pdf-reader 2.1.0 → 2.4.1

data/lib/pdf/reader/page_layout.rb

@@ -1,4 +1,7 @@
 # coding: utf-8
+# frozen_string_literal: true
+
+require 'pdf/reader/overlapping_runs_filter'
 
 class PDF::Reader
 
@@ -14,13 +17,15 @@ class PDF::Reader
     def initialize(runs, mediabox)
       raise ArgumentError, "a mediabox must be provided" if mediabox.nil?
 
-      @runs    = merge_runs(runs)
+      @runs    = merge_runs(OverlappingRunsFilter.exclude_redundant_runs(runs))
       @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
@@ -29,7 +34,7 @@ class PDF::Reader
       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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'pdf/reader/transformation_matrix'
 
@@ -29,7 +30,15 @@ class PDF::Reader
         @xobject_stack = [page.xobjects]
         @cs_stack      = [page.color_spaces]
         @stack         = [DEFAULT_GRAPHICS_STATE.dup]
-        state[:ctm]    = identity_matrix
+        if page.rotate == 0
+          state[:ctm]  = identity_matrix
+        else
+          rotate_cos = Math.cos(page.rotate * (Math::PI/180.0)).round(2)
+          rotate_sin = Math.sin(page.rotate * (Math::PI/180.0)).round(2)
+          state[:ctm] = TransformationMatrix.new(rotate_cos, rotate_sin,
+                                                 rotate_sin * -1, rotate_cos,
+                                                 0, 0)
+        end
       end
 
       #####################################################

data/lib/pdf/reader/page_text_receiver.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'forwardable'
 require 'pdf/reader/page_layout'
@@ -43,10 +44,13 @@ module PDF
         @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
 
       #####################################################

data/lib/pdf/reader/pages_strategy.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #

data/lib/pdf/reader/parser.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #
@@ -132,7 +133,7 @@ class PDF::Reader
     # reads a PDF name from the buffer and converts it to a Ruby Symbol
     def pdf_name
       tok = @buffer.token
-      tok.gsub!(/#([A-Fa-f0-9]{2})/) do |match|
+      tok = tok.dup.gsub(/#([A-Fa-f0-9]{2})/) do |match|
         match[1, 2].hex.chr
       end
       tok.to_sym
@@ -154,7 +155,7 @@ class PDF::Reader
     ################################################################################
     # Reads a PDF hex string from the buffer and converts it to a Ruby String
     def hex_string
-      str = ""
+      str = "".dup
 
       loop do
         token = @buffer.token
@@ -171,11 +172,11 @@ class PDF::Reader
     # Reads a PDF String from the buffer and converts it to a Ruby String
     def string
       str = @buffer.token
-      return "".force_encoding("binary") if str == ")"
+      return "".dup.force_encoding("binary") if str == ")"
       Error.assert_equal(parse_token, ")")
 
       str.gsub!(/\\([nrtbf()\\\n]|\d{1,3})?|\r\n?|\n\r/m) do |match|
-        MAPPING[match] || ""
+        MAPPING[match] || "".dup
       end
       str.force_encoding("binary")
     end

data/lib/pdf/reader/print_receiver.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   # A simple receiver that prints all operaters and parameters in the content

data/lib/pdf/reader/reference.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #

data/lib/pdf/reader/register_receiver.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 # Copyright (C) 2010 James Healy (jimmy@deefa.com)
 

data/lib/pdf/reader/resource_methods.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 module PDF
   class Reader

data/lib/pdf/reader/standard_security_handler.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #

data/lib/pdf/reader/standard_security_handler_v5.rb

@@ -1,4 +1,6 @@
 # coding: utf-8
+# frozen_string_literal: true
+
 require 'digest'
 require 'openssl'
 

data/lib/pdf/reader/stream.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #

data/lib/pdf/reader/synchronized_cache.rb

@@ -1,4 +1,5 @@
 # encoding: utf-8
+# frozen_string_literal: true
 
 # utilities.rb : General-purpose utility classes which don't fit anywhere else
 #

data/lib/pdf/reader/text_run.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   # A value object that represents one or more consecutive characters on a page.
@@ -37,6 +38,10 @@ class PDF::Reader
       @endx ||= x + width
     end
 
+    def endy
+      @endy ||= y + font_size
+    end
+
     def mean_character_width
       @width / character_count
     end
@@ -59,8 +64,28 @@ class PDF::Reader
       "#{text} w:#{width} f:#{font_size} @#{x},#{y}"
     end
 
+    def intersect?(other_run)
+      x <= other_run.endx && endx >= other_run.x &&
+        endy >= other_run.y && y <= other_run.endy
+    end
+
+    # return what percentage of this text run is overlapped by another run
+    def intersection_area_percent(other_run)
+      return 0 unless intersect?(other_run)
+
+      dx = [endx, other_run.endx].min - [x, other_run.x].max
+      dy = [endy, other_run.endy].min - [y, other_run.y].max
+      intersection_area = dx*dy
+
+      intersection_area.to_f / area
+    end
+
     private
 
+    def area
+      (endx - x) * (endy - y)
+    end
+
     def mergable_range
       @mergable_range ||= Range.new(endx - 3, endx + font_size)
     end

data/lib/pdf/reader/token.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #

data/lib/pdf/reader/transformation_matrix.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   # co-ordinate systems in PDF files are specified using a 3x3 matrix that looks

data/lib/pdf/reader/unimplemented_security_handler.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
 

data/lib/pdf/reader/width_calculator.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 # PDF files may define fonts in a number of ways. Each approach means we must
 # calculate glyph widths differently, so this set of classes conform to an

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'afm'
 require 'pdf/reader/synchronized_cache'
@@ -11,11 +12,20 @@ class PDF::Reader
     # see Section 9.6.2.2, PDF 32000-1:2008, pp 256
     class BuiltIn
 
+      BUILTINS = [
+        :Courier, :"Courier-Bold", :"Courier-BoldOblique", :"Courier-Oblique",
+        :Helvetica, :"Helvetica-Bold", :"Helvetica-BoldOblique", :"Helvetica-Oblique",
+        :Symbol,
+        :"Times-Roman", :"Times-Bold", :"Times-BoldItalic", :"Times-Italic",
+        :ZapfDingbats
+      ]
+
       def initialize(font)
         @font = font
         @@all_metrics ||= PDF::Reader::SynchronizedCache.new
 
-        metrics_path = File.join(File.dirname(__FILE__), "..","afm","#{font.basefont}.afm")
+        basefont = extract_basefont(font.basefont)
+        metrics_path = File.join(File.dirname(__FILE__), "..","afm","#{basefont}.afm")
 
         if File.file?(metrics_path)
           @metrics = @@all_metrics[metrics_path] ||= AFM::Font.new(metrics_path)
@@ -53,6 +63,13 @@ class PDF::Reader
         @font.encoding.int_to_name(code_point).first.to_s[/\Acontrol..\Z/]
       end
 
+      def extract_basefont(font_name)
+        if BUILTINS.include?(font_name)
+          font_name
+        else
+          "Times-Roman"
+        end
+      end
     end
   end
 end

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   module WidthCalculator

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   module WidthCalculator
@@ -17,8 +18,7 @@ class PDF::Reader
 
       def glyph_width(code_point)
         return 0 if code_point.nil? || code_point < 0
-
-        glyph_width_from_font(code_point) || glyph_width_from_descriptor(code_point)
+        glyph_width_from_font(code_point) || glyph_width_from_descriptor(code_point) || 0
       end
 
       private

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   module WidthCalculator

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   module WidthCalculator

data/lib/pdf/reader/xref.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 ################################################################################
 #
@@ -203,8 +204,10 @@ class PDF::Reader
         ("\x00" + bytes).unpack("N")[0]
       elsif bytes.size == 4
         bytes.unpack("N")[0]
+      elsif bytes.size == 8
+        bytes.unpack("Q>")[0]
       else
-        raise UnsupportedFeatureError, "Unable to unpack xref stream entries with more than 4 bytes"
+        raise UnsupportedFeatureError, "Unable to unpack xref stream entries of #{bytes.size} bytes"
       end
     end
     ################################################################################
@@ -227,18 +230,21 @@ class PDF::Reader
     # should always be 0, but all sort of crazy junk is prefixed to PDF files
     # in the real world.
     #
-    # Checks up to 50 chars into the file, returns nil if no PDF data detected.
+    # Checks up to 1024 chars into the file,
+    # returns nil if no PDF data detected.
+    # Adobe PDF 1.4 spec (3.4.1) 12. Acrobat viewers require only that the
+    # header appear somewhere within the first 1024 bytes of the file
     #
     def calc_junk_offset(io)
       io.rewind
       offset = io.pos
-      until (c = io.readchar) == '%' || c == 37 || offset > 50
+      until (c = io.readchar) == '%' || c == 37 || offset > 1024
         offset += 1
       end
       io.rewind
-      offset < 50 ? offset : nil
+      offset < 1024 ? offset : nil
     rescue EOFError
-      return nil
+      nil
     end
   end
   ################################################################################

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.1.0
+  version: 2.4.1
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-02-15 00:00:00.000000000 Z
+date: 2020-09-24 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:
     - - ">="
@@ -167,7 +167,7 @@ dependencies:
 description: The PDF::Reader library implements a PDF parser conforming as much as
   possible to the PDF specification from Adobe
 email:
-- jimmy@deefa.com
+- james@yob.id.au
 executables:
 - pdf_object
 - pdf_text
@@ -199,7 +199,6 @@ files:
 - examples/text.rb
 - examples/version.rb
 - lib/pdf-reader.rb
-- lib/pdf/hash.rb
 - lib/pdf/reader.rb
 - lib/pdf/reader/afm/Courier-Bold.afm
 - lib/pdf/reader/afm/Courier-BoldOblique.afm
@@ -209,6 +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
@@ -246,6 +246,7 @@ files:
 - lib/pdf/reader/object_hash.rb
 - lib/pdf/reader/object_stream.rb
 - lib/pdf/reader/orientation_detector.rb
+- lib/pdf/reader/overlapping_runs_filter.rb
 - lib/pdf/reader/page.rb
 - lib/pdf/reader/page_layout.rb
 - lib/pdf/reader/page_state.rb
@@ -271,10 +272,14 @@ files:
 - lib/pdf/reader/width_calculator/type_one_or_three.rb
 - lib/pdf/reader/width_calculator/type_zero.rb
 - lib/pdf/reader/xref.rb
-homepage: http://github.com/yob/pdf-reader
+homepage: https://github.com/yob/pdf-reader
 licenses:
 - MIT
-metadata: {}
+metadata:
+  bug_tracker_uri: https://github.com/yob/pdf-reader/issues
+  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.4.1/CHANGELOG
+  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.4.1
+  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.4.1
 post_install_message: 
 rdoc_options:
 - "--title"
@@ -295,8 +300,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.3
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: A library for accessing the content of PDF files