pdf-reader 1.3.0 → 1.3.1

data/CHANGELOG

@@ -1,3 +1,6 @@
+v1.3.1 (12th February 2013)
+- various bug fixes
+
 v1.3.0 (30th December 2012)
 - Numerous performance optimisations (thanks Alex Dowad)
 - Improved text extraction (thanks Nathaniel Madura)

data/README.rdoc

@@ -77,17 +77,11 @@ of PDF::Reader::Page.
     receiver = RedGreenBlue.new
     page.walk(receiver)
 
-For low level access to the objects in a PDF file, use the ObjectHash class. You can
-build an ObjectHash instance directly:
-
-    puts PDF::Reader::ObjectHash.new("somefile.pdf")
-
-or via a PDF::Reader instance:
+For low level access to the objects in a PDF file, use the ObjectHash class like
+so:
 
     reader  = PDF::Reader.new("somefile.pdf")
-    puts reader.objects
-
-The second method is preferred to increase the effectiveness of internal caching.
+    puts reader.objects.inspect
 
 = Text Encoding
 

data/lib/pdf/reader/page.rb

@@ -61,6 +61,10 @@ module PDF
             hash.merge!(@objects.deref(obj))
           end
         }
+        # This shouldn't be necesary, but some non compliant PDFs leave MediaBox
+        # out. Assuming 8.5" x 11" is what Acobat does, so we do it too.
+        @attributes[:MediaBox] ||= [0,0,612,792]
+        @attributes
       end
 
       # returns the plain text content of this page encoded as UTF-8. Any

data/lib/pdf/reader/page_layout.rb

@@ -9,6 +9,8 @@ class PDF::Reader
   # page to be rendered as described by the page's MediaBox attribute
   class PageLayout
     def initialize(runs, mediabox)
+      raise ArgumentError, "a mediabox must be provided" if mediabox.nil?
+
       @runs    = merge_runs(runs)
       @mean_font_size   = mean(@runs.map(&:font_size)) || 0
       @mean_glyph_width = mean(@runs.map(&:mean_character_width)) || 0
@@ -58,11 +60,11 @@ class PDF::Reader
     end
 
     def row_multiplier
-      @row_multiplier ||= @page_height / row_count
+      @row_multiplier ||= @page_height.to_f / row_count.to_f
     end
 
     def col_multiplier
-      @col_multiplier ||= @page_width / col_count
+      @col_multiplier ||= @page_width.to_f / col_count.to_f
     end
 
     def mean(collection)

data/lib/pdf/reader/page_state.rb

@@ -63,7 +63,12 @@ class PDF::Reader
       #
       def concatenate_matrix(a, b, c, d, e, f)
         if state[:ctm]
-          state[:ctm].multiply!(a,b,c,d,e,f)
+          ctm = state[:ctm]
+          state[:ctm] = TransformationMatrix.new(a,b,c,d,e,f).multiply!(
+            ctm.a, ctm.b,
+            ctm.c, ctm.d,
+            ctm.e, ctm.f
+          )
         else
           state[:ctm] = TransformationMatrix.new(a,b,c,d,e,f)
         end
@@ -102,7 +107,11 @@ class PDF::Reader
       end
 
       def font_size
-        @font_size ||= state[:text_font_size] * @text_matrix.a * ctm.a
+        @font_size ||= begin
+                         _, zero = trm_transform(0,0)
+                         _, one  = trm_transform(1,1)
+                         (zero - one).abs
+                       end
       end
 
       def set_text_leading(leading)
@@ -324,7 +333,7 @@ class PDF::Reader
         #       ctm[0] here, but this gets my tests green and I'm out of
         #       ideas for now
         # TODO: support ty > 0
-        if ctm.a == 1
+        if ctm.a == 1 || ctm.a == 0
           @text_matrix.horizontal_displacement_multiply!(tx)
         else
           @text_matrix.horizontal_displacement_multiply!(tx/ctm.a)
@@ -341,8 +350,8 @@ class PDF::Reader
       def text_rendering_matrix
         @text_rendering_matrix ||= begin
           state_matrix = TransformationMatrix.new(
-            font_size * state[:h_scaling], 0,
-            0, font_size,
+            state[:text_font_size] * state[:h_scaling], 0,
+            0, state[:text_font_size],
             0, state[:text_rise]
           )
           state_matrix.multiply!(

data/lib/pdf/reader/page_text_receiver.rb

@@ -58,8 +58,12 @@ module PDF
       end
 
       def show_text_with_positioning(params) # TJ [(A) 120 (WA) 20 (Y)]
-        params.each_slice(2).each do |string, kerning|
-          internal_show_text(string, kerning || 0)
+        params.each do |arg|
+          if arg.is_a?(String)
+            internal_show_text(arg)
+          else
+            @state.process_glyph_displacement(0, arg, false)
+          end
         end
       end
 
@@ -88,7 +92,7 @@ module PDF
 
       private
 
-      def internal_show_text(string, kerning = 0)
+      def internal_show_text(string)
         if @state.current_font.nil?
           raise PDF::Reader::MalformedPDFError, "current font is invalid"
         end
@@ -102,16 +106,11 @@ module PDF
           # glyph will appear in the correct position
           glyph_width = @state.current_font.glyph_width(glyph_code) / 1000.0
           th = 1
-          if kerning != 0 && index == glyphs.size - 1
-            tj = kerning
-          else
-            tj = 0
-          end
           scaled_glyph_width = glyph_width * @state.font_size * th
           unless utf8_chars == SPACE
             @characters << TextRun.new(newx, newy, scaled_glyph_width, @state.font_size, utf8_chars)
           end
-          @state.process_glyph_displacement(glyph_width, tj, utf8_chars == SPACE)
+          @state.process_glyph_displacement(glyph_width, 0, utf8_chars == SPACE)
         end
       end
 

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

@@ -42,7 +42,14 @@ class PDF::Reader
           name = @font.encoding.int_to_name(code_point)
           m = @metrics.metrics_for_name(name)
         end
-        m[:wx]
+
+        if m
+          m[:wx]
+        elsif @font.widths[code_point - 1]
+          @font.widths[code_point - 1]
+        else
+          raise ArgumentError, "Unknown glyph width for #{codepoint}"
+        end
       end
 
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 1.3.0
+  version: 1.3.1
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-12-29 00:00:00.000000000 Z
+date: 2013-02-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake