pdf-reader 0.7.2 → 0.7.3

data/lib/pdf/reader/encodings/win_ansi.txt

@@ -0,0 +1,29 @@
+# A mapping of WinAnsi (win-1252) characters to unicode. Anything
+# not specified is left unchanged
+80;20AC
+82;201A
+83;0192
+84;201E
+85;2026
+86;2020
+87;2021
+88;02C6
+89;2030
+8A;0160
+8B;2039
+8C;0152
+8E;017D
+91;2018
+92;2019
+93;201C
+94;201D
+95;2022
+96;2013
+97;2014
+98;02DC
+99;2122
+9A;0161
+9B;203A
+9C;0152
+9E;017E
+9F;0178

data/lib/pdf/reader/encodings/zapf_dingbats.txt

@@ -0,0 +1,201 @@
+21;2701
+22;2702
+23;2703
+24;2704
+25;260E
+26;2706
+27;2707
+28;2708
+29;2709
+2A;261B
+2B;261E
+2C;270C
+2D;270D
+2E;270E
+2F;270F
+30;2710
+31;2711
+32;2712
+33;2713
+34;2714
+35;2715
+36;2716
+37;2717
+38;2718
+39;2719
+3A;271A
+3B;271B
+3C;271C
+3D;271D
+3E;271E
+3F;271E
+40;2720
+41;2721
+42;2722
+43;2723
+44;2724
+45;2725
+46;2726
+47;2727
+48;2605
+49;2729
+4A;272A
+4B;272B
+4C;272C
+4D;272D
+4E;272E
+4F;272F
+50;2730
+51;2731
+52;2732
+53;2733
+54;2734
+55;2735
+56;2736
+57;2737
+58;2738
+59;2739
+5A;273A
+5B;273B
+5C;273C
+5D;273D
+5E;273E
+5F;273F
+60;2740
+61;2741
+62;2742
+63;2743
+64;2744
+65;2745
+66;2746
+67;2747
+68;2748
+69;2749
+6A;274A
+6B;274B
+6C;25CF
+6D;274D
+6E;25A0
+6F;274F
+70;2750
+71;2751
+72;2752
+73;2753
+74;2754
+75;2755
+76;2756
+77;2757
+78;2758
+79;2759
+7A;275A
+7B;275B
+7C;275C
+7D;275D
+7E;275E
+80;F8D7
+81;F8D8
+82;F8D9
+83;F8DA
+84;F8DB
+85;F8DC
+86;F8DD
+87;F8DE
+88;F8DF
+89;F8E0
+8A;F8E1
+8B;F8E2
+8C;F8E3
+8D;F8E4
+A1;2761
+A2;2762
+A3;2763
+A4;2764
+A5;2765
+A6;2766
+A7;2767
+A8;2663
+A9;2666
+AA;2665
+AB;2660
+AC;2460
+AD;2461
+AE;2462
+AF;2463
+B0;2464
+B1;2465
+B2;2466
+B3;2467
+B4;2468
+B5;2469
+B6;2776
+B7;2777
+B8;2778
+B9;2779
+BA;277A
+BB;277B
+BC;277C
+BD;277D
+BE;277E
+BF;277F
+C0;2780
+C1;2781
+C2;2782
+C3;2783
+C4;2784
+C5;2785
+C6;2786
+C7;2787
+C8;2788
+C9;2789
+CA;278A
+CB;278B
+CC;278C
+CD;278D
+CE;278E
+CF;278F
+D0;2790
+D1;2791
+D2;2792
+D3;2793
+D4;2794
+D5;2795
+D6;2796
+D7;2797
+D8;2798
+D9;2799
+DA;279A
+DB;279B
+DC;279C
+DD;279D
+DE;279E
+DF;279F
+E0;27A0
+E1;27A1
+E2;27A2
+E3;27A3
+E4;27A4
+E5;27A5
+E6;27A6
+E7;27A7
+E8;27A8
+E9;27A9
+EA;27AA
+EB;27AB
+EC;27AC
+ED;27AD
+EE;27AE
+EF;27AF
+F1;27B1
+F2;27B2
+F3;27B3
+F4;27B4
+F5;27B5
+F6;27B6
+F7;27B7
+F8;27B8
+F9;27B9
+FA;27BA
+FB;27BB
+FC;27BC
+FD;27BD
+FE;27BE

data/lib/pdf/reader/error.rb

@@ -48,6 +48,7 @@ class PDF::Reader
   end
   ################################################################################
   class MalformedPDFError < RuntimeError; end
+  class InvalidObjectError < MalformedPDFError; end
   class UnsupportedFeatureError < RuntimeError; end
 end
 ################################################################################

data/lib/pdf/reader/font.rb

@@ -52,10 +52,11 @@ class PDF::Reader
       # with encoding= if required
       case font
       when "Symbol" then 
-        self.encoding = PDF::Reader::Encoding.factory("SymbolEncoding")
+        self.encoding = PDF::Reader::Encoding.new("SymbolEncoding")
       when "ZapfDingbats" then 
-        self.encoding = PDF::Reader::Encoding.factory("ZapfDingbatsEncoding")
+        self.encoding = PDF::Reader::Encoding.new("ZapfDingbatsEncoding")
       end
+      @basefont = font
     end
 
     def to_utf8(params)
@@ -65,7 +66,7 @@ class PDF::Reader
         # translate the bytestram into a UTF-8 string.
         # If an encoding hasn't been specified, assume the text using this 
         # font is in Adobe Standard Encoding.
-        (encoding || PDF::Reader::Encoding::StandardEncoding.new).to_utf8(params, tounicode)
+        (encoding || PDF::Reader::Encoding.new(:StandardEncoding)).to_utf8(params, tounicode)
       elsif params.class == Array
         params.collect { |param| self.to_utf8(param) }
       else

data/lib/pdf/reader/parser.rb

@@ -47,6 +47,7 @@ class PDF::Reader
       token = @buffer.token
 
       case token
+      when nil                        then return nil
       when "/"                        then return @buffer.token.to_sym
       when "<<"                       then return dictionary()
       when "["                        then return array()

data/lib/pdf/reader/print_receiver.rb

@@ -0,0 +1,19 @@
+class PDF::Reader
+  class PrintReceiver
+
+    attr_accessor :callbacks
+
+    def initialize
+      @callbacks = []
+    end
+
+    def respond_to?(meth)
+      return false if [:begin_inline_image_data].include?(meth)
+      true
+    end
+
+    def method_missing(methodname, *args)
+      puts "#{methodname} => #{args.inspect}"
+    end
+  end
+end

data/lib/pdf/reader/xref.rb

@@ -37,6 +37,16 @@ class PDF::Reader
       @xref = {}
     end
     ################################################################################
+    # returns the PDF version of the current document. Technically this isn't part of the XRef
+    # table, but it is one of the lowest level data items in the file, so we've lumped it in
+    # with the cross reference code.
+    def pdf_version
+      @buffer.seek(0)
+      m, version = *@buffer.read(8).match(/%PDF-(\d.\d)/)
+      raise MalformedPDFError, 'invalid PDF version' if version.nil?
+      return version.to_f
+    end
+    ################################################################################
     # Read the xref table from the underlying buffer. If offset is specified the table
     # will be loaded from there, otherwise the default offset will be located and used.
     #
@@ -122,6 +132,8 @@ class PDF::Reader
     # ref - a PDF::Reader::Reference object containing an object ID and revision number
     def offset_for (ref)
       @xref[ref.id][ref.gen]
+    rescue 
+      raise InvalidObjectError, "Object #{ref.id}, Generation #{ref.gen} is invalid"
     end
     ################################################################################
     # Stores an offset value for a particular PDF object ID and revision number

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pdf-reader
 version: !ruby/object:Gem::Version 
-  version: 0.7.2
+  version: 0.7.3
 platform: ruby
 authors: 
 - Peter Jones
@@ -9,44 +9,53 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-05-20 00:00:00 +10:00
+date: 2008-06-11 00:00:00 +10:00
 default_executable: 
 dependencies: []
 
 description: The PDF::Reader library implements a PDF parser conforming as much as possible to the PDF specification from Adobe
 email: pjones@pmade.com
 executables: 
+- pdf_object
 - pdf_text
 - pdf_list_callbacks
 extensions: []
 
 extra_rdoc_files: 
-- README
+- README.rdoc
 - TODO
 - CHANGELOG
 files: 
 - lib/pdf
+- lib/pdf/reader.rb
 - lib/pdf/reader
-- lib/pdf/reader/explore.rb
-- lib/pdf/reader/reference.rb
-- lib/pdf/reader/xref.rb
-- lib/pdf/reader/token.rb
-- lib/pdf/reader/filter.rb
-- lib/pdf/reader/text_receiver.rb
 - lib/pdf/reader/buffer.rb
-- lib/pdf/reader/error.rb
-- lib/pdf/reader/content.rb
-- lib/pdf/reader/parser.rb
 - lib/pdf/reader/cmap.rb
+- lib/pdf/reader/content.rb
 - lib/pdf/reader/encoding.rb
-- lib/pdf/reader/register_receiver.rb
+- lib/pdf/reader/error.rb
+- lib/pdf/reader/explore.rb
+- lib/pdf/reader/filter.rb
 - lib/pdf/reader/font.rb
 - lib/pdf/reader/glyphlist.txt
+- lib/pdf/reader/parser.rb
+- lib/pdf/reader/xref.rb
+- lib/pdf/reader/reference.rb
+- lib/pdf/reader/register_receiver.rb
+- lib/pdf/reader/text_receiver.rb
+- lib/pdf/reader/token.rb
+- lib/pdf/reader/encodings
+- lib/pdf/reader/encodings/mac_expert.txt
+- lib/pdf/reader/encodings/mac_roman.txt
+- lib/pdf/reader/encodings/pdf_doc.txt
+- lib/pdf/reader/encodings/standard.txt
+- lib/pdf/reader/encodings/symbol.txt
+- lib/pdf/reader/encodings/win_ansi.txt
+- lib/pdf/reader/encodings/zapf_dingbats.txt
 - lib/pdf/reader/stream.rb
-- lib/pdf/reader/parser.rb.rej
-- lib/pdf/reader.rb
+- lib/pdf/reader/print_receiver.rb
 - Rakefile
-- README
+- README.rdoc
 - TODO
 - CHANGELOG
 has_rdoc: true
@@ -56,7 +65,7 @@ rdoc_options:
 - --title
 - PDF::Reader Documentation
 - --main
-- README
+- README.rdoc
 - -q
 require_paths: 
 - lib

data/lib/pdf/reader/parser.rb.rej

@@ -1,29 +0,0 @@
-***************
-*** 173,178 ****
-  
-       obj = parse_token
-       post_obj = parse_token
-         case post_obj
-         when "endobj"   then return [obj,nil]
-         when "stream"   then return [obj, stream(obj)]
---- 173,192 ----
-  
-       obj = parse_token
-       post_obj = parse_token
-+ 
-+       if obj.class == Array
-+          newobj = Array.new
-+          obj.each_index {|idx|
-+              if obj[idx].class == PDF::Reader::Reference
-+                xo, xs = @xref.object(obj[idx])
-+                if xs
-+                   newobj << xs
-+                   end
-+                end
-+              }
-+          return newobj.flatten
-+          end
-+ 
-         case post_obj
-         when "endobj"   then return [obj,nil]
-         when "stream"   then return [obj, stream(obj)]