pdf-reader 0.10.1 → 0.11.0.alpha

data/lib/pdf/reader/page_text_receiver.rb

@@ -0,0 +1,253 @@
+# coding: utf-8
+
+require 'matrix'
+
+module PDF
+  class Reader
+    class PageTextReceiver
+
+      DEFAULT_GRAPHICS_STATE = {
+        :ctm          => Matrix.identity(3),
+        :char_spacing => 0,
+        :word_spacing => 0,
+        :h_scaling    => 100,
+        :text_leading => 0,
+        :text_font    => nil,
+        :text_font_size => nil,
+        :text_mode    => 0,
+        :text_rise    => 0,
+        :text_knockout => 0
+      }
+
+      def initialize(fonts)
+        @fonts   = fonts
+        @content = ::Hash.new
+        @stack = [DEFAULT_GRAPHICS_STATE]
+      end
+
+      def content
+        keys = @content.keys.sort.reverse
+        keys.map { |key|
+          @content[key]
+        }.join("\n")
+      end
+
+      #####################################################
+      # Graphics State Operators
+      #####################################################
+
+      def save_graphics_state
+        @stack.push clone_state
+      end
+
+      def restore_graphics_state
+        @stack.pop
+      end
+
+      #####################################################
+      # Matrix Operators
+      #####################################################
+
+      # update the current transformation matrix.
+      #
+      # If the CTM is currently undefined, just store the new values.
+      #
+      # If there's an existing CTM, then multiply the existing matrix
+      # with the new matrix to form the updated matrix.
+      #
+      def concatenate_matrix(a, b, c, d, e, f)
+        transform = Matrix[
+          [a, b, 0],
+          [c, d, 0],
+          [e, f, 1]
+        ]
+        if state[:ctm]
+          state[:ctm] = transform * state[:ctm]
+        else
+          state[:ctm] = transform
+        end
+      end
+
+      #####################################################
+      # Text Object Operators
+      #####################################################
+
+      def begin_text_object
+        @text_matrix      = Matrix.identity(3)
+        @text_line_matrix = Matrix.identity(3)
+      end
+
+      def end_text_object
+        @text_matrix      = Matrix.identity(3)
+        @text_line_matrix = Matrix.identity(3)
+      end
+
+      #####################################################
+      # Text State Operators
+      #####################################################
+
+      def set_character_spacing(char_spacing)
+        state[:char_spacing] = char_spacing
+      end
+
+      def set_horizontal_text_scaling(h_scaling)
+        state[:h_scaling] = h_scaling
+      end
+
+      def set_text_font_and_size(label, size)
+        state[:text_font]      = label
+        state[:text_font_size] = size
+      end
+
+      def set_text_leading(leading)
+        state[:text_leading] = leading
+      end
+
+      def set_text_rendering_mode(mode)
+        state[:text_mode] = mode
+      end
+
+      def set_text_rise(rise)
+        state[:text_rise] = rise
+      end
+
+      def set_word_spacing(word_spacing)
+        state[:word_spacing] = word_spacing
+      end
+
+      #####################################################
+      # Text Positioning Operators
+      #####################################################
+
+      def move_text_position(x, y) # Td
+        temp_matrix = Matrix[
+                        [1, 0, 0],
+                        [0, 1, 0],
+                        [x, y, 1]
+                      ]
+        @text_matrix = @text_line_matrix = temp_matrix * @text_line_matrix
+      end
+
+      def move_text_position_and_set_leading(x, y) # TD
+        set_text_leading(-1 * y)
+        move_text_position(x, y)
+      end
+
+      def set_text_matrix_and_text_line_matrix(a, b, c, d, e, f) # Tm
+        @text_matrix = @text_line_matrix = Matrix[
+                              [a, b, 0],
+                              [c, d, 0],
+                              [e, f, 1]
+                            ]
+      end
+
+      def move_to_start_of_next_line # T*
+        move_text_position(0, state[:text_leading])
+      end
+
+      #####################################################
+      # Text Showing Operators
+      #####################################################
+
+      # record text that is drawn on the page
+      def show_text(string) # Tj
+        at = transform(Point.new(0,0))
+        @content[at.y] ||= ""
+        @content[at.y] << current_font.to_utf8(string)
+      end
+
+      def show_text_with_positioning(params) # TJ
+        params.each { |arg|
+          case arg
+          when String
+            show_text(arg)
+          when Fixnum, Float
+            show_text(" ") if arg > 1000
+          end
+        }
+      end
+
+      def move_to_next_line_and_show_text(str) # '
+        move_to_start_of_next_line
+        show_text(str)
+      end
+
+      def set_spacing_next_line_show_text(aw, ac, string) # "
+        set_word_spacing(aw)
+        set_character_spacing(ac)
+        move_to_next_line_and_show_text(string)
+      end
+
+      private
+
+      # transform x and y co-ordinates from the current text space to the
+      # underlying device space.
+      #
+      def transform(point, z = 1)
+        trm = text_rendering_matrix
+        Point.new(
+          (trm[0,0] * point.x) + (trm[1,0] * point.y) + (trm[2,0] * z),
+          (trm[0,1] * point.x) + (trm[1,1] * point.y) + (trm[2,1] * z)
+        )
+      end
+
+      def text_rendering_matrix
+        state_matrix = Matrix[
+                         [state[:text_font_size] * state[:h_scaling], 0, 0],
+                         [0, state[:text_font_size], 0],
+                         [0, state[:text_rise], 1]
+                       ]
+
+        state_matrix * @text_matrix * ctm
+      end
+
+      def state
+        @stack.last
+      end
+
+      # when save_graphics_state is called, we need to push a new copy of the
+      # current state onto the stack. That way any modifications to the state
+      # will be undone once restore_graphics_state is called.
+      #
+      # This returns a deep clone of the current state, ensuring changes are
+      # keep separate from earlier states.
+      #
+      # YAML is used to round-trip the state through a string to easily perform
+      # the deep clone. Kinda hacky, but effective.
+      #
+      def clone_state
+        if @stack.empty?
+          {}
+        else
+          yaml_state = YAML.dump(@stack.last)
+          YAML.load(yaml_state)
+        end
+      end
+
+      # return the current transformation matrix
+      #
+      def ctm
+        state[:ctm]
+      end
+
+      def current_font
+        @fonts[state[:text_font]]
+      end
+
+      # private class for representing points on a cartesian plain. Used
+      # to simplify maths in the MinPpi class.
+      #
+      class Point
+        attr_reader :x, :y
+
+        def initialize(x,y)
+          @x, @y = x,y
+        end
+
+        def distance(point)
+          Math.hypot(point.x - x, point.y - y)
+        end
+      end
+    end
+  end
+end

data/lib/pdf/reader/pages_strategy.rb

@@ -175,6 +175,8 @@ class PDF::Reader
   # If it gets mapped to the name "IM1", then it can be placed on the page using
   # invoke_xobject "IM1".
   #
+  # DEPRECATED: this class was deprecated in version 0.11.0 and will
+  #             eventually be removed
   class PagesStrategy< AbstractStrategy # :nodoc:
     OPERATORS = {
       'b'   => :close_fill_stroke,
@@ -460,17 +462,7 @@ class PDF::Reader
       fonts = {}
       resources = @ohash.object(resources[:Font]) || {}
       resources.each do |label, desc|
-        desc = @ohash.object(desc)
-        fonts[label] = PDF::Reader::Font.new
-        fonts[label].label = label
-        fonts[label].subtype = desc[:Subtype] if desc[:Subtype]
-        fonts[label].basefont = desc[:BaseFont] if desc[:BaseFont]
-        fonts[label].encoding = PDF::Reader::Encoding.new(@ohash.object(desc[:Encoding]))
-        fonts[label].descendantfonts = desc[:DescendantFonts] if desc[:DescendantFonts]
-        if desc[:ToUnicode]
-          stream = @ohash.object(desc[:ToUnicode])
-          fonts[label].tounicode = PDF::Reader::CMap.new(stream.unfiltered_data)
-        end
+        fonts[label] = PDF::Reader::Font.new(@ohash, @ohash.object(desc))
       end
       fonts
     end

data/lib/pdf/reader/text_receiver.rb

@@ -31,6 +31,9 @@ class PDF::Reader
   # Usage:
   #  receiver = PDF::Reader::TextReceiver.new($stdout)
   #  PDF::Reader.file("somefile.pdf", receiver)
+  #
+  # DEPRECATED: this class was deprecated in version 0.11.0 and will
+  #             eventually be removed
   class TextReceiver
     ################################################################################
     # Initialize with the library user's receiver

data/lib/pdf/reader/xref.rb

@@ -149,10 +149,9 @@ class PDF::Reader
       unless stream.hash[:Type] == :XRef
         raise PDF::Reader::MalformedPDFError, "xref stream not found when expected"
       end
-      trailer = {}
-      trailer[:Root] = stream.hash[:Root] if stream.hash[:Root]
-      trailer[:Info] = stream.hash[:Info] if stream.hash[:Info]
-      trailer[:Prev] = stream.hash[:Prev] if stream.hash[:Prev]
+      trailer = Hash[stream.hash.select { |key, value|
+        [:Size, :Prev, :Root, :Encrypt, :Info, :ID].include?(key)
+      }]
 
       widths       = stream.hash[:W]
       entry_length = widths.inject(0) { |s, w| s + w }

metadata

@@ -1,12 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: pdf-reader
 version: !ruby/object:Gem::Version 
-  prerelease: false
+  prerelease: true
   segments: 
   - 0
-  - 10
-  - 1
-  version: 0.10.1
+  - 11
+  - 0
+  - alpha
+  version: 0.11.0.alpha
 platform: ruby
 authors: 
 - James Healy
@@ -14,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2011-10-20 00:00:00 +11:00
+date: 2011-07-19 00:00:00 +10:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -87,46 +88,49 @@ extra_rdoc_files:
 - CHANGELOG
 - MIT-LICENSE
 files: 
+- examples/page_counter_naive.rb
+- examples/rspec.rb
 - examples/metadata.rb
-- examples/extract_images.rb
 - examples/extract_bates.rb
-- examples/page_counter_improved.rb
-- examples/callbacks.rb
-- examples/rspec.rb
 - examples/hash.rb
+- examples/callbacks.rb
 - examples/text.rb
-- examples/page_counter_naive.rb
 - examples/version.rb
-- lib/pdf/reader.rb
-- lib/pdf/hash.rb
-- lib/pdf/reader/print_receiver.rb
-- lib/pdf/reader/xref.rb
-- lib/pdf/reader/buffer.rb
-- lib/pdf/reader/font.rb
-- lib/pdf/reader/parser.rb
+- examples/page_counter_improved.rb
+- examples/extract_images.rb
+- lib/pdf/reader/glyphlist.txt
 - lib/pdf/reader/error.rb
+- lib/pdf/reader/font.rb
+- lib/pdf/reader/lzw.rb
+- lib/pdf/reader/print_receiver.rb
+- lib/pdf/reader/reference.rb
 - lib/pdf/reader/filter.rb
-- lib/pdf/reader/object_hash.rb
+- lib/pdf/reader/text_receiver.rb
+- lib/pdf/reader/pages_strategy.rb
+- lib/pdf/reader/abstract_strategy.rb
+- lib/pdf/reader/page_text_receiver.rb
+- lib/pdf/reader/encoding.rb
 - lib/pdf/reader/stream.rb
+- lib/pdf/reader/register_receiver.rb
+- lib/pdf/reader/object_hash.rb
+- lib/pdf/reader/object_cache.rb
+- lib/pdf/reader/token.rb
+- lib/pdf/reader/page.rb
+- lib/pdf/reader/xref.rb
 - lib/pdf/reader/cmap.rb
 - lib/pdf/reader/object_stream.rb
-- lib/pdf/reader/encoding.rb
-- lib/pdf/reader/text_receiver.rb
-- lib/pdf/reader/glyphlist.txt
-- lib/pdf/reader/lzw.rb
-- lib/pdf/reader/register_receiver.rb
-- lib/pdf/reader/abstract_strategy.rb
-- lib/pdf/reader/pages_strategy.rb
-- lib/pdf/reader/reference.rb
+- lib/pdf/reader/metadata_strategy.rb
+- lib/pdf/reader/buffer.rb
+- lib/pdf/reader/encodings/zapf_dingbats.txt
 - lib/pdf/reader/encodings/standard.txt
 - lib/pdf/reader/encodings/mac_roman.txt
-- lib/pdf/reader/encodings/symbol.txt
+- lib/pdf/reader/encodings/mac_expert.txt
 - lib/pdf/reader/encodings/win_ansi.txt
-- lib/pdf/reader/encodings/zapf_dingbats.txt
+- lib/pdf/reader/encodings/symbol.txt
 - lib/pdf/reader/encodings/pdf_doc.txt
-- lib/pdf/reader/encodings/mac_expert.txt
-- lib/pdf/reader/metadata_strategy.rb
-- lib/pdf/reader/token.rb
+- lib/pdf/reader/parser.rb
+- lib/pdf/hash.rb
+- lib/pdf/reader.rb
 - lib/pdf-reader.rb
 - Rakefile
 - README.rdoc
@@ -140,7 +144,7 @@ has_rdoc: true
 homepage: http://github.com/yob/pdf-reader
 licenses: []
 
-post_install_message: 
+post_install_message: "\n  ********************************************\n\n  This is an alpha release of PDF::Reader to gather feedback on the proposed\n  API changes.\n\n  The old API is marked as deprecated but will continue to work with no\n  visible warnings for now.\n\n  The new API is documented in the README and in rdoc for the PDF::Reader,\n  PDF::Reader::Page and PDF::Reader::ObjectHash classes.\n\n  Do not use this in production, stick to stable releases for that. If you do\n  take the new API for a spin, please send any feedback my way.\n\n  ********************************************\n\n"
 rdoc_options: 
 - --title
 - PDF::Reader Documentation
@@ -162,11 +166,13 @@ required_ruby_version: !ruby/object:Gem::Requirement
 required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
   requirements: 
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version 
       segments: 
-      - 0
-      version: "0"
+      - 1
+      - 3
+      - 1
+      version: 1.3.1
 requirements: []
 
 rubyforge_project: