pdf-reader 2.5.0 → 2.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 652d05cf6a22fad5ecb4b92de1e27ba60cafc6525c5ca524e24c7f9796fe1b83
-  data.tar.gz: 2c7448e97890a9fcbd10ec2cd5bafb9025db2fb75dabaf71a4074c542b1065a1
+  metadata.gz: ccc4d14f5820ca798f6eafa1c0978207759ec1668c6f6307acb7cd43bcd0626e
+  data.tar.gz: 466bfe0a91f57463a56d9697ccd2529f981c6917e4ed578b4103f2bc87065522
 SHA512:
-  metadata.gz: ac82452924cf46af98ee15f2a20642b1d06d5b9c22104fe171b5b4612665e482f341e12473805016ccb9d921fc15324ba51675170b369adeace8b278cd1279fb
-  data.tar.gz: b1dc1c4422b0e6bf01092cf724630ba7424fdef1fdaf34f33aaa3a31397caf6ef5a73185a98e6e2828a9e082d87cbca311565397cb064cac20d86e72be27626f
+  metadata.gz: 45d6c16b3d9ed029e6eb5a45cc64aa95e7ada2950e052053cbe0b6f5aae632f824a86f0505a5cee660abd1cd896177a0637a2f2f5a3f3633e829e8d46fb59817
+  data.tar.gz: e3e566344bd5560387577597dea20b2f7da40aed2a7fa8b8d074c0742486db59d7e349f6c38c91c8dcd9b0a8cf2aa4c19a00d0ee097003449504b3f06f18ca3c

data/CHANGELOG

@@ -1,3 +1,20 @@
+v2.6.0 (12th November 2021)
+- Text extraction improvements
+  - Improved text layout on pages with a variery 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/) 

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/lib/pdf/reader/buffer.rb

@@ -48,6 +48,15 @@ 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 +95,12 @@ 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 +109,9 @@ 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 +139,8 @@ 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 +229,9 @@ 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 +239,51 @@ 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/encoding.rb

@@ -208,7 +208,7 @@ 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

@@ -33,17 +33,17 @@ 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
     ################################################################################
   end

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

@@ -17,7 +17,11 @@ 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/depredict.rb

@@ -34,7 +34,7 @@ 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 +51,11 @@ 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)

data/lib/pdf/reader/glyph_hash.rb

@@ -103,19 +103,25 @@ class PDF::Reader
 
     # returns a hash that maps glyph names to unicode codepoints. The mapping is based on
     # a text file supplied by Adobe at:
-    # http://www.adobe.com/devnet/opentype/archives/glyphlist.txt
+    # https://github.com/adobe-type-tools/agl-aglfn
     def load_adobe_glyph_mapping
       keyed_by_name      = {}
       keyed_by_codepoint = {}
 
-      File.open(File.dirname(__FILE__) + "/glyphlist.txt", "r:BINARY") do |f|
-        f.each do |l|
-          _m, name, code = *l.match(/([0-9A-Za-z]+);([0-9A-F]{4})/)
-          if name && code
-            cp = "0x#{code}".hex
-            keyed_by_name[name.to_sym]   = cp
-            keyed_by_codepoint[cp]     ||= []
-            keyed_by_codepoint[cp]     << name.to_sym
+      paths = [
+        File.dirname(__FILE__) + "/glyphlist.txt",
+        File.dirname(__FILE__) + "/glyphlist-zapfdingbats.txt",
+      ]
+      paths.each do |path|
+        File.open(path, "r:BINARY") do |f|
+          f.each do |l|
+            _m, name, code = *l.match(/([0-9A-Za-z]+);([0-9A-F]{4})/)
+            if name && code
+              cp = "0x#{code}".hex
+              keyed_by_name[name.to_sym]   = cp
+              keyed_by_codepoint[cp]     ||= []
+              keyed_by_codepoint[cp]     << name.to_sym
+            end
           end
         end
       end

data/lib/pdf/reader/glyphlist-zapfdingbats.txt

@@ -0,0 +1,245 @@
+# -----------------------------------------------------------
+# Copyright 2002-2019 Adobe (http://www.adobe.com/).
+#
+# Redistribution and use in source and binary forms, with or
+# without modification, are permitted provided that the
+# following conditions are met:
+#
+# Redistributions of source code must retain the above
+# copyright notice, this list of conditions and the following
+# disclaimer.
+#
+# Redistributions in binary form must reproduce the above
+# copyright notice, this list of conditions and the following
+# disclaimer in the documentation and/or other materials
+# provided with the distribution.
+#
+# Neither the name of Adobe nor the names of its contributors
+# may be used to endorse or promote products derived from this
+# software without specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
+# CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+# INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+# NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+# -----------------------------------------------------------
+# Name:          ITC Zapf Dingbats Glyph List
+# Table version: 2.0
+# Date:          September 20, 2002
+# URL:           https://github.com/adobe-type-tools/agl-aglfn
+#
+# Format: two semicolon-delimited fields:
+#   (1) glyph name--upper/lowercase letters and digits
+#   (2) Unicode scalar value--four uppercase hexadecimal digits
+#
+a100;275E
+a101;2761
+a102;2762
+a103;2763
+a104;2764
+a105;2710
+a106;2765
+a107;2766
+a108;2767
+a109;2660
+a10;2721
+a110;2665
+a111;2666
+a112;2663
+a117;2709
+a118;2708
+a119;2707
+a11;261B
+a120;2460
+a121;2461
+a122;2462
+a123;2463
+a124;2464
+a125;2465
+a126;2466
+a127;2467
+a128;2468
+a129;2469
+a12;261E
+a130;2776
+a131;2777
+a132;2778
+a133;2779
+a134;277A
+a135;277B
+a136;277C
+a137;277D
+a138;277E
+a139;277F
+a13;270C
+a140;2780
+a141;2781
+a142;2782
+a143;2783
+a144;2784
+a145;2785
+a146;2786
+a147;2787
+a148;2788
+a149;2789
+a14;270D
+a150;278A
+a151;278B
+a152;278C
+a153;278D
+a154;278E
+a155;278F
+a156;2790
+a157;2791
+a158;2792
+a159;2793
+a15;270E
+a160;2794
+a161;2192
+a162;27A3
+a163;2194
+a164;2195
+a165;2799
+a166;279B
+a167;279C
+a168;279D
+a169;279E
+a16;270F
+a170;279F
+a171;27A0
+a172;27A1
+a173;27A2
+a174;27A4
+a175;27A5
+a176;27A6
+a177;27A7
+a178;27A8
+a179;27A9
+a17;2711
+a180;27AB
+a181;27AD
+a182;27AF
+a183;27B2
+a184;27B3
+a185;27B5
+a186;27B8
+a187;27BA
+a188;27BB
+a189;27BC
+a18;2712
+a190;27BD
+a191;27BE
+a192;279A
+a193;27AA
+a194;27B6
+a195;27B9
+a196;2798
+a197;27B4
+a198;27B7
+a199;27AC
+a19;2713
+a1;2701
+a200;27AE
+a201;27B1
+a202;2703
+a203;2750
+a204;2752
+a205;276E
+a206;2770
+a20;2714
+a21;2715
+a22;2716
+a23;2717
+a24;2718
+a25;2719
+a26;271A
+a27;271B
+a28;271C
+a29;2722
+a2;2702
+a30;2723
+a31;2724
+a32;2725
+a33;2726
+a34;2727
+a35;2605
+a36;2729
+a37;272A
+a38;272B
+a39;272C
+a3;2704
+a40;272D
+a41;272E
+a42;272F
+a43;2730
+a44;2731
+a45;2732
+a46;2733
+a47;2734
+a48;2735
+a49;2736
+a4;260E
+a50;2737
+a51;2738
+a52;2739
+a53;273A
+a54;273B
+a55;273C
+a56;273D
+a57;273E
+a58;273F
+a59;2740
+a5;2706
+a60;2741
+a61;2742
+a62;2743
+a63;2744
+a64;2745
+a65;2746
+a66;2747
+a67;2748
+a68;2749
+a69;274A
+a6;271D
+a70;274B
+a71;25CF
+a72;274D
+a73;25A0
+a74;274F
+a75;2751
+a76;25B2
+a77;25BC
+a78;25C6
+a79;2756
+a7;271E
+a81;25D7
+a82;2758
+a83;2759
+a84;275A
+a85;276F
+a86;2771
+a87;2772
+a88;2773
+a89;2768
+a8;271F
+a90;2769
+a91;276C
+a92;276D
+a93;276A
+a94;276B
+a95;2774
+a96;2775
+a97;275B
+a98;275C
+a99;275D
+a9;2720
+# END

data/lib/pdf/reader/page_layout.rb

@@ -2,6 +2,7 @@
 # frozen_string_literal: true
 
 require 'pdf/reader/overlapping_runs_filter'
+require 'pdf/reader/zero_width_runs_filter'
 
 class PDF::Reader
 
@@ -17,10 +18,12 @@ class PDF::Reader
     def initialize(runs, mediabox)
       raise ArgumentError, "a mediabox must be provided" if mediabox.nil?
 
-      @runs    = merge_runs(OverlappingRunsFilter.exclude_redundant_runs(runs))
+      runs = ZeroWidthRunsFilter.exclude_zero_width_runs(runs)
+      runs = OverlappingRunsFilter.exclude_redundant_runs(runs)
+      @runs = merge_runs(runs)
       @mean_font_size   = mean(@runs.map(&:font_size)) || DEFAULT_FONT_SIZE
       @mean_font_size = DEFAULT_FONT_SIZE if @mean_font_size == 0
-      @mean_glyph_width = mean(@runs.map(&:mean_character_width)) || 0
+      @median_glyph_width = median(@runs.map(&:mean_character_width)) || 0
       @page_width  = (mediabox[2] - mediabox[0]).abs
       @page_height = (mediabox[3] - mediabox[1]).abs
       @x_offset = @runs.map(&:x).sort.first || 0
@@ -67,7 +70,7 @@ class PDF::Reader
     end
 
     def col_count
-      @col_count ||= ((@page_width  / @mean_glyph_width) * 1.05).floor
+      @col_count ||= ((@page_width  / @median_glyph_width) * 1.05).floor
     end
 
     def row_multiplier
@@ -86,12 +89,12 @@ class PDF::Reader
       end
     end
 
-    def each_line(&block)
-      @runs.sort.group_by { |run|
-        run.y.to_i
-      }.map { |y, collection|
-        yield y, collection
-      }
+    def median(collection)
+      if collection.size == 0
+        0
+      else
+        collection.sort[(collection.size * 0.5).floor]
+      end
     end
 
     # take a collection of TextRun objects and merge any that are in close

data/lib/pdf/reader/page_text_receiver.rb

@@ -45,8 +45,8 @@ module PDF
         @content = []
         @characters = []
         @mediabox = page.objects.deref(page.attributes[:MediaBox])
-        device_bl = @state.ctm_transform(@mediabox[0], @mediabox[1])
-        device_tr = @state.ctm_transform(@mediabox[2], @mediabox[3])
+        device_bl = apply_rotation(*@state.ctm_transform(@mediabox[0], @mediabox[1]))
+        device_tr = apply_rotation(*@state.ctm_transform(@mediabox[2], @mediabox[3]))
         @device_mediabox = [ device_bl.first, device_bl.last, device_tr.first, device_tr.last]
       end
 

data/lib/pdf/reader/parser.rb

@@ -175,15 +175,18 @@ class PDF::Reader
       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] || "".dup
+      str.gsub!(/\\(\r\n|[nrtbf()\\\n\r]|([0-7]{1,3}))?|\r\n?/m) do |match|
+        if $2.nil? # not octal digits
+          MAPPING[match] || "".dup
+        else # must be octal digits
+          ($2.oct & 0xff).chr # ignore high level overflow
+        end
       end
       str.force_encoding("binary")
     end
 
     MAPPING = {
       "\r"   => "\n",
-      "\n\r" => "\n",
       "\r\n" => "\n",
       "\\n"  => "\n",
       "\\r"  => "\r",
@@ -194,10 +197,9 @@ class PDF::Reader
       "\\)"  => ")",
       "\\\\" => "\\",
       "\\\n" => "",
+      "\\\r" => "",
+      "\\\r\n" => "",
     }
-    0.upto(9)   { |n| MAPPING["\\00"+n.to_s] = ("00"+n.to_s).oct.chr }
-    0.upto(99)  { |n| MAPPING["\\0"+n.to_s]  = ("0"+n.to_s).oct.chr }
-    0.upto(377) { |n| MAPPING["\\"+n.to_s]   = n.to_s.oct.chr }
 
     ################################################################################
     # Decodes the contents of a PDF Stream and returns it as a Ruby String.

data/lib/pdf/reader/xref.rb

@@ -131,6 +131,9 @@ class PDF::Reader
             generation = buf.token.to_i
             state = buf.token
 
+            # Some PDF writers start numbering at 1 instead of 0. Fix up the number.
+            # TODO should this fix be logged?
+            objid = 0 if objid == 1 and offset == 0 and generation == 65535 and state == 'f'
             store(objid, generation, offset + @junk_offset) if state == "n" && offset > 0
             objid += 1
             params.clear
@@ -146,7 +149,9 @@ class PDF::Reader
       end
 
       load_offsets(trailer[:XRefStm])   if trailer.has_key?(:XRefStm)
-      load_offsets(trailer[:Prev].to_i) if trailer.has_key?(:Prev)
+      # Some PDF creators seem to use '/Prev 0' in trailer if there is no previous xref
+      # It's not possible for an xref to appear at offset 0, so can safely skip the ref
+      load_offsets(trailer[:Prev].to_i) if trailer.has_key?(:Prev) and trailer[:Prev].to_i != 0
 
       trailer
     end

data/lib/pdf/reader/zero_width_runs_filter.rb

@@ -0,0 +1,11 @@
+# coding: utf-8
+
+class PDF::Reader
+  # There's no point rendering zero-width characters
+  class ZeroWidthRunsFilter
+
+    def self.exclude_zero_width_runs(runs)
+      runs.reject { |run| run.width == 0 }
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdf-reader
 version: !ruby/object:Gem::Version
-  version: 2.5.0
+  version: 2.6.0
 platform: ruby
 authors:
 - James Healy
-autorequire:
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-06-06 00:00:00.000000000 Z
+date: 2021-11-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -239,6 +239,7 @@ files:
 - lib/pdf/reader/font_descriptor.rb
 - lib/pdf/reader/form_xobject.rb
 - lib/pdf/reader/glyph_hash.rb
+- lib/pdf/reader/glyphlist-zapfdingbats.txt
 - lib/pdf/reader/glyphlist.txt
 - lib/pdf/reader/lzw.rb
 - lib/pdf/reader/null_security_handler.rb
@@ -272,15 +273,16 @@ files:
 - lib/pdf/reader/width_calculator/type_one_or_three.rb
 - lib/pdf/reader/width_calculator/type_zero.rb
 - lib/pdf/reader/xref.rb
+- lib/pdf/reader/zero_width_runs_filter.rb
 homepage: https://github.com/yob/pdf-reader
 licenses:
 - MIT
 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:
+  changelog_uri: https://github.com/yob/pdf-reader/blob/v2.6.0/CHANGELOG
+  documentation_uri: https://www.rubydoc.info/gems/pdf-reader/2.6.0
+  source_code_uri: https://github.com/yob/pdf-reader/tree/v2.6.0
+post_install_message: 
 rdoc_options:
 - "--title"
 - PDF::Reader Documentation
@@ -300,8 +302,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.3
-signing_key:
+rubygems_version: 3.1.4
+signing_key: 
 specification_version: 4
 summary: A library for accessing the content of PDF files
 test_files: []