pdf-reader 2.4.0 → 2.5.0

data/lib/pdf/reader/font.rb

@@ -131,7 +131,9 @@ class PDF::Reader
       if obj[:ToUnicode]
         # ToUnicode is optional for Type1 and Type3
         stream = @ohash.object(obj[:ToUnicode])
-        @tounicode = PDF::Reader::CMap.new(stream.unfiltered_data)
+        if stream.is_a?(PDF::Reader::Stream)
+          @tounicode = PDF::Reader::CMap.new(stream.unfiltered_data)
+        end
       end
     end
 

data/lib/pdf/reader/object_hash.rb

@@ -331,7 +331,9 @@ class PDF::Reader
     def decrypt(ref, obj)
       case obj
       when PDF::Reader::Stream then
-        obj.data = sec_handler.decrypt(obj.data, ref)
+        # PDF 32000-1:2008 7.5.8.2: "The cross-reference stream shall not be encrypted [...]."
+        # Therefore we shouldn't try to decrypt it.
+        obj.data = sec_handler.decrypt(obj.data, ref) unless obj.hash[:Type] == :XRef
         obj
       when Hash                then
         arr = obj.map { |key,val| [key, decrypt(ref, val)] }.flatten(1)

data/lib/pdf/reader/orientation_detector.rb

@@ -22,8 +22,8 @@ class PDF::Reader
     def detect_orientation
       llx,lly,urx,ury = @attributes[:MediaBox]
       rotation        = @attributes[:Rotate].to_i
-      width           = urx.to_i - llx.to_i
-      height          = ury.to_i - lly.to_i
+      width           = (urx.to_i - llx.to_i).abs
+      height          = (ury.to_i - lly.to_i).abs
       if width > height
         (rotation % 180).zero? ? 'landscape' : 'portrait'
       else

data/lib/pdf/reader/page.rb

@@ -124,6 +124,34 @@ module PDF
         }.join(" ")
       end
 
+      # returns the angle to rotate the page clockwise. Always 0, 90, 180 or 270
+      #
+      def rotate
+        value = attributes[:Rotate].to_i
+        case value
+        when 0, 90, 180, 270
+          value
+        else
+          0
+        end
+      end
+
+      # returns the "boxes" that define the page object.
+      # values are defaulted according to section 7.7.3.3 of the PDF Spec 1.7
+      #
+      def boxes
+        mediabox = attributes[:MediaBox]
+        cropbox = attributes[:Cropbox] || mediabox
+
+        {
+          MediaBox: objects.deref!(mediabox),
+          CropBox: objects.deref!(cropbox),
+          BleedBox: objects.deref!(attributes[:BleedBox] || cropbox),
+          TrimBox: objects.deref!(attributes[:TrimBox] || cropbox),
+          ArtBox: objects.deref!(attributes[:ArtBox] || cropbox)
+        }
+      end
+
       private
 
       def root

data/lib/pdf/reader/page_layout.rb

@@ -21,18 +21,21 @@ class PDF::Reader
       @mean_font_size   = mean(@runs.map(&:font_size)) || DEFAULT_FONT_SIZE
       @mean_font_size = DEFAULT_FONT_SIZE if @mean_font_size == 0
       @mean_glyph_width = mean(@runs.map(&:mean_character_width)) || 0
-      @page_width  = mediabox[2] - mediabox[0]
-      @page_height = mediabox[3] - mediabox[1]
-      @x_offset = @runs.map(&:x).sort.first
+      @page_width  = (mediabox[2] - mediabox[0]).abs
+      @page_height = (mediabox[3] - mediabox[1]).abs
+      @x_offset = @runs.map(&:x).sort.first || 0
+      lowest_y = @runs.map(&:y).sort.first || 0
+      @y_offset = lowest_y > 0 ? 0 : lowest_y
     end
 
     def to_s
       return "" if @runs.empty?
+      return "" if row_count == 0
 
       page = row_count.times.map { |i| " " * col_count }
       @runs.each do |run|
         x_pos = ((run.x - @x_offset) / col_multiplier).round
-        y_pos = row_count - (run.y / row_multiplier).round
+        y_pos = row_count - ((run.y - @y_offset) / row_multiplier).round
         if y_pos <= row_count && y_pos >= 0 && x_pos <= col_count && x_pos >= 0
           local_string_insert(page[y_pos-1], run.text, x_pos)
         end

data/lib/pdf/reader/page_state.rb

@@ -30,7 +30,7 @@ class PDF::Reader
         @xobject_stack = [page.xobjects]
         @cs_stack      = [page.color_spaces]
         @stack         = [DEFAULT_GRAPHICS_STATE.dup]
-        state[:ctm]    = identity_matrix
+        state[:ctm]  = identity_matrix
       end
 
       #####################################################
@@ -322,11 +322,13 @@ class PDF::Reader
         th = state[:h_scaling]
         # optimise the common path to reduce Float allocations
         if th == 1 && tj == 0 && tc == 0 && tw == 0
-          glyph_width = w0 * fs
-          tx = glyph_width
+          tx = w0 * fs
+        elsif tj != 0
+          # don't apply spacing to TJ displacement
+          tx = (w0 - (tj/1000.0)) * fs * th
         else
-          glyph_width = ((w0 - (tj/1000.0)) * fs) * th
-          tx = glyph_width + ((tc + tw) * th)
+          # apply horizontal scaling to spacing values but not font size
+          tx = ((w0 * fs) + tc + tw) * th
         end
 
         # TODO: I'm pretty sure that tx shouldn't need to be divided by

data/lib/pdf/reader/page_text_receiver.rb

@@ -41,13 +41,17 @@ module PDF
       # starting a new page
       def page=(page)
         @state = PageState.new(page)
+        @page = page
         @content = []
         @characters = []
         @mediabox = page.objects.deref(page.attributes[:MediaBox])
+        device_bl = @state.ctm_transform(@mediabox[0], @mediabox[1])
+        device_tr = @state.ctm_transform(@mediabox[2], @mediabox[3])
+        @device_mediabox = [ device_bl.first, device_bl.last, device_tr.first, device_tr.last]
       end
 
       def content
-        PageLayout.new(@characters, @mediabox).to_s
+        PageLayout.new(@characters, @device_mediabox).to_s
       end
 
       #####################################################
@@ -101,6 +105,8 @@ module PDF
         glyphs.each_with_index do |glyph_code, index|
           # paint the current glyph
           newx, newy = @state.trm_transform(0,0)
+          newx, newy = apply_rotation(newx, newy)
+
           utf8_chars = @state.current_font.to_utf8(glyph_code)
 
           # apply to glyph displacment for the current glyph so the next
@@ -115,6 +121,21 @@ module PDF
         end
       end
 
+      def apply_rotation(x, y)
+        if @page.rotate == 90
+          tmp = x
+          x = y
+          y = tmp * -1
+        elsif @page.rotate == 180
+          y *= -1
+        elsif @page.rotate == 270
+          tmp = x
+          x = y * -1
+          y = tmp * -1
+        end
+        return x, y
+      end
+
     end
   end
 end

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

@@ -37,23 +37,15 @@ class PDF::Reader
       def glyph_width(code_point)
         return 0 if code_point.nil? || code_point < 0
 
-        m = @metrics.char_metrics_by_code[code_point]
-        if m.nil?
-          names = @font.encoding.int_to_name(code_point)
+        names = @font.encoding.int_to_name(code_point)
+        metrics = names.map { |name|
+          @metrics.char_metrics[name.to_s]
+        }.compact.first
 
-          m = names.map { |name|
-            @metrics.char_metrics[name.to_s]
-          }.compact.first
-        end
-
-        if m
-          m[:wx]
-        elsif @font.widths[code_point - 1]
-          @font.widths[code_point - 1]
-        elsif control_character?(code_point)
-          0
+        if metrics
+          metrics[:wx]
         else
-          0
+          @font.widths[code_point - 1] || 0
         end
       end
 

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.4.0
+  version: 2.5.0
 platform: ruby
 authors:
 - James Healy
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-11-21 00:00:00.000000000 Z
+date: 2021-06-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '13.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "<"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -67,7 +67,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.2'
 - !ruby/object:Gem::Dependency
-  name: ir_b
+  name: pry
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -100,14 +100,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '1.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.0.0
+        version: '1.0'
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
   requirement: !ruby/object:Gem::Requirement
@@ -208,6 +208,7 @@ files:
 - lib/pdf/reader/afm/Helvetica-BoldOblique.afm
 - lib/pdf/reader/afm/Helvetica-Oblique.afm
 - lib/pdf/reader/afm/Helvetica.afm
+- lib/pdf/reader/afm/MustRead.html
 - lib/pdf/reader/afm/Symbol.afm
 - lib/pdf/reader/afm/Times-Bold.afm
 - lib/pdf/reader/afm/Times-BoldItalic.afm
@@ -276,10 +277,10 @@ licenses:
 - MIT
 metadata:
   bug_tracker_uri: https://github.com/yob/pdf-reader/issues
-  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.4.0/CHANGELOG
-  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.4.0
-  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.4.0
-post_install_message: 
+  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.5.0/CHANGELOG
+  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.5.0
+  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.5.0
+post_install_message:
 rdoc_options:
 - "--title"
 - PDF::Reader Documentation
@@ -292,15 +293,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.3
+      version: '2.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: A library for accessing the content of PDF files
 test_files: []