pdf-reader 2.3.0 → 2.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 419ef1c2770f8cff11f2ee6453f70cec80562eddb7912ddd618013c5c013bcad
-  data.tar.gz: 71a7a814472b527b7a03e24d4923893962a8c0a1748e0d9007eb5cd7c8bbf7b3
+  metadata.gz: c1acf8110733b6aff447e40353cc7d847e6edbb9bad016beab35bebe191bc91a
+  data.tar.gz: 1e50a894289d9c4f8df83bcf55e1f0bfe9e7c3088365705bea9b253a34a9254e
 SHA512:
-  metadata.gz: 4a5d4e76a74a766ceae3960587efce9aa63600c1b78b16175e9b41b58435d1c766871c2b288e79edec1499444aa12c786937eda70634bf301cd05ad8f2373063
-  data.tar.gz: 7e7bf8f2bb43822a64f89ca46bf0369a1e34b0e60078483ad1d4cf774ef6c6122f689b765f41d02a2120eafeba30fd47bb2cbd1b0dd5c56e7cf556648b3f4e33
+  metadata.gz: 473d030dd4e12e6aba2e037fe7b73410e99f14112ddd7823483056281cdd89e6865efb1f02866760038f892b7d60f153db8c88643d73035ee354e43d1cf047c5
+  data.tar.gz: 30d842ae8260a8a2005b484c9550ae04a77e23b17e36b324e36e6d6faa4a7e0f83ebdab7cc69b504e143740ebcb9fad341e5ca8c0b0b6339fa826634f94996e2

data/CHANGELOG

@@ -1,3 +1,12 @@
+v2.4.0 (21st November 2019)
+- Optimise overlapping characters code introduced in 2.3.0. Text extraction of pages with
+  thousands of characters is still slower than it was in 2.2.1, but it might tolerable
+  for now. See https://github.com/yob/pdf-reader/pull/308 for details.
+- Implement very basic font substitution for Type1 and TrueType fonts that aren't embedded
+- Remove PDF::Hash class. It's been deprecated since 2010, and it's hard to believe anyone
+  is still using it.
+- Several small bug fixes
+
 v2.3.0 (7th November 2019)
 - Text extraction now makes an effort to skip duplicate characters that overlap, a
   common approach used for a fake "bold" effect, This will make text extraction a bit

data/README.md

@@ -1,4 +1,4 @@
-# Release Notes
+# pdf-reader
 
 The PDF::Reader library implements a PDF parser conforming as much as possible
 to the PDF specification from Adobe.

data/bin/pdf_callbacks

@@ -9,7 +9,7 @@ require 'pdf/reader'
 receiver = PDF::Reader::PrintReceiver.new
 
 if ARGV.empty?
-  browser = PDF::Reader.new($stdin)
+  browser = PDF::Reader.new(StringIO.new(ARGF.read))
 else
   browser = PDF::Reader.new(ARGV[0])
 end

data/bin/pdf_text

@@ -4,7 +4,7 @@ require 'rubygems'
 require 'pdf/reader'
 
 if ARGV.empty?
-  browser = PDF::Reader.new($stdin)
+  browser = PDF::Reader.new(StringIO.new(ARGF.read))
 else
   browser = PDF::Reader.new(ARGV[0])
 end

data/lib/pdf/reader.rb

@@ -180,7 +180,7 @@ module PDF
       (1..self.page_count).map do |num|
         begin
           PDF::Reader::Page.new(@objects, num, :cache => @cache)
-        rescue InvalidPageError => ex
+        rescue InvalidPageError
           raise MalformedPDFError, "Missing data for page: #{num}"
         end
       end
@@ -301,4 +301,3 @@ require 'pdf/reader/token'
 require 'pdf/reader/xref'
 require 'pdf/reader/orientation_detector'
 require 'pdf/reader/page'
-require 'pdf/hash'

data/lib/pdf/reader/encoding.rb

@@ -42,10 +42,10 @@ class PDF::Reader
 
       @enc_name = if enc.kind_of?(Hash)
         enc[:Encoding] || enc[:BaseEncoding]
-      elsif enc != nil
+      elsif enc && enc.respond_to?(:to_sym)
         enc.to_sym
       else
-        nil
+        :StandardEncoding
       end
 
       @unpack   = get_unpack(@enc_name)

data/lib/pdf/reader/font.rb

@@ -97,7 +97,13 @@ class PDF::Reader
       elsif @subtype == :Type3
         PDF::Reader::WidthCalculator::TypeOneOrThree.new(self)
       elsif @subtype == :TrueType
-        PDF::Reader::WidthCalculator::TrueType.new(self)
+        if @font_descriptor
+          PDF::Reader::WidthCalculator::TrueType.new(self)
+        else
+          # A TrueType font that isn't embedded. Most readers look for a version on the
+          # local system and fallback to a substitute. For now, we go straight to a substitute
+          PDF::Reader::WidthCalculator::BuiltIn.new(self)
+        end
       elsif @subtype == :CIDFontType0 || @subtype == :CIDFontType2
         PDF::Reader::WidthCalculator::Composite.new(self)
       else

data/lib/pdf/reader/overlapping_runs_filter.rb

@@ -21,27 +21,26 @@ class PDF::Reader
 
       event_point_schedule.sort! { |a,b| a.x <=> b.x }
 
-      while not event_point_schedule.empty? do
-        event_point = event_point_schedule.shift
-        break unless event_point
+      event_point_schedule.each do |event_point|
+        run = event_point.run
 
-        if event_point.start? then
+        if event_point.start?
           if detect_intersection(sweep_line_status, event_point)
-            to_exclude << event_point.run
+            to_exclude << run
           end
-          sweep_line_status.push event_point
+          sweep_line_status.push(run)
         else
-          sweep_line_status.delete event_point
+          sweep_line_status.delete(run)
         end
       end
       runs - to_exclude
     end
 
     def self.detect_intersection(sweep_line_status, event_point)
-      sweep_line_status.each do |point_in_sls|
-        if event_point.x >= point_in_sls.run.x &&
-            event_point.x <= point_in_sls.run.endx &&
-            point_in_sls.run.intersection_area_percent(event_point.run) >= OVERLAPPING_THRESHOLD
+      sweep_line_status.each do |open_text_run|
+        if event_point.x >= open_text_run.x &&
+            event_point.x <= open_text_run.endx &&
+            open_text_run.intersection_area_percent(event_point.run) >= OVERLAPPING_THRESHOLD
           return true
         end
       end

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

@@ -12,11 +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)
@@ -54,6 +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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 2.4.0
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-07 00:00:00.000000000 Z
+date: 2019-11-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -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
@@ -272,10 +271,14 @@ 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/v2.4.0/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: 
 rdoc_options:
 - "--title"

data/lib/pdf/hash.rb

@@ -1,20 +0,0 @@
-# coding: utf-8
-# frozen_string_literal: true
-
-module PDF
-  # This class is deprecated, please stop using it.
-  class Hash < ::PDF::Reader::ObjectHash # :nodoc:
-    def initialize(input)
-      warn "DEPRECATION NOTICE: PDF::Hash has been deprecated, use PDF::Reader::ObjectHash instead"
-      super
-    end
-
-    def version
-      warn <<-EOS
-        DEPRECATION NOTICE: PDF::Hash#version has been deprecated,
-        use PDF::Reader::ObjectHash#pdf_version instead
-      EOS
-      pdf_version
-    end
-  end
-end