pdf-reader 1.4.1 → 2.0.0.beta1

data/lib/pdf/reader/parser.rb

@@ -118,6 +118,7 @@ class PDF::Reader
       loop do
         key = parse_token
         break if key.kind_of?(Token) and key == ">>"
+        raise MalformedPDFError, "unterminated dict" if @buffer.empty?
         raise MalformedPDFError, "Dictionary key (#{key.inspect}) is not a name" unless key.kind_of?(Symbol)
 
         value = parse_token
@@ -131,7 +132,6 @@ class PDF::Reader
     # reads a PDF name from the buffer and converts it to a Ruby Symbol
     def pdf_name
       tok = @buffer.token
-      tok = " " if tok == "" && RUBY_VERSION < "1.9"
       tok.gsub!(/#([A-Fa-f0-9]{2})/) do |match|
         match[1, 2].hex.chr
       end
@@ -145,6 +145,7 @@ class PDF::Reader
       loop do
         item = parse_token
         break if item.kind_of?(Token) and item == "]"
+        raise MalformedPDFError, "unterminated array" if @buffer.empty?
         a << item
       end
 
@@ -158,24 +159,25 @@ class PDF::Reader
       loop do
         token = @buffer.token
         break if token == ">"
+        raise MalformedPDFError, "unterminated hex string" if @buffer.empty?
         str << token
       end
 
       # add a missing digit if required, as required by the spec
       str << "0" unless str.size % 2 == 0
-      str.scan(/../).map {|i| i.hex.chr}.join
+      str.scan(/../).map {|i| i.hex.chr}.join.force_encoding("binary")
     end
     ################################################################################
     # Reads a PDF String from the buffer and converts it to a Ruby String
     def string
       str = @buffer.token
-      return "" if str == ")"
+      return "".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] || ""
       end
-      str
+      str.force_encoding("binary")
     end
 
     MAPPING = {

data/lib/pdf/reader/standard_security_handler.rb

@@ -82,7 +82,7 @@ class PDF::Reader
       (0..2).each { |e| objKey << (ref.id >> e*8 & 0xFF ) }
       (0..1).each { |e| objKey << (ref.gen >> e*8 & 0xFF ) }
       length = objKey.length < 16 ? objKey.length : 16
-      rc4 = RC4.new( Digest::MD5.digest(objKey)[(0...length)] )
+      rc4 = RC4.new( Digest::MD5.digest(objKey)[0,length] )
       rc4.decrypt(buf)
     end
 
@@ -94,7 +94,7 @@ class PDF::Reader
       if p.nil? || p.empty?
         PassPadBytes.pack('C*')
       else
-        p[(0...32)] + PassPadBytes[0...(32-p.length)].pack('C*')
+        p[0, 32] + PassPadBytes[0, 32-p.length].pack('C*')
       end
     end
 
@@ -118,13 +118,13 @@ class PDF::Reader
       md5 = Digest::MD5.digest(pad_pass(pass))
       if @revision > 2 then
         50.times { md5 = Digest::MD5.digest(md5) }
-        keyBegins = md5[(0...@key_length)]
+        keyBegins = md5[0, key_length]
         #first itteration decrypt owner_key
         out = @owner_key
         #RC4 keyed with (keyBegins XOR with itteration #) to decrypt previous out
         19.downto(0).each { |i| out=RC4.new(xor_each_byte(keyBegins,i)).decrypt(out) }
       else
-        out = RC4.new( md5[(0...5)] ).decrypt( @owner_key )
+        out = RC4.new( md5[0, 5] ).decrypt( @owner_key )
       end
       # c) check output as user password
       auth_user_pass( out )
@@ -142,12 +142,12 @@ class PDF::Reader
     #
     def auth_user_pass(pass)
       keyBegins = make_file_key(pass)
-      if @revision > 2
+      if @revision >= 3
         #initialize out for first iteration
         out = Digest::MD5.digest(PassPadBytes.pack("C*") + @file_id)
         #zero doesn't matter -> so from 0-19
-        20.times{ |i| out=RC4.new(xor_each_byte(keyBegins, i)).decrypt(out) }
-        pass = @user_key[(0...16)] == out
+        20.times{ |i| out=RC4.new(xor_each_byte(keyBegins, i)).encrypt(out) }
+        pass = @user_key[0, 16] == out
       else
         pass = RC4.new(keyBegins).encrypt(PassPadBytes.pack("C*")) == @user_key
       end
@@ -163,20 +163,24 @@ class PDF::Reader
       (0..24).step(8){|e| @buf << (@permissions >> e & 0xFF)}
       # e) add the file ID
       @buf << @file_id
-      # f) if revision > 4 then if encryptMetadata add 4 bytes of 0x00 else add 4 bytes of 0xFF
-      if @revision > 4
-        @buf << [ @encryptMetadata ? 0x00 : 0xFF ].pack('C')*4
+      # f) if revision >= 4 and metadata not encrypted then add 4 bytes of 0xFF
+      if @revision >= 4 && !@encryptMeta
+        @buf << [0xFF,0xFF,0xFF,0xFF].pack('C*')
       end
       # b) init MD5 digest + g) finish the hash
       md5 = Digest::MD5.digest(@buf)
       # h) spin hash 50 times
-      if @revision > 2
+      if @revision >= 3
         50.times {
-          md5 = Digest::MD5.digest(md5[(0...@key_length)])
+          md5 = Digest::MD5.digest(md5[0, @key_length])
         }
       end
-      # i) n = key_length revision > 3, n = 5 revision == 2
-      md5[(0...((@revision < 3) ? 5 : @key_length))]
+      # i) n = key_length revision >= 3, n = 5 revision == 2
+      if @revision < 3
+        md5[0, 5]
+      else
+        md5[0, @key_length]
+      end
     end
 
     def build_standard_key(pass)

data/lib/pdf/reader/text_run.rb

@@ -65,16 +65,10 @@ class PDF::Reader
       @mergable_range ||= Range.new(endx - 3, endx + font_size)
     end
 
+    # Assume string encoding is marked correctly and we can trust String#size to return a
+    # character count
     def character_count
-      if @text.size == 1
-        1.0
-      elsif @text.respond_to?(:bytesize)
-        # M17N aware VM
-        # so we can trust String#size to return a character count
-        @text.size.to_f
-      else
-        text.unpack("U*").size.to_f
-      end
+      @text.size.to_f
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 1.4.1
+  version: 2.0.0.beta1
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-01-01 00:00:00.000000000 Z
+date: 2017-02-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -30,28 +30,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
+        version: '3.5'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.4'
-- !ruby/object:Gem::Dependency
-  name: ZenTest
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 4.4.2
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: 4.4.2
+        version: '3.5'
 - !ruby/object:Gem::Dependency
   name: cane
   requirement: !ruby/object:Gem::Requirement
@@ -70,16 +56,16 @@ dependencies:
   name: morecane
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.2'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '0.2'
 - !ruby/object:Gem::Dependency
   name: ir_b
   requirement: !ruby/object:Gem::Requirement
@@ -185,22 +171,20 @@ email:
 executables:
 - pdf_object
 - pdf_text
-- pdf_list_callbacks
 - pdf_callbacks
 extensions: []
 extra_rdoc_files:
-- README.rdoc
+- README.md
 - TODO
 - CHANGELOG
 - MIT-LICENSE
 files:
 - CHANGELOG
 - MIT-LICENSE
-- README.rdoc
+- README.md
 - Rakefile
 - TODO
 - bin/pdf_callbacks
-- bin/pdf_list_callbacks
 - bin/pdf_object
 - bin/pdf_text
 - examples/callbacks.rb
@@ -217,7 +201,6 @@ files:
 - lib/pdf-reader.rb
 - lib/pdf/hash.rb
 - lib/pdf/reader.rb
-- lib/pdf/reader/abstract_strategy.rb
 - lib/pdf/reader/afm/Courier-Bold.afm
 - lib/pdf/reader/afm/Courier-BoldOblique.afm
 - lib/pdf/reader/afm/Courier-Oblique.afm
@@ -258,7 +241,6 @@ files:
 - lib/pdf/reader/glyph_hash.rb
 - lib/pdf/reader/glyphlist.txt
 - lib/pdf/reader/lzw.rb
-- lib/pdf/reader/metadata_strategy.rb
 - lib/pdf/reader/object_cache.rb
 - lib/pdf/reader/object_hash.rb
 - lib/pdf/reader/object_stream.rb
@@ -276,7 +258,6 @@ files:
 - lib/pdf/reader/standard_security_handler.rb
 - lib/pdf/reader/stream.rb
 - lib/pdf/reader/synchronized_cache.rb
-- lib/pdf/reader/text_receiver.rb
 - lib/pdf/reader/text_run.rb
 - lib/pdf/reader/token.rb
 - lib/pdf/reader/transformation_matrix.rb
@@ -291,26 +272,12 @@ homepage: http://github.com/yob/pdf-reader
 licenses:
 - MIT
 metadata: {}
-post_install_message: |2+
-
-    ********************************************
-
-    v1.0.0 of PDF::Reader introduced a new page-based API. There are extensive
-    examples showing how to use it in the README and examples directory.
-
-    For detailed documentation, check the rdocs for the PDF::Reader,
-    PDF::Reader::Page and PDF::Reader::ObjectHash classes.
-
-    The old API is marked as deprecated but will continue to work with no
-    visible warnings for now.
-
-    ********************************************
-
+post_install_message: 
 rdoc_options:
 - "--title"
 - PDF::Reader Documentation
 - "--main"
-- README.rdoc
+- README.md
 - "-q"
 require_paths:
 - lib
@@ -321,9 +288,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: 1.9.3
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - ">="
+  - - ">"
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.5.2

data/bin/pdf_list_callbacks

@@ -1,17 +0,0 @@
-#!/usr/bin/env ruby
-
-# this executable is deprecated, use pdf_callbacks instead
-
-require 'rubygems'
-
-$LOAD_PATH.unshift(File.dirname(__FILE__) + "/../lib")
-
-require 'pdf/reader'
-
-receiver = PDF::Reader::PrintReceiver.new
-
-if ARGV.empty?
-  PDF::Reader.new.parse($stdin, receiver)
-else
-  PDF::Reader.file(ARGV[0], receiver)
-end

data/lib/pdf/reader/abstract_strategy.rb

@@ -1,81 +0,0 @@
-# coding: utf-8
-
-class PDF::Reader
-
-  # DEPRECATED: this class was deprecated in version 0.11.0 and will
-  #             eventually be removed
-  class AbstractStrategy # :nodoc:
-
-    def initialize(ohash, receivers, options = {})
-      @ohash, @options = ohash, options
-      if receivers.is_a?(Array)
-        @receivers = receivers
-      else
-        @receivers = [receivers]
-      end
-    end
-
-    private
-
-    def options
-      @options || {}
-    end
-
-    # calls the name callback method on the receiver class with params as the arguments
-    #
-    def callback(name, params=[])
-      @receivers.each do |receiver|
-        receiver.send(name, *params) if receiver.respond_to?(name)
-      end
-    end
-
-    # strings outside of page content should be in either PDFDocEncoding or UTF-16.
-    def decode_strings(obj)
-      case obj
-      when String then
-        if obj[0,2].unpack("C*").slice(0,2) == [254,255]
-          PDF::Reader::Encoding.new(:UTF16Encoding).to_utf8(obj[2, obj.size])
-        else
-          PDF::Reader::Encoding.new(:PDFDocEncoding).to_utf8(obj)
-        end
-      when Hash   then obj.each { |key,val| obj[key] = decode_strings(val) }
-      when Array  then obj.collect { |item| decode_strings(item) }
-      else
-        obj
-      end
-    end
-
-    def info
-      ohash.object(trailer[:Info])
-    end
-
-    def info?
-      info ? true : false
-    end
-
-    def ohash
-      @ohash
-    end
-
-    def pages
-      ohash.object(root[:Pages])
-    end
-
-    def pages?
-      pages ? true : false
-    end
-
-    def root
-      ohash.object(trailer[:Root])
-    end
-
-    def root?
-      root ? true : false
-    end
-
-    def trailer
-      ohash.trailer
-    end
-
-  end
-end

data/lib/pdf/reader/metadata_strategy.rb

@@ -1,56 +0,0 @@
-# coding: utf-8
-
-class PDF::Reader
-
-  # DEPRECATED: this class was deprecated in version 0.11.0 and will
-  #             eventually be removed
-  #
-  class MetadataStrategy < AbstractStrategy # :nodoc:
-
-    def self.to_sym
-      :metadata
-    end
-
-    def process
-      return false unless options[:metadata]
-
-      # may be useful to some people
-      callback(:pdf_version, ohash.pdf_version)
-
-      # ye olde metadata
-      callback(:metadata, [decoded_info]) if info?
-
-      # new style xml metadata
-      callback(:xml_metadata, [xml_metadata]) if xml_metadata?
-
-      # page count
-      if pages?
-        count = ohash.object(pages[:Count])
-        callback(:page_count, count.to_i)
-      end
-    end
-
-    private
-
-    def xml_metadata
-      return @xml_metadata if defined?(@xml_metadata)
-
-      if root[:Metadata].nil?
-        @xml_metadata = nil
-      else
-        string = ohash.object(root[:Metadata]).unfiltered_data
-        string.force_encoding("utf-8") if string.respond_to?(:force_encoding)
-        @xml_metadata = string
-      end
-    end
-
-    def xml_metadata?
-      xml_metadata ? true : false
-    end
-
-    def decoded_info
-      @decoded_info ||= decode_strings(info)
-    end
-
-  end
-end