pdf-reader 2.1.0 → 2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b1e63414d8a3db12b6ea802fc45893ebf35c09dd37ca02c5cc73137d7d782364
-  data.tar.gz: afb778860a3dd8aab83d634c393666e159101505aba843262f61f7af49cf30e5
+  metadata.gz: cfc4ed13692a51d8b78fc181d67fcf8b5e00fb1679dbca36137961f63365edaf
+  data.tar.gz: de5556fabc41642746fd242a2623c92c9424c56da2d845507c49624c312b646b
 SHA512:
-  metadata.gz: 1c32f7ac1b0d9f0d27ec445905af7dce3544d505221d6b940b8f5f37f85eaf95fad81d40850c85788dc459b59dd1f58398b27e9ec8e72bdbb077e94f77e9f332
-  data.tar.gz: 88bdd1bebe08ad919344788a9a7416e782c7fb5185ef984447ab1f9c968a8fb6a24af2b95dec99da2b43d4d4861a64ba1e8584f0ec25d01c3c13ae4f81f0191c
+  metadata.gz: 4074d5dd87f1ad9286f4022ad46a4160f44c6afed2341f9115029770770ae80b248ace9a8d5df0e444046bed662f9aa5a9334822b23222abec9574523d9e7c36
+  data.tar.gz: a69837921f7581d2aeb9226d0791b4b0dd5925a9f83e9cb4cee4dbaf43af33e6a7a570292650a14006ffc9d1759f2ea4ef268381e5aa63fc6da5c1a6d38f46a7

data/CHANGELOG

@@ -1,4 +1,9 @@
-v2.1.0 (15th Februar 2018)
+v2.2.0 (18th December 2018)
+- Support additional XRef Stream variants (thanks Stefan Wienert)
+- Add frozen_strings pragma to reduce object allocations on ruby 2.3+
+- various bug fixes
+
+v2.1.0 (15th February 2018)
 - Support extra encrypted PDF variants (thanks to Gyuchang Jun)
 - various bug fixes
 

data/lib/pdf-reader.rb

@@ -1,3 +1,4 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require "pdf/reader"

data/lib/pdf/hash.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 module PDF
   # This class is deprecated, please stop using it.

data/lib/pdf/reader.rb

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

data/lib/pdf/reader/buffer.rb

@@ -1,4 +1,5 @@
 # coding: ASCII-8BIT
+# frozen_string_literal: true
 
 ################################################################################
 #
@@ -225,7 +226,7 @@ class PDF::Reader
     end
 
     def prepare_inline_token
-      str = ""
+      str = "".dup
 
       buffer = []
 
@@ -248,7 +249,7 @@ class PDF::Reader
     # we find a closing >
     #
     def prepare_hex_token
-      str = ""
+      str = "".dup
       finished = false
 
       while !finished
@@ -278,7 +279,7 @@ class PDF::Reader
     # problem.
     #
     def prepare_literal_token
-      str = ""
+      str = "".dup
       count = 1
 
       while count > 0
@@ -308,7 +309,7 @@ class PDF::Reader
     # to read up on it.
     #
     def prepare_regular_token
-      tok = ""
+      tok = "".dup
 
       while byte = @io.getbyte
         case byte
@@ -327,7 +328,7 @@ class PDF::Reader
           while TOKEN_WHITESPACE.include?(peek_byte) && tok.size == 0
             @io.getbyte
           end
-          tok = ""
+          tok = "".dup
           break
         when 0x3C
           # opening delimiter '<', start of new token
@@ -338,7 +339,7 @@ class PDF::Reader
           else
             @tokens << "<"
           end
-          tok = ""
+          tok = "".dup
           break
         when 0x3E
           # closing delimiter '>', start of new token
@@ -349,26 +350,26 @@ class PDF::Reader
           else
             @tokens << ">"
           end
-          tok = ""
+          tok = "".dup
           break
         when 0x28, 0x5B, 0x7B
           # opening delimiter, start of new token
           @tokens << tok if tok.size > 0
           @tokens << byte.chr
-          tok = ""
+          tok = "".dup
           break
         when 0x29, 0x5D, 0x7D
           # closing delimiter
           @tokens << tok if tok.size > 0
           @tokens << byte.chr
-          tok = ""
+          tok = "".dup
           break
         when 0x2F
           # PDF name, start of new token
           @tokens << tok if tok.size > 0
           @tokens << byte.chr
           @tokens << "" if byte == 0x2F && ([nil, 0x20, 0x0A] + TOKEN_DELIMITER).include?(peek_byte)
-          tok = ""
+          tok = "".dup
           break
         else
           tok << byte

data/lib/pdf/reader/cid_widths.rb

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

data/lib/pdf/reader/cmap.rb

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

data/lib/pdf/reader/encoding.rb

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

data/lib/pdf/reader/error.rb

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

data/lib/pdf/reader/filter.rb

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

data/lib/pdf/reader/filter/ascii85.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'ascii85'
 

data/lib/pdf/reader/filter/ascii_hex.rb

@@ -1,4 +1,6 @@
 # coding: utf-8
+# frozen_string_literal: true
+
 #
 class PDF::Reader
   module Filter # :nodoc:

data/lib/pdf/reader/filter/depredict.rb

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

data/lib/pdf/reader/filter/flate.rb

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

data/lib/pdf/reader/filter/lzw.rb

@@ -1,4 +1,6 @@
 # coding: utf-8
+# frozen_string_literal: true
+
 #
 class PDF::Reader
   module Filter # :nodoc:

data/lib/pdf/reader/filter/null.rb

@@ -1,4 +1,6 @@
 # coding: utf-8
+# frozen_string_literal: true
+
 #
 class PDF::Reader
   module Filter # :nodoc:

data/lib/pdf/reader/filter/run_length.rb

@@ -1,4 +1,6 @@
 # coding: utf-8
+# frozen_string_literal: true
+
 #
 class PDF::Reader # :nodoc:
   module Filter # :nodoc:
@@ -12,7 +14,7 @@ class PDF::Reader # :nodoc:
       # Decode the specified data with the RunLengthDecode compression algorithm
       def filter(data)
         pos = 0
-        out = ""
+        out = "".dup
 
         while pos < data.length
           length = data.getbyte(pos)

data/lib/pdf/reader/font.rb

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

data/lib/pdf/reader/font_descriptor.rb

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

data/lib/pdf/reader/form_xobject.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'digest/md5'
 

data/lib/pdf/reader/glyph_hash.rb

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

data/lib/pdf/reader/lzw.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 module PDF
 
@@ -82,7 +83,7 @@ module PDF
       #
       def self.decode(data)
         stream = BitStream.new data.to_s, 9 # size of codes between 9 and 12 bits
-        result = ''
+        result = "".dup
         until (code = stream.read) == CODE_EOD
           if code == CODE_CLEAR_TABLE
             stream.set_bits_in_chunk(9)

data/lib/pdf/reader/null_security_handler.rb

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

data/lib/pdf/reader/object_cache.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'hashery/lru_hash'
 

data/lib/pdf/reader/object_hash.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   # Provides low level access to the objects in a PDF file via a hash-like

data/lib/pdf/reader/object_stream.rb

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

data/lib/pdf/reader/orientation_detector.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 class PDF::Reader
   # Small util class for detecting the orientation of a single PDF page. Accounts

data/lib/pdf/reader/page.rb

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

data/lib/pdf/reader/page_layout.rb

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

data/lib/pdf/reader/page_state.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 
 require 'pdf/reader/transformation_matrix'
 

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'

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.

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'

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
     ################################################################################

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.1.0
+  version: 2.2.0
 platform: ruby
 authors:
 - James Healy
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-02-15 00:00:00.000000000 Z
+date: 2018-12-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -296,7 +296,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.3
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: A library for accessing the content of PDF files