pdf-reader 1.3.1 → 1.3.2

data/CHANGELOG

@@ -1,3 +1,6 @@
+v1.3.2 (26th February 2013)
+- various bug fixes
+
 v1.3.1 (12th February 2013)
 - various bug fixes
 

data/lib/pdf/reader/encoding.rb

@@ -76,7 +76,7 @@ class PDF::Reader
           byte = val.to_i
         else
           @differences[byte] = val
-          @mapping[byte] = names_to_unicode[val]
+          @mapping[byte] = glyphlist.name_to_unicode(val)
           byte += 1
         end
       end
@@ -116,15 +116,15 @@ class PDF::Reader
     #     int_to_name(65)
     #     => :A
     #
-    # TODO: this needs to be expanded to return the appropriate name for standard
-    #       glyph codes in the encoding. 65 to :A, etc. At the moment it only
-    #       handles glyphs in the difference table
-    #
     def int_to_name(glyph_code)
       if @enc_name == "Identity-H" || @enc_name == "Identity-V"
-        nil
+        []
+      elsif differences[glyph_code]
+        [differences[glyph_code]]
+      elsif @mapping[glyph_code]
+        glyphlist.unicode_to_name(@mapping[glyph_code])
       else
-        @differences[glyph_code]
+        []
       end
     end
 
@@ -189,8 +189,8 @@ class PDF::Reader
       @mapping.size > 0
     end
 
-    def names_to_unicode
-      @names_to_unicode ||= PDF::Reader::GlyphHash.new
+    def glyphlist
+      @glyphlist ||= PDF::Reader::GlyphHash.new
     end
 
     def load_mapping(file)

data/lib/pdf/reader/glyph_hash.rb

@@ -32,7 +32,9 @@ class PDF::Reader
   class GlyphHash # :nodoc:
     def initialize
       # only parse the glyph list once, and cache the results (for performance)
-      @adobe = @@cache ||= load_adobe_glyph_mapping
+      adobe = @@cache ||= load_adobe_glyph_mapping
+      @by_name      = adobe.first
+      @by_codepoint = adobe.last
     end
 
     # attempt to convert a PDF Name to a unicode codepoint. Returns nil
@@ -40,26 +42,26 @@ class PDF::Reader
     #
     #   h = GlyphHash.new
     #
-    #   h[:A]
+    #   h.name_to_unicode(:A)
     #   => 65
     #
-    #   h[:Euro]
+    #   h.name_to_unicode(:Euro)
     #   => 8364
     #
-    #   h[:G30]
+    #   h.name_to_unicode(:G30)
     #   => 48
     #
-    #   h[:34]
+    #   h.name_to_unicode(:34)
     #   => 34
     #
-    def [](name)
+    def name_to_unicode(name)
       return nil unless name.is_a?(Symbol)
 
       name = name.to_s.gsub('_', '').intern
       str = name.to_s
 
-      if @adobe.has_key?(name)
-        @adobe[name]
+      if @by_name.has_key?(name)
+        @by_name[name]
       elsif str.match(/\Auni[A-F\d]{4}\Z/)
         "0x#{str[3,4]}".hex
       elsif str.match(/\Au[A-F\d]{4,6}\Z/)
@@ -73,23 +75,47 @@ class PDF::Reader
       end
     end
 
+    # attempt to convert a Unicode code point to the equivilant PDF Name. Returns nil
+    # if no conversion is possible.
+    #
+    #   h = GlyphHash.new
+    #
+    #   h.unicode_to_name(65)
+    #   => :A
+    #
+    #   h.unicode_to_name(8364)
+    #   => :Euro
+    #
+    #   h.unicode_to_name(34)
+    #   => :34
+    #
+    def unicode_to_name(codepoint)
+      @by_codepoint[codepoint.to_i]
+    end
+
     private
 
     # returns a hash that maps glyph names to unicode codepoints. The mapping is based on
     # a text file supplied by Adobe at:
     # http://www.adobe.com/devnet/opentype/archives/glyphlist.txt
     def load_adobe_glyph_mapping
-      glyphs = {}
+      keyed_by_name      = {}
+      keyed_by_codepoint = {}
 
       RUBY_VERSION >= "1.9" ? mode = "r:BINARY" : mode = "r"
       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.to_sym] = "0x#{code}".hex if name
+          if name && code
+            cp = "0x#{code}".hex
+            keyed_by_name[name.to_sym]   = cp
+            keyed_by_codepoint[cp]     ||= []
+            keyed_by_codepoint[cp]     << name.to_sym
+          end
         end
       end
 
-      glyphs.freeze
+      [keyed_by_name.freeze, keyed_by_codepoint.freeze]
     end
 
   end

data/lib/pdf/reader/width_calculator/built_in.rb

@@ -39,8 +39,10 @@ class PDF::Reader
 
         m = @metrics.metrics_for(code_point)
         if m.nil?
-          name = @font.encoding.int_to_name(code_point)
-          m = @metrics.metrics_for_name(name)
+          names = @font.encoding.int_to_name(code_point)
+          m = names.map { |name|
+            @metrics.metrics_for_name(name)
+          }.compact.first
         end
 
         if m
@@ -48,7 +50,7 @@ class PDF::Reader
         elsif @font.widths[code_point - 1]
           @font.widths[code_point - 1]
         else
-          raise ArgumentError, "Unknown glyph width for #{codepoint}"
+          raise ArgumentError, "Unknown glyph width for #{code_point}"
         end
       end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 1.3.1
+  version: 1.3.2
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-02-12 00:00:00.000000000 Z
+date: 2013-02-26 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -219,88 +219,88 @@ extra_rdoc_files:
 - CHANGELOG
 - MIT-LICENSE
 files:
-- examples/extract_fonts.rb
-- examples/hash.rb
-- examples/extract_bates.rb
 - examples/metadata.rb
-- examples/extract_images.rb
+- examples/callbacks.rb
 - examples/rspec.rb
 - examples/page_count.rb
-- examples/callbacks.rb
-- examples/text.rb
 - examples/version.rb
-- lib/pdf/hash.rb
-- lib/pdf/reader.rb
-- lib/pdf/reader/width_calculator/built_in.rb
-- lib/pdf/reader/width_calculator/type_zero.rb
-- lib/pdf/reader/width_calculator/true_type.rb
-- lib/pdf/reader/width_calculator/composite.rb
-- lib/pdf/reader/width_calculator/type_one_or_three.rb
-- lib/pdf/reader/xref.rb
-- lib/pdf/reader/page.rb
-- lib/pdf/reader/transformation_matrix.rb
-- lib/pdf/reader/encoding.rb
-- lib/pdf/reader/page_layout.rb
-- lib/pdf/reader/font.rb
-- lib/pdf/reader/print_receiver.rb
-- lib/pdf/reader/lzw.rb
+- examples/hash.rb
+- examples/extract_fonts.rb
+- examples/text.rb
+- examples/extract_bates.rb
+- examples/extract_images.rb
+- lib/pdf-reader.rb
+- lib/pdf/reader/error.rb
+- lib/pdf/reader/filter.rb
+- lib/pdf/reader/reference.rb
+- lib/pdf/reader/form_xobject.rb
+- lib/pdf/reader/metadata_strategy.rb
 - lib/pdf/reader/buffer.rb
-- lib/pdf/reader/synchronized_cache.rb
-- lib/pdf/reader/object_stream.rb
-- lib/pdf/reader/cmap.rb
-- lib/pdf/reader/text_receiver.rb
-- lib/pdf/reader/register_receiver.rb
-- lib/pdf/reader/cid_widths.rb
-- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/parser.rb
 - lib/pdf/reader/encodings/mac_roman.txt
-- lib/pdf/reader/encodings/zapf_dingbats.txt
-- lib/pdf/reader/encodings/symbol.txt
-- lib/pdf/reader/encodings/win_ansi.txt
-- lib/pdf/reader/encodings/mac_expert.txt
 - lib/pdf/reader/encodings/standard.txt
+- lib/pdf/reader/encodings/symbol.txt
 - lib/pdf/reader/encodings/pdf_doc.txt
-- lib/pdf/reader/filter.rb
-- lib/pdf/reader/filter/null.rb
-- lib/pdf/reader/filter/flate.rb
-- lib/pdf/reader/filter/lzw.rb
-- lib/pdf/reader/filter/ascii85.rb
-- lib/pdf/reader/filter/ascii_hex.rb
-- lib/pdf/reader/filter/run_length.rb
-- lib/pdf/reader/filter/depredict.rb
-- lib/pdf/reader/object_hash.rb
-- lib/pdf/reader/reference.rb
+- lib/pdf/reader/encodings/zapf_dingbats.txt
+- lib/pdf/reader/encodings/mac_expert.txt
+- lib/pdf/reader/encodings/win_ansi.txt
+- lib/pdf/reader/cid_widths.rb
+- lib/pdf/reader/stream.rb
+- lib/pdf/reader/object_stream.rb
+- lib/pdf/reader/cmap.rb
+- lib/pdf/reader/font_descriptor.rb
+- lib/pdf/reader/standard_security_handler.rb
+- lib/pdf/reader/page.rb
+- lib/pdf/reader/token.rb
+- lib/pdf/reader/transformation_matrix.rb
+- lib/pdf/reader/font.rb
+- lib/pdf/reader/abstract_strategy.rb
+- lib/pdf/reader/object_cache.rb
+- lib/pdf/reader/register_receiver.rb
+- lib/pdf/reader/text_receiver.rb
+- lib/pdf/reader/synchronized_cache.rb
+- lib/pdf/reader/resource_methods.rb
+- lib/pdf/reader/page_state.rb
+- lib/pdf/reader/pages_strategy.rb
 - lib/pdf/reader/glyphlist.txt
+- lib/pdf/reader/print_receiver.rb
+- lib/pdf/reader/glyph_hash.rb
+- lib/pdf/reader/text_run.rb
+- lib/pdf/reader/object_hash.rb
+- lib/pdf/reader/page_layout.rb
+- lib/pdf/reader/afm/Times-Bold.afm
 - lib/pdf/reader/afm/Courier-BoldOblique.afm
-- lib/pdf/reader/afm/Symbol.afm
 - lib/pdf/reader/afm/Times-Italic.afm
-- lib/pdf/reader/afm/Courier-Oblique.afm
-- lib/pdf/reader/afm/Helvetica-Bold.afm
-- lib/pdf/reader/afm/Courier-Bold.afm
-- lib/pdf/reader/afm/Times-BoldItalic.afm
-- lib/pdf/reader/afm/Helvetica-BoldOblique.afm
 - lib/pdf/reader/afm/Helvetica.afm
-- lib/pdf/reader/afm/ZapfDingbats.afm
-- lib/pdf/reader/afm/Helvetica-Oblique.afm
-- lib/pdf/reader/afm/Times-Bold.afm
+- lib/pdf/reader/afm/Courier-Bold.afm
 - lib/pdf/reader/afm/Times-Roman.afm
+- lib/pdf/reader/afm/Helvetica-Bold.afm
+- lib/pdf/reader/afm/Helvetica-Oblique.afm
+- lib/pdf/reader/afm/Courier-Oblique.afm
+- lib/pdf/reader/afm/ZapfDingbats.afm
+- lib/pdf/reader/afm/Helvetica-BoldOblique.afm
 - lib/pdf/reader/afm/Courier.afm
-- lib/pdf/reader/token.rb
-- lib/pdf/reader/parser.rb
-- lib/pdf/reader/page_state.rb
-- lib/pdf/reader/error.rb
-- lib/pdf/reader/glyph_hash.rb
+- lib/pdf/reader/afm/Times-BoldItalic.afm
+- lib/pdf/reader/afm/Symbol.afm
+- lib/pdf/reader/encoding.rb
 - lib/pdf/reader/width_calculator.rb
-- lib/pdf/reader/resource_methods.rb
-- lib/pdf/reader/standard_security_handler.rb
-- lib/pdf/reader/text_run.rb
-- lib/pdf/reader/form_xobject.rb
-- lib/pdf/reader/stream.rb
-- lib/pdf/reader/pages_strategy.rb
-- lib/pdf/reader/abstract_strategy.rb
-- lib/pdf/reader/metadata_strategy.rb
-- lib/pdf/reader/object_cache.rb
-- lib/pdf/reader/font_descriptor.rb
-- lib/pdf-reader.rb
+- lib/pdf/reader/xref.rb
+- lib/pdf/reader/filter/flate.rb
+- lib/pdf/reader/filter/depredict.rb
+- lib/pdf/reader/filter/null.rb
+- lib/pdf/reader/filter/ascii_hex.rb
+- lib/pdf/reader/filter/ascii85.rb
+- lib/pdf/reader/filter/run_length.rb
+- lib/pdf/reader/filter/lzw.rb
+- lib/pdf/reader/width_calculator/built_in.rb
+- lib/pdf/reader/width_calculator/true_type.rb
+- lib/pdf/reader/width_calculator/composite.rb
+- lib/pdf/reader/width_calculator/type_zero.rb
+- lib/pdf/reader/width_calculator/type_one_or_three.rb
+- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/lzw.rb
+- lib/pdf/hash.rb
+- lib/pdf/reader.rb
 - Rakefile
 - README.rdoc
 - TODO