pdf-reader 0.7 → 0.7.1

data/CHANGELOG

@@ -1,3 +1,8 @@
+v0.7.1 (6th May 2008)
+- Non-page strings (ie. metadata, etc) are now converted to UTF-8 more accurately
+- Fixed a regression between 0.6.2 and 0.7 that prevented difference tables from being applied
+  correctly when translating text into UTF-8
+
 v0.7 (6th May 2008)
 - API INCOMPATIBLE CHANGE: any hashes that are passed to callbacks use symbols as keys instead of PDF::Reader::Name instances.
 - Improved support for converting text in some PDF files to unicode
@@ -5,7 +10,7 @@ v0.7 (6th May 2008)
 - Include some basic metadata callbacks
 - Don't interpret a comment token (%) inside a string as a comment
 - Small fixes to improve 1.9 compatability
-- Improved our Zlib deflating to make it more slightly more robust - still some more issues to work out though
+- Improved our Zlib deflating to make it slightly more robust - still some more issues to work out though
 - Throw an UnsupportedFeatureError if a pdf that uses XRef streams is opened
 - Added an option to PDF::Reader#file and PDF::Reader#string to enable parsing of only parts of a PDF file(ie. only metadata, etc)
 

data/Rakefile

@@ -6,7 +6,7 @@ require 'rake/testtask'
 require "rake/gempackagetask"
 require 'spec/rake/spectask'
 
-PKG_VERSION = "0.7"
+PKG_VERSION = "0.7.1"
 PKG_NAME = "pdf-reader"
 PKG_FILE_NAME = "#{PKG_NAME}-#{PKG_VERSION}"
 

data/TODO

@@ -10,7 +10,7 @@ v0.8
   from the Original encoding to Unicode.
 - detect when a font's encoding is a CMap (generally used for pre-Unicode, multibyte asian encodings), and display a user friendly error
 - Provide a way to get raw access to a particular object. Good for testing purposes
-- Improve interpretation of non content stream data (ie metadata). Use PDFDofEncoding, recognise UTF16 strings, recognise dates, etc
+- Improve interpretation of non content stream data (ie metadata). recognise dates, etc
 - Support Cross Reference Streams (spec 3.4.7)
 
 v0.9

data/lib/pdf/reader/content.rb

@@ -23,7 +23,6 @@
 #
 ################################################################################
 require 'stringio'
-#require 'enumerable'
 
 class PDF::Reader
   ################################################################################
@@ -254,7 +253,7 @@ class PDF::Reader
     ################################################################################
     # Begin processing the document metadata
     def metadata (info)
-      info = utf16_to_utf8(info)
+      info = decode_strings(info)
       callback(:metadata, [info]) if info
     end
     ################################################################################
@@ -430,16 +429,17 @@ class PDF::Reader
     end
     ################################################################################
     private
-    def utf16_to_utf8(obj)
+    # strings outside of page content should be in either PDFDocEncoding or UTF-16.
+    def decode_strings(obj)
       case obj
       when String then 
         if obj[0,2] == "\376\377"
-          obj[2, obj.size-2].unpack("n*").pack("U*")
+          PDF::Reader::Encoding::UTF16Encoding.new.to_utf8(obj)
         else
-          obj
+          PDF::Reader::Encoding::PDFDocEncoding.new.to_utf8(obj)
         end
-      when Hash   then obj.each { |key,val| obj[key] = utf16_to_utf8(val) }
-      when Array  then obj.collect { |item| utf16_to_utf8(item) }
+      when Hash   then obj.each { |key,val| obj[key] = decode_strings(val) }
+      when Array  then obj.collect { |item| decode_strings(item) }
       else
         obj
       end

data/lib/pdf/reader/encoding.rb

@@ -34,13 +34,13 @@ class PDF::Reader
 
     # set the differences table for this encoding. should be an array in the following format:
     #
-    #   [25, "A", 26, "B"]
+    #   [25, :A, 26, :B]
     #
     # The array alternates bewteen a decimal byte number and a glyph name to map to that byte
     #
     # To save space the following array is also valid and equivilant to the previous one
     #
-    #   [25, "A", "B"]
+    #   [25, :A, :B]
     def differences=(diff)
       raise ArgumentError, "diff must be an array" unless diff.kind_of?(Array)
 
@@ -498,6 +498,84 @@ class PDF::Reader
       end
     end
 
+    class PDFDocEncoding < Encoding
+      # convert a PDFDocEncoding string into UTF-8
+      def to_utf8(str, tounicode = nil)
+        array_pdf = str.unpack('C*')
+        array_pdf = self.process_differences(array_pdf)
+        array_enc = []
+        array_pdf.each do |num|
+          if tounicode && (code = tounicode.decode(num))
+            array_enc << code
+          elsif tounicode
+            array_enc << PDF::Reader::Encoding::UNKNOWN_CHAR
+          else
+            case num
+              # change necesary characters to equivilant Unicode codepoints
+            when 0x18; array_enc << 0x02D8
+            when 0x19; array_enc << 0x02C7
+            when 0x1A; array_enc << 0x02C6
+            when 0x1B; array_enc << 0x02D9
+            when 0x1C; array_enc << 0x02DD
+            when 0x1D; array_enc << 0x02DB
+            when 0x1E; array_enc << 0x02DA
+            when 0x1F; array_enc << 0x02DC
+            when 0x7F; array_enc << PDF::Reader::Encoding::UNKNOWN_CHAR # Undefined
+            when 0x80; array_enc << 0x2022
+            when 0x81; array_enc << 0x2020
+            when 0x82; array_enc << 0x2021
+            when 0x83; array_enc << 0x2026
+            when 0x84; array_enc << 0x2014
+            when 0x85; array_enc << 0x2013
+            when 0x86; array_enc << 0x0192
+            when 0x87; array_enc << 0x2044
+            when 0x88; array_enc << 0x2039
+            when 0x89; array_enc << 0x203A
+            when 0x8A; array_enc << 0x2212
+            when 0x8B; array_enc << 0x2030
+            when 0x8C; array_enc << 0x201E
+            when 0x8D; array_enc << 0x201C
+            when 0x8E; array_enc << 0x201D
+            when 0x8F; array_enc << 0x2018
+            when 0x90; array_enc << 0x2019
+            when 0x91; array_enc << 0x201A
+            when 0x92; array_enc << 0x2122
+            when 0x93; array_enc << 0xFB01
+            when 0x94; array_enc << 0xFB02
+            when 0x95; array_enc << 0x0141
+            when 0x96; array_enc << 0x0152
+            when 0x97; array_enc << 0x0160
+            when 0x98; array_enc << 0x0178
+            when 0x99; array_enc << 0x017D
+            when 0x9A; array_enc << 0x0131
+            when 0x9B; array_enc << 0x0142
+            when 0x9C; array_enc << 0x0153
+            when 0x9D; array_enc << 0x0161
+            when 0x9E; array_enc << 0x017E
+            when 0x9F; array_enc << PDF::Reader::Encoding::UNKNOWN_CHAR # Undefined
+            when 0xA0; array_enc << 0x20AC
+            else
+              array_enc << num
+            end
+          end
+        end
+
+        # convert any glyph names to unicode codepoints
+        array_enc = self.process_glyphnames(array_enc)
+
+        # replace charcters that didn't convert to unicode nicely with something valid
+        array_enc.collect! { |c| c ? c : PDF::Reader::Encoding::UNKNOWN_CHAR }
+
+        # pack all our Unicode codepoints into a UTF-8 string
+        ret = array_enc.pack("U*")
+
+        # set the strings encoding correctly under ruby 1.9+
+        ret.force_encoding("UTF-8") if ret.respond_to?(:force_encoding)
+
+        return ret
+      end
+    end
+
     class StandardEncoding < Encoding
       # convert an Adobe Standard Encoding string into UTF-8
       def to_utf8(str, tounicode = nil)
@@ -771,6 +849,23 @@ class PDF::Reader
       end
     end
 
+    class UTF16Encoding < Encoding
+      # convert a UTF-16 string into UTF-8
+      def to_utf8(str, tounicode = nil)
+
+        # remove the UTF-16 Byte Order Mark if it exists
+        str = str[2, str.size-2] if str[0,2] == "\376\377"
+
+        # convert away
+        str = str.unpack("n*").pack("U*")
+
+        # set the strings encoding correctly under ruby 1.9+
+        str.force_encoding("UTF-8") if str.respond_to?(:force_encoding)
+
+        return str
+      end
+    end
+
     class WinAnsiEncoding < Encoding
       # convert a WinAnsiEncoding string into UTF-8
       def to_utf8(str, tounicode = nil)

data/lib/pdf/reader/font.rb

@@ -39,7 +39,7 @@ class PDF::Reader
         File.open(File.dirname(__FILE__) + "/glyphlist.txt",mode) do |f|
           f.each do |l|
             m, name, code = *l.match(/([0-9A-Za-z]+);([0-9A-F]{4})/)
-            @@glyphs[name] = "0x#{code}".hex if name
+            @@glyphs[name.to_sym] = "0x#{code}".hex if name
           end
         end
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: pdf-reader
 version: !ruby/object:Gem::Version 
-  version: "0.7"
+  version: 0.7.1
 platform: ruby
 authors: 
 - Peter Jones