pdf, options = {})
-          super()
-          
-          self['app'] = ApplicationObject.new
-          if options.has_key?(:viewerVersion)
-            self['app'].instance_variable_set :@viewerVersion, options[:viewerVersion]
+        def getField(cName)
+          field = @pdf.get_field(cName)
+
+          Field.new(field) if field
+        end
+
+        def getNthFieldName(nIndex)
+          fields = @pdf.fields
+
+          (Field.new(fields[nIndex]).name if fields and fields[nIndex]).to_s
+        end
+      end
+
+      class App < AcrobatObject
+        attr_reader :platform, :viewerVariation, :viewerVersion
+
+        def initialize(platform, viewerVariation, viewerVersion)
+          @platform = platform
+          @viewerVariation, @viewerVersion = viewerVariation, viewerVersion
+        end
+
+        def response(params)
+          puts params.class
+          gets
+        end
+      end
+
+      class Console < AcrobatObject
+        def initialize(output = STDOUT)
+          @output = output
+        end
+
+        def println(msg)
+          @output.puts msg
+        end
+      end
+
+      class Util < AcrobatObject
+        def streamFromString(cString, cCharset = 'utf-8')
+          ReadStream.new(cString.to_s)
+        end
+
+        def stringFromStream(oStream, cCharset = 'utf-8')
+          if oStream.is_a?(ReadStream)
+            oStream.instance_variable_get(:@data).dup
           end
+        end
+      end
 
-          self['console'] = ConsoleObject.new
-          self['util'] = UtilObject.new
+      class Field < AcrobatObject
+        def initialize(field)
+          @field = field
+        end
 
-          # Johnson includes the Ruby namespace in the global scope.
-          # Unsets that for obvious security reasons.
-          self['Ruby'] = nil
+        def doc; Doc.new(@field.pdf) end
+        def name
+          (@field[:T].solve.value if @field.has_key?(:T)).to_s
+        end
+        
+        def value
+          @field[:V].solve.value if @field.has_key?(:V)
+        end
 
-          # Hack the 'this' object to point to the DocumentObject
-          @doc_obj = self['doc'] = DocumentObject.new(pdf)
-          evaluate('this.doc.eval = function(script) {eval(script)}')
-          evaluate('this.doc = undefined')
+        def valueAsString
+          self.value.to_s
         end
 
-        def exec(script)
-          @doc_obj.eval(script)
+        def type
+          (if @field.has_key?(:FT)
+            case @field[:FT].solve.value
+              when PDF::Field::Type::BUTTON
+                if @fields.has_key?(:Ff)
+                  flags = @fields[:Ff].solve.value
+
+                  if (flags & Origami::Annotation::Widget::Button::Flags::PUSHBUTTON) != 0
+                    'button'
+                  elsif (flags & Origami::Annotation::Widget::Button::Flags::RADIO) != 0
+                    'radiobox'
+                  else
+                    'checkbox'
+                  end
+                end
+              when PDF::Field::Type::TEXT then 'text'
+              when PDF::Field::Type::SIGNATURE then 'signature'
+              when PDF::Field::Type::CHOICE
+                if @field.has_key?(:Ff)
+                  if (@field[:Ff].solve.value & Origami::Annotation::Widget::Choice::Flags::COMBO).zero?
+                    'listbox'
+                  else
+                    'combobox'
+                  end
+                end
+            end
+          end).to_s
         end
 
       end
 
+      class Data < AcrobatObject
+        attr_reader :name, :path, :size
+        attr_reader :creationDate, :modDate
+        attr_reader :description, :MIMEType
+
+        def initialize(name, size, path = nil, creationDate = nil, modDate = nil, description = nil, mimeType = nil)
+          @name, @path, @size = name, path, size
+          @creationDate, @modDate = creationDate, modDate
+          @description, @MIMEType = description, mimeType
+        end
+      end
+
+      class ReadStream < AcrobatObject
+        def initialize(data)
+          @data = data
+        end
+
+        def read(n)
+          @data.slice!(0, n)
+        end
+      end
+    end
+
+    begin
+      require 'v8'
+
+      class JavaScript::Engine
+
+        attr_reader :context
+
+        def initialize(pdf, params = {})
+          options = 
+          {
+            :viewerVersion => JavaScript::Platforms::WINDOWS, 
+            :viewerVariation => JavaScript::Viewers::ADOBE_READER, 
+            :platform => 9
+          }.update(params)
+
+          doc = JavaScript::Doc.new(pdf)
+          app = JavaScript::App.new(options[:platform], options[:viewerVariation], options[:viewerVersion])
+          util = JavaScript::Util.new
+          console = JavaScript::Console.new
+
+          @context = V8::Context.new(:with => doc)
+          @context['app'] = app
+          @context['console'] = console
+          @context['util'] = util
+        end
+
+        def exec(script)
+          @context.eval(script)
+        end
+      end
+
     rescue LoadError
     end
   end
 
-  if defined?(PDF::JavaScriptEngine)
+  if defined?(PDF::JavaScript::Engine)
     module String
       def eval_as_js(options = {})
-        runtime = options[:runtime] || PDF::JavaScriptEngine.new(self.pdf, options)
+        runtime = options[:runtime] || PDF::JavaScript::Engine.new(self.pdf, options)
         runtime.exec(self.value)
       end
     end
 
     class Stream
       def eval_as_js(options = {})
-        runtime = options[:runtime] || PDF::JavaScriptEngine.new(self.pdf, options)
+        runtime = options[:runtime] || PDF::JavaScript::Engine.new(self.pdf, options)
         runtime.exec(self.data)
       end
     end
+
+    class PDF
+      def eval_js(code)
+        get_js_engine.exec(code) 
+      end
+
+      private
+
+      def get_js_engine(options = {})
+        @js_engine ||= PDF::JavaScript::Engine.new(self, options)
+      end
+    end
   end
     
 end

data/origami/linearization.rb

@@ -27,6 +27,9 @@ module Origami
 
   class PDF
 
+    class LinearizationError < Exception #:nodoc:
+    end
+
     #
     # Returns whether the current document is linearized.
     #
@@ -45,7 +48,7 @@ module Origami
     # This operation is xrefs destructive, should be fixed in the future to merge tables.
     #
     def delinearize!
-      raise RuntimeError, 'Not a linearized document' unless is_linearized?
+      raise LinearizationError, 'Not a linearized document' unless is_linearized?
       
       #
       # Saves the first trailer.
@@ -70,6 +73,27 @@ module Origami
         end
       end
 
+      #
+      # Update the trailer.
+      #
+      last_trailer = (@revisions.last.trailer ||= Trailer.new)
+
+      last_trailer.dictionary ||= Dictionary.new
+       
+      if prev_trailer.has_dictionary?
+        last_trailer.dictionary =
+          last_trailer.dictionary.merge(prev_trailer.dictionary)
+      else
+        xrefstm = get_object_by_offset(last_trailer.startxref)
+        raise LinearizationError, 
+          'Cannot find trailer info while delinearizing document' unless xrefstm.is_a?(XRefStream)
+
+        last_trailer.dictionary[:Root] = xrefstm[:Root]
+        last_trailer.dictionary[:Encrypt] = xrefstm[:Encrypt]
+        last_trailer.dictionary[:Info] = xrefstm[:Info]
+        last_trailer.dictionary[:ID] = xrefstm[:ID]
+      end
+
       #
       # Remove all xrefs.
       # Fix: Should be merged instead.
@@ -81,15 +105,6 @@ module Origami
       #
       remove_revision(0)
 
-      #
-      # Update the trailer.
-      #
-      last_trailer = (@revisions.last.trailer ||= Trailer.new)
-
-      last_trailer.dictionary ||= Dictionary.new
-      last_trailer.dictionary =
-        last_trailer.dictionary.merge(prev_trailer.dictionary)
-
       self
     end
 

data/origami/parser.rb

@@ -155,6 +155,7 @@ module Origami
           StringScanner.new(stream.read)
         end
       elsif stream.is_a? ::String
+        @filename = stream
         if ''.respond_to? :force_encoding
           StringScanner.new(File.open(stream, "r", :encoding => 'binary').binmode.read)
         else
@@ -246,6 +247,18 @@ module Origami
       end
     end
 
+    def target_filename
+      @filename
+    end
+
+    def target_filesize
+      @data.string.size if @data
+    end
+
+    def target_data
+      @data.string.dup if @data
+    end
+
     private
  
     def error(str = "") #:nodoc:

data/origami/parsers/pdf/linear.rb

@@ -39,7 +39,7 @@ module Origami
           @data.pos = @data.pos - 5
         end
 
-        pdf = PDF.new(false)
+        pdf = PDF.new(self)
 
         info "...Reading header..."
         begin

data/origami/pdf.rb

@@ -57,8 +57,8 @@ require 'origami/xfa'
 
 module Origami
 
-  VERSION   = "1.1.1"
-  REVISION  = "$Revision: rev 117/, 2011/09/14 15:24:40 darko $" #:nodoc:
+  VERSION   = "1.1.2"
+  REVISION  = "$Revision: rev 122/, 2011/09/26 12:12:39 darko $" #:nodoc:
   
   #
   # Global options for Origami.
@@ -206,28 +206,56 @@ module Origami
     
     #
     # Creates a new PDF instance.
-    # _init_structure_:: If this flag is set, then some structures will be automatically generated while manipulating this PDF. Set it if you are creating a new PDF file, this _must_ _not_ be used when parsing an existing file.
+    # _parser_:: The Parser object creating the document. If none is specified, some default structures are automatically created to get a minimal working document. 
     #
-    def initialize(init_structure = true)
+    def initialize(parser = nil)
       @header = PDF::Header.new
       @revisions = []
       
       add_new_revision
       @revisions.first.trailer = Trailer.new
 
-      init if init_structure
+      if parser
+        @parser = parser
+      else
+        init
+      end
     end
     
+    #
+    # Original file name if parsed from disk, nil otherwise.
+    #
+    def original_filename
+      @parser.target_filename if @parser
+    end
+
+    #
+    # Original file size if parsed from a data stream, nil otherwise.
+    #
+    def original_filesize
+      @parser.target_filesize if @parser
+    end
+
+    #
+    # Original data parsed to create this document, nil if created from scratch.
+    #
+    def original_data
+      @parser.target_data if @parser
+    end
    
     #
-    # Serializes the current PDF
+    # Serializes the current PDF.
     #
     def serialize(filename)
-        Zlib::GzipWriter.open(filename) { |gz|
-          gz.write Marshal.dump(self)
-        }
-        
-        self
+      parser = @parser
+      @parser = nil # do not serialize the parser
+
+      Zlib::GzipWriter.open(filename) { |gz|
+        gz.write Marshal.dump(self)
+      }
+      
+      @parser = parser
+      self
     end
     
     #

data/origami/stream.rb

@@ -436,7 +436,7 @@ module Origami
         obj.set_indirect(true)
       end
       
-      @data = prolog + data
+      self.data = prolog + data
       
       @dictionary[:N] = @objects.size
       @dictionary[:First] = prolog.size

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: origami
 version: !ruby/object:Gem::Version 
-  hash: 17
+  hash: 23
   prerelease: false
   segments: 
   - 1
   - 1
-  - 1
-  version: 1.1.1
+  - 2
+  version: 1.1.2
 platform: ruby
 authors: 
 - "Guillaume Delugr\xC3\xA9"
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-09-22 00:00:00 +02:00
+date: 2011-09-26 00:00:00 +02:00
 default_executable: 
 dependencies: []