pdf-reader 2.4.1 → 2.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2b38615953615bfbca1a80ab344f26166377d8c08d2ba2e05badf43c10682415
-  data.tar.gz: 658b5d05a14300ad056ee31c10ea998533ccb1b91600e8bc9097070605d003ea
+  metadata.gz: 5ee0d8c3c55f6a0aebb60a0a6dce92428e8371b96a6beb6d75bfe90602bffae7
+  data.tar.gz: '0911d108353bf577aa9fd7b49b97dda1cf9d54816bf8ff6c4225281eeda63229'
 SHA512:
-  metadata.gz: 210b0bee8c4ac009808555c8ba945f3b17b85af22126ac1440eb9b49d91f542f1974b0984efb22726985f2cf8e03440511ebc4664ac5c4d91a6bddea9a43687e
-  data.tar.gz: 8fb60cb59dc4430179a4b9ba83d30ae6dc23aa13dbef5e8febe1569311ddf7e531783da7e7dd0a6542f0087748e97898af56d540e7c088832f213b48059aa7d3
+  metadata.gz: 917db2b1fb977b41e7b057ff3d215b8f249577254d9fe3df72f330b32ff49630874c58f480495ddcd137d9f31d014083438623cdf7260b0d7a87bbe3a5f3685a
+  data.tar.gz: cd9832f025264e54d586e81eff69727379e8646d741f53ae61e90a5b38945d852147853891d468bab683581bdd0beb68a9b7c7f5e54e064e9a3935262ea9d651

data/CHANGELOG

@@ -1,3 +1,43 @@
+v2.7.0 (13th December 2021)
+- Include RBI type files in the gem
+  - Downstream users of pdf-reader who also use sorbet *should* find many parts of the API will
+    now be typed checked by sorbet
+- Fix glyph positioning in some rotation scenarios (http://github.com/yob/pdf-reader/pull/403)
+  - Improved text extraction on some rotated pages, and rotated text on normal pages
+- Add PDF::Reader::Page#rectangles (http://github.com/yob/pdf-reader/pull/402)
+  - Returns page boxes (MediaBox, etc) with rotation applied, and as PORO rather than arrays of numbers
+- Add PDF::Reader::Page#origin (http://github.com/yob/pdf-reader/pull/400)
+- Add PDF::Reader::Page#{height,width} (http://github.com/yob/pdf-reader/pull/399)
+- Overlap filter should only drop characters that overlap *and* match (http://github.com/yob/pdf-reader/pull/401)
+
+v2.6.0 (12th November 2021)
+- Text extraction improvements
+  - Improved text layout on pages with a variety of font sizes (http://github.com/yob/pdf-reader/pull/355)
+  - Fixed text positioning for some rotated pages (http://github.com/yob/pdf-reader/pull/356)
+  - Improved character width calculation for PDFs using built-in (non-embedded) ZapfDingbats (http://github.com/yob/pdf-reader/pull/373)
+  - Skip zero-width characters (http://github.com/yob/pdf-reader/pull/372)
+- Performance improvements
+  - Reduced memory pressure when decoding TIFF images (http://github.com/yob/pdf-reader/pull/360)
+  - Optional dependency on ascii81_native gem for faster processing of files using the ascii85 filter (http://github.com/yob/pdf-reader/pull/359)
+- Successfully parse more files
+  - Gracefully handle some non-spec compliant CR/LF issues (http://github.com/yob/pdf-reader/pull/364)
+  - Fix parsing of some escape sequences in content streams (http://github.com/yob/pdf-reader/pull/368)
+  - Increase the amount of junk bytes we detect and skip at the end of a file (382)
+  - Ignore "/Prev 0" in trailers (http://github.com/yob/pdf-reader/pull/383)
+  - Fix parsing of some inline images (BI ID EI tokens) (http://github.com/yob/pdf-reader/pull/389)
+  - Gracefully handle some xref tables that incorrectly start with 1 (http://github.com/yob/pdf-reader/pull/384)
+
+v2.5.0 (6th June 2021)
+- bump minimum ruby version to 2.0
+- Correctly handle trascoding to UTF-8 from some fonts that use a difference table [#344](https://github.com/yob/pdf-reader/pull/344/) 
+- Fix some character spacing issues with the TJ operator [#343](https://github.com/yob/pdf-reader/pull/343)
+- Fix crash with some encrypted PDFs [#348](https://github.com/yob/pdf-reader/pull/348/)
+- Fix positions of text on some PDFs with pages rotated 90° [#350](https://github.com/yob/pdf-reader/pull/350/)
+
+v2.4.2 (28th January 2021)
+- relax ASCII85 dependency to allow 1.x
+- improved support for decompressing objects with slightly malformed zlib data
+
 v.2.4.1 (24th September 2020)
 - Re-vendor font metrics from Adobe to clarify their license
 

data/README.md

@@ -166,6 +166,19 @@ http://groups.google.com/group/pdf-reader
 The easiest way to explain how this works in practice is to show some examples.
 Check out the examples/ directory for a few files.
 
+# Alternate Decoder
+
+For PDF files containing Ascii85 streams, the [ascii85_native](https://github.com/AnomalousBit/ascii85_native) gem can be used for increased performance. If the ascii85_native gem is detected, pdf-reader will automatically use the gem.
+
+First, run `gem install ascii85_native` and then require the gem alongside pdf-reader:
+
+```ruby
+require "pdf-reader"
+require "ascii85_native"
+```
+
+Another way of enabling native Ascii85 decoding is to place `gem 'ascii85_native'` in your project's `Gemfile`.
+
 # Known Limitations
 
 Occasionally some text cannot be extracted properly due to the way it has been
@@ -176,7 +189,9 @@ little UTF-8 friendly box to indicate an unrecognisable character.
 
 * PDF::Reader Code Repository: http://github.com/yob/pdf-reader
 
-* PDF Specification: http://www.adobe.com/devnet/pdf/pdf_reference.html
+* PDF Specification: https://www.adobe.com/content/dam/acom/en/devnet/pdf/pdfs/PDF32000_2008.pdf
+
+* Adobe PDF Developer Resources: http://www.adobe.com/devnet/pdf/pdf_reference.html
 
 * PDF Tutorial Slide Presentations: https://web.archive.org/web/20150110042057/http://home.comcast.net/~jk05/presentations/PDFTutorials.html
 

data/Rakefile

@@ -14,7 +14,7 @@ desc "Run cane to check quality metrics"
 Cane::RakeTask.new(:quality) do |cane|
   cane.abc_max = 20
   cane.style_measure = 100
-  cane.max_violations = 31
+  cane.max_violations = 32
 
   cane.use Morecane::EncodingCheck, :encoding_glob => "{app,lib,spec}/**/*.rb"
 end

data/examples/extract_fonts.rb

@@ -17,8 +17,8 @@ module ExtractFonts
       return count if page.fonts.nil? || page.fonts.empty?
 
       page.fonts.each do |label, font|
-        next if complete_refs[font]
-        complete_refs[font] = true
+        next if complete_refs[label]
+        complete_refs[label] = true
 
         process_font(page, font)
 
@@ -39,7 +39,7 @@ module ExtractFonts
       when :TrueType, :CIDFontType2 then
         ExtractFonts::TTF.new(page.objects, font).save("#{font[:BaseFont]}.ttf")
       else
-        $stderr.puts "unsupported font type #{font[:Subtype]}"
+        $stderr.puts "unsupported font type #{font[:Subtype]} for #{font[:BaseFont]}"
       end
     end
 
@@ -68,10 +68,15 @@ module ExtractFonts
   end
 end
 
-filename = File.expand_path(File.dirname(__FILE__)) + "/../spec/data/cairo-unicode.pdf"
+if ARGV.size == 0 # default file name
+  ARGV << File.expand_path(File.join(File.dirname(__dir__), "spec", "data", "cairo-unicode.pdf")) 
+end
+
 extractor = ExtractFonts::Extractor.new
 
-PDF::Reader.open(filename) do |reader|
-  page = reader.page(1)
-  extractor.page(page)
+ARGV.each do |arg|
+  PDF::Reader.open(arg) do |reader|
+    page = reader.page(1)
+    extractor.page(page)
+  end
 end

data/examples/rspec.rb

@@ -1,5 +1,6 @@
 #!/usr/bin/env ruby
 # coding: utf-8
+# typed: ignore
 
 #  Basic RSpec of a generated PDF
 #

data/lib/pdf/reader/buffer.rb

@@ -1,4 +1,5 @@
 # coding: ASCII-8BIT
+# typed: false
 # frozen_string_literal: true
 
 ################################################################################
@@ -48,6 +49,15 @@ class PDF::Reader
     ID = "ID"
     FWD_SLASH = "/"
     NULL_BYTE = "\x00"
+    CR = "\r"
+    LF = "\n"
+    CRLF = "\r\n"
+    WHITE_SPACE = [LF, CR, ' ']
+
+    # Quite a few PDFs have trailing junk.
+    # This can be several k of nuls in some cases
+    # Allow for this here
+    TRAILING_BYTECOUNT = 5000
 
     attr_reader :pos
 
@@ -86,9 +96,12 @@ class PDF::Reader
     #
     # options:
     #
-    #   :skip_eol - if true, the IO stream is advanced past a CRLF or LF that
-    #               is sitting under the io cursor.
-    #
+    #   :skip_eol - if true, the IO stream is advanced past a CRLF, CR or LF
+    #               that is sitting under the io cursor.
+    #   Note:
+    #   Skipping a bare CR is not spec-compliant.
+    #   This is because the data may start with LF.
+    #   However we check for CRLF first, so the ambiguity is avoided.
     def read(bytes, opts = {})
       reset_pos
 
@@ -97,9 +110,9 @@ class PDF::Reader
         str = @io.read(2)
         if str.nil?
           return nil
-        elsif str == "\r\n"
+        elsif str == CRLF # This MUST be done before checking for CR alone
           # do nothing
-        elsif str[0,1] == "\n"
+        elsif str[0, 1] == LF || str[0, 1] == CR # LF or CR alone
           @io.seek(-1, IO::SEEK_CUR)
         else
           @io.seek(-2, IO::SEEK_CUR)
@@ -127,8 +140,8 @@ class PDF::Reader
     #
     def find_first_xref_offset
       check_size_is_non_zero
-      @io.seek(-1024, IO::SEEK_END) rescue @io.seek(0)
-      data = @io.read(1024)
+      @io.seek(-TRAILING_BYTECOUNT, IO::SEEK_END) rescue @io.seek(0)
+      data = @io.read(TRAILING_BYTECOUNT)
 
       # the PDF 1.7 spec (section #3.4) says that EOL markers can be either \r, \n, or both.
       lines = data.split(/[\n\r]+/).reverse
@@ -217,7 +230,9 @@ class PDF::Reader
       return if @tokens.size < 3
       return if @tokens[2] != "R"
 
-      if @tokens[0].match(/\d+/) && @tokens[1].match(/\d+/)
+      # must match whole tokens
+      digits_only = %r{\A\d+\z}
+      if @tokens[0].match(digits_only) && @tokens[1].match(digits_only)
         @tokens[0] = PDF::Reader::Reference.new(@tokens[0].to_i, @tokens[1].to_i)
         @tokens[1] = nil
         @tokens[2] = nil
@@ -225,24 +240,51 @@ class PDF::Reader
       end
     end
 
+    # Extract data between ID and EI
+    # If the EI follows white-space the space is dropped from the data
+    # The EI must followed by white-space or end of buffer
+    # This is to reduce the chance of accidentally matching an embedded EI
     def prepare_inline_token
-      str = "".dup
-
-      buffer = []
-
-      until buffer[0] =~ /\s|\0/ && buffer[1, 2] == ["E", "I"]
+      idstart = @io.pos
+      chr = prevchr = nil
+      eisize = 0 # how many chars in the end marker
+      seeking = 'E' # what are we looking for now?
+      loop do
         chr = @io.read(1)
-        buffer << chr
-
-        if buffer.length > 3
-          str << buffer.shift
+        break if chr.nil?
+        case seeking
+        when 'E'
+          if chr == 'E'
+            seeking = 'I'
+            if WHITE_SPACE.include? prevchr
+              eisize = 3 # include whitespace in delimiter, i.e. drop from data
+            else # assume the EI immediately follows the data
+              eisize = 2 # leave prevchr in data
+            end
+          end
+        when 'I'
+          if chr == 'I'
+            seeking = :END
+          else
+            seeking = 'E'
+          end
+        when :END
+          if WHITE_SPACE.include? chr
+            eisize += 1 # Drop trailer
+            break
+          else
+            seeking = 'E'
+          end
         end
+        prevchr = chr
       end
-
-      str << NULL_BYTE if buffer.first == NULL_BYTE
-
+      unless seeking == :END
+        raise MalformedPDFError, "EI terminator not found"
+      end
+      eiend = @io.pos
+      @io.seek(idstart, IO::SEEK_SET)
+      str = @io.read(eiend - eisize - idstart) # get the ID content
       @tokens << string_token(str)
-      @io.seek(-3, IO::SEEK_CUR) unless chr.nil?
     end
 
     # if we're currently inside a hex string, read hex nibbles until

data/lib/pdf/reader/cid_widths.rb

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

data/lib/pdf/reader/cmap.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: false
 # frozen_string_literal: true
 
 ################################################################################
@@ -32,6 +33,7 @@ class PDF::Reader
   # extracting various useful information.
   #
   class CMap # :nodoc:
+
     CMAP_KEYWORDS = {
       "begincodespacerange" => 1,
       "endcodespacerange" => 1,
@@ -53,7 +55,7 @@ class PDF::Reader
 
     def process_data(data)
       parser = build_parser(data)
-      mode = nil
+      mode = :none
       instructions = []
 
       while token = parser.parse_token(CMAP_KEYWORDS)
@@ -62,13 +64,13 @@ class PDF::Reader
         elsif token == "endbfchar"
           process_bfchar_instructions(instructions)
           instructions = []
-          mode = nil
+          mode = :none
         elsif token == "beginbfrange"
           mode = :range
         elsif token == "endbfrange"
           process_bfrange_instructions(instructions)
           instructions = []
-          mode = nil
+          mode = :none
         elsif mode == :char || mode == :range
           instructions << token
         end

data/lib/pdf/reader/encoding.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 ################################################################################
@@ -68,7 +69,7 @@ class PDF::Reader
     #
     #   [25, :A, :B]
     def differences=(diff)
-      raise ArgumentError, "diff must be an array" unless diff.kind_of?(Array)
+      PDF::Reader::Error.validate_type(diff, "diff", Array)
 
       @differences = {}
       byte = 0
@@ -208,7 +209,7 @@ class PDF::Reader
     def load_mapping(file)
       File.open(file, "r:BINARY") do |f|
         f.each do |l|
-          _m, single_byte, unicode = *l.match(/([0-9A-Za-z]+);([0-9A-F]{4})/)
+          _m, single_byte, unicode = *l.match(/\A([0-9A-Za-z]+);([0-9A-F]{4})/)
           @mapping["0x#{single_byte}".hex] = "0x#{unicode}".hex if single_byte
         end
       end

data/lib/pdf/reader/error.rb

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: strict
 # frozen_string_literal: true
 
 ################################################################################
@@ -33,19 +34,26 @@ class PDF::Reader
     def self.str_assert(lvalue, rvalue, chars=nil)
       raise MalformedPDFError, "PDF malformed, expected string but found #{lvalue.class} instead" if chars and !lvalue.kind_of?(String)
       lvalue = lvalue[0,chars] if chars
-      raise MalformedPDFError, "PDF malformed, expected '#{rvalue}' but found #{lvalue} instead"  if lvalue != rvalue
+      raise MalformedPDFError, "PDF malformed, expected '#{rvalue}' but found '#{lvalue}' instead"  if lvalue != rvalue
     end
     ################################################################################
     def self.str_assert_not(lvalue, rvalue, chars=nil)
       raise MalformedPDFError, "PDF malformed, expected string but found #{lvalue.class} instead" if chars and !lvalue.kind_of?(String)
       lvalue = lvalue[0,chars] if chars
-      raise MalformedPDFError, "PDF malformed, expected '#{rvalue}' but found #{lvalue} instead"  if lvalue == rvalue
+      raise MalformedPDFError, "PDF malformed, expected '#{rvalue}' but found '#{lvalue}' instead"  if lvalue == rvalue
     end
     ################################################################################
     def self.assert_equal(lvalue, rvalue)
-      raise MalformedPDFError, "PDF malformed, expected #{rvalue} but found #{lvalue} instead" if lvalue != rvalue
+      raise MalformedPDFError, "PDF malformed, expected '#{rvalue}' but found '#{lvalue}' instead" if lvalue != rvalue
     end
     ################################################################################
+    def self.validate_type(object, name, klass)
+      raise ArgumentError, "#{name} (#{object}) must be a #{klass}" unless object.is_a?(klass)
+    end
+    ################################################################################
+    def self.validate_not_nil(object, name)
+      raise ArgumentError, "#{object} must not be nil" if object.nil?
+    end
   end
 
   ################################################################################

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: false
 # frozen_string_literal: true
 
 require 'ascii85'
@@ -7,6 +8,7 @@ class PDF::Reader
   module Filter # :nodoc:
     # implementation of the Ascii85 filter
     class Ascii85
+
       def initialize(options = {})
         @options = options
       end
@@ -17,7 +19,11 @@ class PDF::Reader
       #
       def filter(data)
         data = "<~#{data}" unless data.to_s[0,2] == "<~"
-        ::Ascii85::decode(data)
+        if defined?(::Ascii85Native)
+          ::Ascii85Native::decode(data)
+        else
+          ::Ascii85::decode(data)
+        end
       rescue Exception => e
         # Oops, there was a problem decoding the stream
         raise MalformedPDFError,

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 #
@@ -6,6 +7,7 @@ class PDF::Reader
   module Filter # :nodoc:
     # implementation of the AsciiHex stream filter
     class AsciiHex
+
       def initialize(options = {})
         @options = options
       end
@@ -16,9 +18,12 @@ class PDF::Reader
       def filter(data)
         data.chop! if data[-1,1] == ">"
         data = data[1,data.size] if data[0,1] == "<"
+
+        return "" if data.nil?
+
         data.gsub!(/[^A-Fa-f0-9]/,"")
         data << "0" if data.size % 2 == 1
-        data.scan(/.{2}/).map { |s| s.hex.chr }.join("")
+        data.scan(/.{2}/).flatten.map { |s| s.hex.chr }.join("")
       rescue Exception => e
         # Oops, there was a problem decoding the stream
         raise MalformedPDFError,

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 class PDF::Reader
@@ -6,6 +7,7 @@ class PDF::Reader
     # some filter implementations support preprocessing of the  data to
     # improve compression
     class Depredict
+
       def initialize(options = {})
         @options = options || {}
       end
@@ -34,7 +36,7 @@ class PDF::Reader
       ################################################################################
       def tiff_depredict(data)
         data        = data.unpack("C*")
-        unfiltered  = []
+        unfiltered  = ''
         bpc         = @options[:BitsPerComponent] || 8
         pixel_bits  = bpc * @options[:Colors]
         pixel_bytes = pixel_bits / 8
@@ -51,11 +53,11 @@ class PDF::Reader
             left = index < pixel_bytes ? 0 : row_data[index - pixel_bytes]
             row_data[index] = (byte + left) % 256
           end
-          unfiltered += row_data
+          unfiltered += row_data.pack("C*")
           pos += line_len
         end
 
-        unfiltered.pack("C*")
+        unfiltered
       end
       ################################################################################
       def png_depredict(data)
@@ -67,7 +69,7 @@ class PDF::Reader
         scanline_length = (pixel_bytes * @options[:Columns]) + 1
         row = 0
         pixels = []
-        paeth, pa, pb, pc = nil
+        paeth, pa, pb, pc = 0, 0, 0, 0
         until data.empty? do
           row_data = data.slice! 0, scanline_length
           filter = row_data.shift
@@ -94,17 +96,17 @@ class PDF::Reader
               row_data[index] = (byte + ((left + upper)/2).floor) % 256
             end
           when 4 # Paeth
-            left = upper = upper_left = nil
+            left = upper = upper_left = 0
             row_data.each_with_index do |byte, index|
               col = index / pixel_bytes
 
-              left = index < pixel_bytes ? 0 : row_data[index - pixel_bytes]
+              left = index < pixel_bytes ? 0 : Integer(row_data[index - pixel_bytes])
               if row.zero?
                 upper = upper_left = 0
               else
-                upper = pixels[row-1][col][index % pixel_bytes]
+                upper = Integer(pixels[row-1][col][index % pixel_bytes])
                 upper_left = col.zero? ? 0 :
-                  pixels[row-1][col-1][index % pixel_bytes]
+                  Integer(pixels[row-1][col-1][index % pixel_bytes])
               end
 
               p = left + upper - upper_left

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 
@@ -8,7 +9,9 @@ class PDF::Reader
   module Filter # :nodoc:
     # implementation of the Flate (zlib) stream filter
     class Flate
+
       ZLIB_AUTO_DETECT_ZLIB_OR_GZIP = 47  # Zlib::MAX_WBITS + 32
+      ZLIB_RAW_DEFLATE              = -15 # Zlib::MAX_WBITS * -1
 
       def initialize(options = {})
         @options = options
@@ -17,24 +20,34 @@ class PDF::Reader
       ################################################################################
       # Decode the specified data with the Zlib compression algorithm
       def filter(data)
-        deflated = nil
+        deflated = zlib_inflate(data) || zlib_inflate(data[0, data.bytesize-1])
+
+        if deflated.nil?
+          raise MalformedPDFError,
+            "Error while inflating a compressed stream (no suitable inflation algorithm found)"
+        end
+        Depredict.new(@options).filter(deflated)
+      end
+
+      private
+
+      def zlib_inflate(data)
         begin
-          deflated = Zlib::Inflate.new(ZLIB_AUTO_DETECT_ZLIB_OR_GZIP).inflate(data)
-        rescue Zlib::DataError => e
+          return Zlib::Inflate.new(ZLIB_AUTO_DETECT_ZLIB_OR_GZIP).inflate(data)
+        rescue Zlib::DataError
           # by default, Ruby's Zlib assumes the data it's inflating
           # is RFC1951 deflated data, wrapped in a RFC1950 zlib container. If that
-          # fails, then use a lightly-documented 'feature' to attempt to inflate
-          # the data as a raw RFC1951 stream.
-          #
-          # See
-          # - http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-talk/243545
-          deflated = Zlib::Inflate.new(-Zlib::MAX_WBITS).inflate(data)
+          # fails, swallow the exception and attempt to inflate the data as a raw
+          # RFC1951 stream.
         end
-        Depredict.new(@options).filter(deflated)
-      rescue Exception => e
-        # Oops, there was a problem inflating the stream
-        raise MalformedPDFError,
-          "Error occured while inflating a compressed stream (#{e.class.to_s}: #{e.to_s})"
+
+        begin
+          return Zlib::Inflate.new(ZLIB_RAW_DEFLATE).inflate(data)
+        rescue StandardError
+          # swallow this one too, so we can try some other fallback options
+        end
+
+        nil
       end
     end
   end

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 #
@@ -6,6 +7,7 @@ class PDF::Reader
   module Filter # :nodoc:
     # implementation of the LZW stream filter
     class Lzw
+
       def initialize(options = {})
         @options = options
       end

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

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

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

@@ -1,4 +1,5 @@
 # coding: utf-8
+# typed: true
 # frozen_string_literal: true
 
 #
@@ -6,6 +7,7 @@ class PDF::Reader # :nodoc:
   module Filter # :nodoc:
     # implementation of the run length stream filter
     class RunLength
+
       def initialize(options = {})
         @options = options
       end
@@ -20,19 +22,23 @@ class PDF::Reader # :nodoc:
           length = data.getbyte(pos)
           pos += 1
 
-          case
-          when length == 128
-            break
-          when length < 128
-            # When the length is < 128, we copy the following length+1 bytes
-            # literally.
-            out << data[pos, length + 1]
-            pos += length
-          else
-            # When the length is > 128, we copy the next byte (257 - length)
-            # times; i.e., "\xFA\x00" ([250, 0]) will expand to
-            # "\x00\x00\x00\x00\x00\x00\x00".
-            out << data[pos, 1] * (257 - length)
+          unless length.nil?
+            case
+              # nothing
+            when length == 128
+              break
+            when length < 128
+              # When the length is < 128, we copy the following length+1 bytes
+              # literally.
+              out << data[pos, length + 1]
+              pos += length
+            else
+              # When the length is > 128, we copy the next byte (257 - length)
+              # times; i.e., "\xFA\x00" ([250, 0]) will expand to
+              # "\x00\x00\x00\x00\x00\x00\x00".
+              previous_byte = data[pos, 1] || ""
+              out << previous_byte * (257 - length)
+            end
           end
 
           pos += 1

data/lib/pdf/reader/filter.rb

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

data/lib/pdf/reader/font.rb

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