pdf-reader 2.2.1 → 2.5.0

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)
@@ -28,23 +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)
-
-          m = names.map { |name|
-            @metrics.char_metrics[name.to_s]
-          }.compact.first
-        end
+        names = @font.encoding.int_to_name(code_point)
+        metrics = names.map { |name|
+          @metrics.char_metrics[name.to_s]
+        }.compact.first
 
-        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
 
@@ -54,6 +55,13 @@ 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/xref.rb

@@ -230,18 +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: 2.2.1
+  version: 2.5.0
 platform: ruby
 authors:
 - James Healy
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-07-27 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
@@ -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
@@ -271,11 +272,15 @@ 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: {}
-post_install_message: 
+metadata:
+  bug_tracker_uri: https://github.com/yob/pdf-reader/issues
+  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
@@ -288,15 +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: 3.0.1
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: A library for accessing the content of PDF files
 test_files: []

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