pdf-reader 0.12.0.alpha → 1.0.0.beta1

data/CHANGELOG

@@ -1,3 +1,8 @@
+v1.0.0.beta1 (6th October 2011)
+- ensure inline images that contain "EI" are correctly parsed
+  (thanks Bernard Schaefer)
+- fix parsing of inline image data
+
 v0.12.0.alpha (28th August 2011)
 - small breaking changes to the page-based API - it's alpha for a reason
   - resource related methods on Page object return raw PDF objects
@@ -6,7 +11,7 @@ v0.12.0.alpha (28th August 2011)
     need to do so themselves
 - add support for RunLengthDecode filters (thanks Bernerd Schaefer)
 - add support for standard PDF encryption (thanks Evan Brunner)
-- add support for decoding stream wityh TIFF prediction
+- add support for decoding stream with TIFF prediction
 - new PDF::Reader::FormXObject class to simplify working with form XObjects
 
 v0.11.0.alpha (19th July 2011)

data/bin/pdf_callbacks

@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+
+$LOAD_PATH.unshift(File.dirname(__FILE__) + "/../lib")
+
+require 'pdf/reader'
+
+receiver = PDF::Reader::PrintReceiver.new
+
+if ARGV.empty?
+  browser = PDF::Reader.new($stdin)
+else
+  browser = PDF::Reader.new(ARGV[0])
+end
+browser.pages.each do |page|
+  puts
+  puts "********************************"
+  puts "page #{page.number}"
+  puts page.attributes.inspect
+  puts "********************************"
+  page.walk(receiver)
+end

data/examples/extract_fonts.rb

@@ -0,0 +1,76 @@
+# coding: utf-8
+
+# This demonstrates a way to extract TTF fonts from a PDF. It could be expanded
+# to support extra font formats if required. Be aware that many PDFs subset
+# fonts before they're embedded so glyphs may be missing or re-arranged.
+
+require 'pdf/reader'
+
+module ExtractFonts
+
+  class Extractor
+
+    def page(page)
+      count = 0
+
+      return count if page.fonts.nil? || page.fonts.empty?
+
+      page.fonts.each do |label, font|
+        next if complete_refs[font]
+        complete_refs[font] = true
+
+        process_font(page, font)
+
+        count += 1
+      end
+
+      count
+    end
+
+    private
+
+    def process_font(page, font)
+      font = page.objects.deref(font)
+
+      case font[:Subtype]
+      when :Type0 then
+        font[:DescendantFonts].each { |f| process_font(page, f) }
+      when :TrueType, :CIDFontType2 then
+        ExtractFonts::TTF.new(page.objects, font).save("#{font[:BaseFont]}.ttf")
+      else
+        $stderr.puts "unsupported font type #{font[:Subtype]}"
+      end
+    end
+
+    def complete_refs
+      @complete_refs ||= {}
+    end
+
+  end
+
+  class TTF
+
+    def initialize(objects, font)
+      @objects, @font = objects, font
+      @descriptor = @objects.deref(@font[:FontDescriptor])
+    end
+
+    def save(filename)
+      puts "#{filename}"
+      if @descriptor && @descriptor[:FontFile2]
+        stream = @objects.deref(@descriptor[:FontFile2])
+        File.open(filename, "wb") { |file| file.write stream.unfiltered_data }
+      else
+        $stderr.puts "- TTF font not embedded"
+      end
+    end
+  end
+end
+
+filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-unicode.pdf"
+extractor = ExtractFonts::Extractor.new
+
+PDF::Reader.open(filename) do |reader|
+  page = reader.page(1)
+  extractor.page(page)
+end

data/lib/pdf/reader/buffer.rb

@@ -209,14 +209,14 @@ class PDF::Reader
     def prepare_inline_token
       str = ""
 
-      while str[-2,2] != "EI"
+      while str !~ /\sEI$/
         chr = @io.read(1)
         break if chr.nil?
         str << chr
       end
 
-      @tokens << str[0, str.size-2].strip
-      @io.seek(-2, IO::SEEK_CUR) unless chr.nil?
+      @tokens << string_token(str[0..-3].strip)
+      @io.seek(-3, IO::SEEK_CUR) unless chr.nil?
     end
 
     # if we're currently inside a hex string, read hex nibbles until
@@ -342,5 +342,16 @@ class PDF::Reader
       @io.seek(-1, IO::SEEK_CUR) unless chr.nil?
       chr
     end
+
+    # for a handful of tokens we want to tell the parser how to convert them
+    # into higher level tokens. This methods adds a to_token() method
+    # to tokens that should remain as strings.
+    #
+    def string_token(token)
+      def token.to_token
+        to_s
+      end
+      token
+    end
   end
 end

data/lib/pdf/reader/filter.rb

@@ -48,6 +48,7 @@ class PDF::Reader
       when :DCTDecode       then @filter = nil
       when :FlateDecode     then @filter = :flate
       when :JBIG2Decode     then @filter = nil
+      when :JPXDecode       then @filter = nil
       when :LZWDecode       then @filter = :lzw
       when :RunLengthDecode then @filter = :runlength
       else
@@ -126,7 +127,11 @@ class PDF::Reader
       out = ""
 
       while pos < data.length
-        length = data.getbyte(pos)
+        if data.respond_to?(:getbyte)
+          length = data.getbyte(pos)
+        else
+          length = data[pos]
+        end
         pos += 1
 
         case

data/lib/pdf/reader/glyph_hash.rb

@@ -56,7 +56,7 @@ class PDF::Reader
         "0x#{str[3,4]}".hex
       elsif str.match(/\Au[A-F\d]{4,6}\Z/)
         "0x#{str[1,6]}".hex
-      elsif str.match(/\A[A-Za-z]\d{2,4}\Z/)
+      elsif str.match(/\A[A-Za-z]\d{1,4}\Z/)
         str[1,4].to_i
       elsif str.match(/\A[A-Za-z]{2}\d{2,4}\Z/)
         str[2,4].to_i

data/lib/pdf/reader/glyphlist.txt

@@ -1,43 +1,4 @@
-# ###################################################################################
-# Copyright (c) 1997,1998,2002,2007 Adobe Systems Incorporated
-# 
-# Permission is hereby granted, free of charge, to any person obtaining a
-# copy of this documentation file to use, copy, publish, distribute,
-# sublicense, and/or sell copies of the documentation, and to permit
-# others to do the same, provided that:
-# - No modification, editing or other alteration of this document is
-# allowed; and
-# - The above copyright notice and this permission notice shall be
-# included in all copies of the documentation.
-# 
-# Permission is hereby granted, free of charge, to any person obtaining a
-# copy of this documentation file, to create their own derivative works
-# from the content of this document to use, copy, publish, distribute,
-# sublicense, and/or sell the derivative works, and to permit others to do
-# the same, provided that the derived work is not represented as being a
-# copy or version of this document.
-# 
-# Adobe shall not be liable to any party for any loss of revenue or profit
-# or for indirect, incidental, special, consequential, or other similar
-# damages, whether based on tort (including without limitation negligence
-# or strict liability), contract or other legal or equitable grounds even
-# if Adobe has been advised or had reason to know of the possibility of
-# such damages. The Adobe materials are provided on an "AS IS" basis.
-# Adobe specifically disclaims all express, statutory, or implied
-# warranties relating to the Adobe materials, including but not limited to
-# those concerning merchantability or fitness for a particular purpose or
-# non-infringement of any third party rights regarding the Adobe
-# materials.
-# ###################################################################################
-# Name:          Adobe Glyph List
-# Table version: 2.0
-# Date:          September 20, 2002
-#
-# See http://partners.adobe.com/asn/developer/typeforum/unicodegn.html
-#
-# Format: Semicolon-delimited fields:
-#            (1) glyph name
-#            (2) Unicode scalar value
+# This file maps glyph names to unicode codepoints
 A;0041
 AE;00C6
 AEacute;01FC

data/lib/pdf/reader/lzw.rb

@@ -102,10 +102,12 @@ module PDF
               old_code = code
             end
             #increase de size of the codes when limit reached
-            case string_table.string_table_pos
-            when 511 then stream.set_bits_in_chunk(10)
-            when 1023 then stream.set_bits_in_chunk(11)
-            when 2047 then stream.set_bits_in_chunk(12)
+            if string_table.string_table_pos == 511
+              stream.set_bits_in_chunk(10)
+            elsif string_table.string_table_pos == 1023
+              stream.set_bits_in_chunk(11)
+            elsif string_table.string_table_pos == 2047
+              stream.set_bits_in_chunk(12)
             end
           end
         end

data/lib/pdf/reader/object_hash.rb

@@ -31,26 +31,15 @@ class PDF::Reader
     attr_accessor :default
     attr_reader :trailer, :pdf_version
 
-    # Creates a new ObjectHash object. input can be a string with a valid filename,
-    # a string containing a PDF file, or an IO object.
+    # Creates a new ObjectHash object. Input can be a string with a valid filename
+    # or an IO-like object.
     #
-    # valid options
+    # Valid options:
     #
     #   :password - the user password to decrypt the source PDF
     #
     def initialize(input, opts = {})
-      if input.respond_to?(:seek) && input.respond_to?(:read)
-        @io = input
-      elsif File.file?(input.to_s)
-        if File.respond_to?(:binread)
-          input = File.binread(input.to_s)
-        else
-          input = File.read(input.to_s)
-        end
-        @io = StringIO.new(input)
-      else
-        raise ArgumentError, "input must be an IO-like object or a filename"
-      end
+      @io          = extract_io_from(input)
       @pdf_version = read_version
       @xref        = PDF::Reader::XRef.new(@io)
       @trailer     = @xref.trailer
@@ -67,9 +56,7 @@ class PDF::Reader
 
     # returns true if the supplied references points to an object with a stream
     def stream?(ref)
-      self[ref].class == PDF::Reader::Stream
-    rescue
-      false
+      self.has_key?(ref) && self[ref].is_a?(PDF::Reader::Stream)
     end
 
     # Access an object from the PDF. key can be an int or a PDF::Reader::Reference
@@ -83,23 +70,23 @@ class PDF::Reader
     #
     def [](key)
       return default if key.to_i <= 0
-      begin
-        unless key.kind_of?(PDF::Reader::Reference)
-          key = PDF::Reader::Reference.new(key.to_i, 0)
-        end
-        if @cache.has_key?(key)
-          @cache[key]
-        elsif xref[key].is_a?(Fixnum)
-          buf = new_buffer(xref[key])
-          @cache[key] = decrypt(key, Parser.new(buf, self).object(key.id, key.gen))
-        elsif xref[key].is_a?(PDF::Reader::Reference)
-          container_key = xref[key]
-          object_streams[container_key] ||= PDF::Reader::ObjectStream.new(object(container_key))
-          @cache[key] = object_streams[container_key][key.id]
-        end
-      rescue InvalidObjectError
-        return default
+
+      unless key.is_a?(PDF::Reader::Reference)
+        key = PDF::Reader::Reference.new(key.to_i, 0)
+      end
+
+      if @cache.has_key?(key)
+        @cache[key]
+      elsif xref[key].is_a?(Fixnum)
+        buf = new_buffer(xref[key])
+        @cache[key] = decrypt(key, Parser.new(buf, self).object(key.id, key.gen))
+      elsif xref[key].is_a?(PDF::Reader::Reference)
+        container_key = xref[key]
+        object_streams[container_key] ||= PDF::Reader::ObjectStream.new(object(container_key))
+        @cache[key] = object_streams[container_key][key.id]
       end
+    rescue InvalidObjectError
+      return default
     end
 
     # If key is a PDF::Reader::Reference object, lookup the corresponding
@@ -315,5 +302,23 @@ class PDF::Reader
       version.to_f
     end
 
+    def extract_io_from(input)
+      if input.respond_to?(:seek) && input.respond_to?(:read)
+        input
+      elsif File.file?(input.to_s)
+        StringIO.new read_as_binary(input)
+      else
+        raise ArgumentError, "input must be an IO-like object or a filename"
+      end
+    end
+
+    def read_as_binary(input)
+      if File.respond_to?(:binread)
+        File.binread(input.to_s)
+      else
+        File.read(input.to_s)
+      end
+    end
+
   end
 end

data/lib/pdf/reader/page.rb

@@ -49,11 +49,11 @@ module PDF
       # attributes inherited from parents.
       #
       def attributes
-        hash = {}
-        page_with_ancestors.reverse.each do |obj|
-          hash.merge!(@objects.deref(obj))
-        end
-        hash
+        {}.tap { |hash|
+          page_with_ancestors.reverse.each do |obj|
+            hash.merge!(@objects.deref(obj))
+          end
+        }
       end
 
       # Returns the resources that accompany this page. Includes
@@ -185,7 +185,7 @@ module PDF
         raise MalformedPDFError, "End Of File while processing a content stream"
       end
 
-      # calls the name callback method on the receiver class with params as the arguments
+      # calls the name callback method on each receiver object with params as the arguments
       #
       def callback (receivers, name, params=[])
         receivers.each do |receiver|
@@ -193,14 +193,16 @@ module PDF
         end
       end
 
-      def page_with_ancestors(obj = nil)
-        obj = objects.deref(obj)
-        if obj.nil?
-          [@page_object] + page_with_ancestors(@page_object[:Parent])
-        elsif obj[:Parent]
-          [select_inheritable(obj)] + page_with_ancestors(obj[:Parent])
+      def page_with_ancestors
+        [ @page_object ] + ancestors
+      end
+
+      def ancestors(origin = @page_object[:Parent])
+        if origin.nil?
+          []
         else
-          [select_inheritable(obj)]
+          obj = objects.deref(origin)
+          [ select_inheritable(obj) ] + ancestors(obj[:Parent])
         end
       end
 

data/lib/pdf/reader/page_text_receiver.rb

@@ -3,6 +3,11 @@
 require 'matrix'
 require 'yaml'
 
+begin
+  require 'psych'
+rescue LoadError
+end
+
 module PDF
   class Reader
     class PageTextReceiver
@@ -26,7 +31,7 @@ module PDF
         @objects = page.objects
         @fonts   = build_fonts(page.fonts)
         @form_fonts = {}
-        @content = ::Hash.new
+        @content = {}
         @stack   = [DEFAULT_GRAPHICS_STATE]
       end
 
@@ -126,10 +131,10 @@ module PDF
 
       def move_text_position(x, y) # Td
         temp_matrix = Matrix[
-                        [1, 0, 0],
-                        [0, 1, 0],
-                        [x, y, 1]
-                      ]
+          [1, 0, 0],
+          [0, 1, 0],
+          [x, y, 1]
+        ]
         @text_matrix = @text_line_matrix = temp_matrix * @text_line_matrix
       end
 
@@ -140,14 +145,14 @@ module PDF
 
       def set_text_matrix_and_text_line_matrix(a, b, c, d, e, f) # Tm
         @text_matrix = @text_line_matrix = Matrix[
-                              [a, b, 0],
-                              [c, d, 0],
-                              [e, f, 1]
-                            ]
+          [a, b, 0],
+          [c, d, 0],
+          [e, f, 1]
+        ]
       end
 
       def move_to_start_of_next_line # T*
-        move_text_position(0, state[:text_leading])
+        move_text_position(0, -state[:text_leading])
       end
 
       #####################################################
@@ -209,9 +214,11 @@ module PDF
       # wrap the raw PDF Font objects in handy ruby Font objects.
       #
       def build_fonts(raw_fonts)
-        ::Hash[raw_fonts.map { |label, font|
+        wrapped_fonts = raw_fonts.map { |label, font|
           [label, PDF::Reader::Font.new(@objects, @objects.deref(font))]
-        }]
+        }
+
+        ::Hash[wrapped_fonts]
       end
 
       # transform x and y co-ordinates from the current text space to the
@@ -219,10 +226,8 @@ module PDF
       #
       def transform(point, z = 1)
         trm = text_rendering_matrix
-        Point.new(
-          (trm[0,0] * point.x) + (trm[1,0] * point.y) + (trm[2,0] * z),
-          (trm[0,1] * point.x) + (trm[1,1] * point.y) + (trm[2,1] * z)
-        )
+
+        point.transform(text_rendering_matrix, z)
       end
 
       def text_rendering_matrix
@@ -253,11 +258,14 @@ module PDF
         if @stack.empty?
           {}
         else
-          yaml_state = YAML.dump(@stack.last)
-          YAML.load(yaml_state)
+          yaml_lib.load yaml_lib.dump(@stack.last)
         end
       end
 
+      def yaml_lib
+        Kernel.const_defined?("Psych") ? Psych : YAML
+      end
+
       # return the current transformation matrix
       #
       def ctm
@@ -271,15 +279,16 @@ module PDF
       # private class for representing points on a cartesian plain. Used
       # to simplify maths in the MinPpi class.
       #
-      class Point
-        attr_reader :x, :y
-
-        def initialize(x,y)
-          @x, @y = x,y
+      class Point < Struct.new(:x, :y)
+        def transform(trm, z)
+          Point.new(
+            (trm[0,0] * x) + (trm[1,0] * y) + (trm[2,0] * z),
+            (trm[0,1] * x) + (trm[1,1] * y) + (trm[2,1] * z)
+          )
         end
 
         def distance(point)
-          Math.hypot(point.x - x, point.y - y)
+          Math.hypot(point.x - @x, point.y - @y)
         end
       end
     end

data/lib/pdf/reader/parser.rb

@@ -32,10 +32,10 @@ class PDF::Reader
     # Create a new parser around a PDF::Reader::Buffer object
     #
     # buffer - a PDF::Reader::Buffer object that contains PDF data
-    # ohash  - a PDF::Reader::ObjectHash object that can return objects from the PDF file
-    def initialize (buffer, ohash=nil)
+    # objects  - a PDF::Reader::ObjectHash object that can return objects from the PDF file
+    def initialize (buffer, objects=nil)
       @buffer = buffer
-      @ohash  = ohash
+      @objects  = objects
     end
     ################################################################################
     # Reads the next token from the underlying buffer and convets it to an appropriate
@@ -59,7 +59,8 @@ class PDF::Reader
       when "stream", "endstream"       then return Token.new(token)
       when ">>", "]", ">", ")"         then return Token.new(token)
       else
-        if operators.has_key?(token)   then return Token.new(token)
+        if token.respond_to?(:to_token) then return token.to_token
+        elsif operators.has_key?(token)   then return Token.new(token)
         elsif token =~ /\d*\.\d/       then return token.to_f
         else                           return token.to_i
         end
@@ -206,8 +207,8 @@ class PDF::Reader
     # Decodes the contents of a PDF Stream and returns it as a Ruby String.
     def stream (dict)
       raise MalformedPDFError, "PDF malformed, missing stream length" unless dict.has_key?(:Length)
-      if @ohash
-        length = @ohash.object(dict[:Length])
+      if @objects
+        length = @objects.deref(dict[:Length])
       else
         length = dict[:Length] || 0
       end

data/lib/pdf/reader/standard_security_handler.rb

@@ -87,7 +87,7 @@ class PDF::Reader
 
     # Pads supplied password to 32bytes using PassPadBytes as specified on
     # pp61 of spec
-    def padPass(p="")
+    def pad_pass(p="")
       if p.nil? || p.empty?
         PassPadBytes.pack('C*')
       else
@@ -95,7 +95,7 @@ class PDF::Reader
       end
     end
 
-    def xorEachByte(buf, int)
+    def xor_each_byte(buf, int)
       buf.each_byte.map{ |b| b^int}.pack("C*")
     end
 
@@ -111,20 +111,20 @@ class PDF::Reader
     # if the supplied password is not a valid owner password for this document
     # then it returns nil
     #
-    def authOwnerPass(pass)
-      md5 = Digest::MD5.digest(padPass(pass))
+    def auth_owner_pass(pass)
+      md5 = Digest::MD5.digest(pad_pass(pass))
       if @revision > 2 then
         50.times { md5 = Digest::MD5.digest(md5) }
         keyBegins = md5[(0...@key_length)]
         #first itteration decrypt owner_key
         out = @owner_key
         #RC4 keyed with (keyBegins XOR with itteration #) to decrypt previous out
-        19.downto(0).each { |i| out=RC4.new(xorEachByte(keyBegins,i)).decrypt(out) }
+        19.downto(0).each { |i| out=RC4.new(xor_each_byte(keyBegins,i)).decrypt(out) }
       else
         out = RC4.new( md5[(0...5)] ).decrypt( @owner_key )
       end
       # c) check output as user password
-      authUserPass( out )
+      auth_user_pass( out )
     end
 
     # Algorithm 6 - Authenticating the User Password
@@ -137,22 +137,22 @@ class PDF::Reader
     # if the supplied password is not a valid user password for this document
     # then it returns nil
     #
-    def authUserPass(pass)
-      keyBegins = makeFileKey(pass)
+    def auth_user_pass(pass)
+      keyBegins = make_file_key(pass)
       if @revision > 2
         #initialize out for first iteration
         out = Digest::MD5.digest(PassPadBytes.pack("C*") + @file_id)
         #zero doesn't matter -> so from 0-19
-        20.times{ |i| out=RC4.new(xorEachByte(keyBegins, i)).decrypt(out) }
+        20.times{ |i| out=RC4.new(xor_each_byte(keyBegins, i)).decrypt(out) }
       else
         out = RC4.new(keyBegins).encrypt(PassPadBytes.pack("C*"))
       end
       @user_key[(0...16)] == out ? keyBegins : nil
     end
 
-    def makeFileKey( user_pass )
+    def make_file_key( user_pass )
       # a) if there's a password, pad it to 32 bytes, else, just use the padding.
-      @buf  = padPass(user_pass)
+      @buf  = pad_pass(user_pass)
       # c) add owner key
       @buf << @owner_key
       # d) add permissions 1 byte at a time, in little-endian order
@@ -176,8 +176,8 @@ class PDF::Reader
     end
 
     def build_standard_key(pass)
-      encrypt_key   = authOwnerPass(pass)
-      encrypt_key ||= authUserPass(pass)
+      encrypt_key   = auth_owner_pass(pass)
+      encrypt_key ||= auth_user_pass(pass)
 
       raise PDF::Reader::EncryptedPDFError, "Invalid password (#{pass})" if encrypt_key.nil?
       encrypt_key

metadata

@@ -3,11 +3,11 @@ name: pdf-reader
 version: !ruby/object:Gem::Version 
   prerelease: true
   segments: 
+  - 1
   - 0
-  - 12
   - 0
-  - alpha
-  version: 0.12.0.alpha
+  - beta1
+  version: 1.0.0.beta1
 platform: ruby
 authors: 
 - James Healy
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-08-28 00:00:00 +10:00
+date: 2011-10-06 00:00:00 +11:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -108,6 +108,7 @@ executables:
 - pdf_object
 - pdf_text
 - pdf_list_callbacks
+- pdf_callbacks
 extensions: []
 
 extra_rdoc_files: 
@@ -116,51 +117,52 @@ extra_rdoc_files:
 - CHANGELOG
 - MIT-LICENSE
 files: 
-- examples/rspec.rb
 - examples/metadata.rb
+- examples/extract_images.rb
 - examples/extract_bates.rb
-- examples/hash.rb
 - examples/callbacks.rb
+- examples/rspec.rb
+- examples/hash.rb
 - examples/text.rb
-- examples/version.rb
+- examples/extract_fonts.rb
 - examples/page_count.rb
-- examples/extract_images.rb
-- lib/pdf/reader/glyphlist.txt
-- lib/pdf/reader/error.rb
-- lib/pdf/reader/glyph_hash.rb
-- lib/pdf/reader/font.rb
-- lib/pdf/reader/lzw.rb
+- examples/version.rb
+- lib/pdf/reader.rb
+- lib/pdf/hash.rb
 - lib/pdf/reader/print_receiver.rb
-- lib/pdf/reader/reference.rb
+- lib/pdf/reader/xref.rb
+- lib/pdf/reader/buffer.rb
+- lib/pdf/reader/font.rb
+- lib/pdf/reader/parser.rb
+- lib/pdf/reader/error.rb
 - lib/pdf/reader/filter.rb
-- lib/pdf/reader/text_receiver.rb
+- lib/pdf/reader/object_hash.rb
+- lib/pdf/reader/stream.rb
 - lib/pdf/reader/standard_security_handler.rb
-- lib/pdf/reader/pages_strategy.rb
+- lib/pdf/reader/cmap.rb
 - lib/pdf/reader/form_xobject.rb
-- lib/pdf/reader/abstract_strategy.rb
-- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/object_cache.rb
+- lib/pdf/reader/object_stream.rb
 - lib/pdf/reader/encoding.rb
-- lib/pdf/reader/stream.rb
+- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/text_receiver.rb
+- lib/pdf/reader/glyph_hash.rb
+- lib/pdf/reader/glyphlist.txt
+- lib/pdf/reader/lzw.rb
 - lib/pdf/reader/register_receiver.rb
-- lib/pdf/reader/object_hash.rb
-- lib/pdf/reader/object_cache.rb
-- lib/pdf/reader/token.rb
 - lib/pdf/reader/page.rb
-- lib/pdf/reader/xref.rb
-- lib/pdf/reader/cmap.rb
-- lib/pdf/reader/object_stream.rb
-- lib/pdf/reader/metadata_strategy.rb
-- lib/pdf/reader/buffer.rb
-- lib/pdf/reader/encodings/zapf_dingbats.txt
+- lib/pdf/reader/abstract_strategy.rb
+- lib/pdf/reader/pages_strategy.rb
+- lib/pdf/reader/reference.rb
 - lib/pdf/reader/encodings/standard.txt
 - lib/pdf/reader/encodings/mac_roman.txt
-- lib/pdf/reader/encodings/mac_expert.txt
-- lib/pdf/reader/encodings/win_ansi.txt
 - lib/pdf/reader/encodings/symbol.txt
+- lib/pdf/reader/encodings/win_ansi.txt
+- lib/pdf/reader/encodings/zapf_dingbats.txt
 - lib/pdf/reader/encodings/pdf_doc.txt
-- lib/pdf/reader/parser.rb
-- lib/pdf/hash.rb
-- lib/pdf/reader.rb
+- lib/pdf/reader/encodings/mac_expert.txt
+- lib/pdf/reader/metadata_strategy.rb
+- lib/pdf/reader/token.rb
 - lib/pdf-reader.rb
 - Rakefile
 - README.rdoc
@@ -170,11 +172,12 @@ files:
 - bin/pdf_object
 - bin/pdf_text
 - bin/pdf_list_callbacks
+- bin/pdf_callbacks
 has_rdoc: true
 homepage: http://github.com/yob/pdf-reader
 licenses: []
 
-post_install_message: "\n  ********************************************\n\n  This is an alpha release of PDF::Reader to gather feedback on the proposed\n  API changes.\n\n  The old API is marked as deprecated but will continue to work with no\n  visible warnings for now.\n\n  The new API is documented in the README and in rdoc for the PDF::Reader,\n  PDF::Reader::Page and PDF::Reader::ObjectHash classes.\n\n  Do not use this in production, stick to stable releases for that. If you do\n  take the new API for a spin, please send any feedback my way.\n\n  ********************************************\n\n"
+post_install_message: "\n  ********************************************\n\n  This is a beta release of PDF::Reader to gather feedback on the proposed\n  API changes.\n\n  The old API is marked as deprecated but will continue to work with no\n  visible warnings for now.\n\n  The new API is documented in the README and in rdoc for the PDF::Reader,\n  PDF::Reader::Page and PDF::Reader::ObjectHash classes.\n\n  Do not use this in production, stick to stable releases for that. If you do\n  take the new API for a spin, please send any feedback my way.\n\n  ********************************************\n\n"
 rdoc_options: 
 - --title
 - PDF::Reader Documentation