hexapdf 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 61b0fb56c6522f2af82eb8ffb10570c45bb11460cf4c048c1bdfe8d9daf71afe
-  data.tar.gz: 91cb053019c367825ac0799a84e4ddad837fe283a6ab2bc6df16ee9ed9f2456d
+  metadata.gz: 44eb3afec42bc0c5e0645c0ff6eb48f211083694866fb7c355a0b4ca3e3ad24a
+  data.tar.gz: 864792c029e975b0d8167d80326815ea6a7ebff90bc360c4d550c8a2d4a28003
 SHA512:
-  metadata.gz: 9a71ee1e9307f0ef67c9dec108c7f68db45166a62f9b6ec60915ce2c089cf0e9ec5bfcd8d74e8b31b63238a09c820a0798689a84e5ea0b1577e2492e5a1d425e
-  data.tar.gz: b20043cead03f7fc7fe527fdbcb3674ab2d1da06b546bac9c1549b6eb6d143232453132709d93ae008d78a83bff36cf85fd0dbc0938da848e7847a1830e6011e
+  metadata.gz: 19d415762cb49abfaf31df0d6dc8455c5a6a8b1eee40f18cc4d56b7a18e4d9e9aded8d5826a4f5a265bbc639d61f5a2fe081b1e672b626984d4be719115f4c9a
+  data.tar.gz: 6c8d31294566e9c408cb0fe8512ca4898d583edebe750191fda6d42fcb0a6cb44d83de90359abcac6cca1cf7b47f38e3515b5c94246456b485091d3d72c0be5c

data/CHANGELOG.md

@@ -1,3 +1,17 @@
+## 1.0.1 - 2024-11-05
+
+### Added
+
+* [HexaPDF::Type::CMap] for representing CMap streams
+
+### Fixed
+
+* Checksum calculation for TrueType tables
+* Automatic wrapping of dictionary entry /CIDToGIDMap for CID fonts
+* Performance regression when encoding char codes for TrueType fonts
+* PDF/A validation regression for PDFs using TrueType fonts
+
+
 ## 1.0.1 - 2024-11-04
 
 ### Changed

data/lib/hexapdf/configuration.rb

@@ -722,6 +722,7 @@ module HexaPDF
                         OutputIntent: 'HexaPDF::Type::OutputIntent',
                         XXDestOutputProfileRef: 'HexaPDF::Type::OutputIntent::DestOutputProfileRef',
                         ExData: 'HexaPDF::Type::Annotations::MarkupAnnotation::ExData',
+                        CMap: 'HexaPDF::Type::CMap',
                       },
                       'object.subtype_map' => {
                         nil => {

data/lib/hexapdf/font/true_type/subsetter.rb

@@ -63,16 +63,6 @@ module HexaPDF
         def use_glyph(glyph_id)
           return @glyph_map[glyph_id] if @glyph_map.key?(glyph_id)
           @last_id += 1
-          # Handle codes for ASCII characters \r (13), (, ) (40, 41) and \ (92) specially so that
-          # they never appear in the output (PDF serialization would need to escape them)
-          if @last_id == 13 || @last_id == 40 || @last_id == 92
-            @glyph_map[:"s#{@last_id}"] = @last_id
-            if @last_id == 40
-              @last_id += 1
-              @glyph_map[:"s#{@last_id}"] = @last_id
-            end
-            @last_id += 1
-          end
           @glyph_map[glyph_id] = @last_id
         end
 
@@ -117,7 +107,7 @@ module HexaPDF
           locations = []
 
           @glyph_map.each_key do |old_gid|
-            glyph = orig_glyf[old_gid.kind_of?(Symbol) ? 0 : old_gid]
+            glyph = orig_glyf[old_gid]
             locations << table.size
             data = glyph.raw_data
             if glyph.compound?
@@ -176,10 +166,7 @@ module HexaPDF
         # Adds the components of compound glyphs to the subset.
         def add_glyph_components
           glyf = @font[:glyf]
-          @glyph_map.keys.each do |gid|
-            next if gid.kind_of?(Symbol)
-            glyf[gid].components&.each {|cgid| use_glyph(cgid) }
-          end
+          @glyph_map.keys.each {|gid| glyf[gid].components&.each {|cgid| use_glyph(cgid) } }
         end
 
       end

data/lib/hexapdf/font/true_type/table.rb

@@ -63,7 +63,12 @@ module HexaPDF
 
         # Calculates the checksum for the given data.
         def self.calculate_checksum(data)
-          data.unpack('N*').inject(0) {|sum, long| sum + long } % 2**32
+          checksum = 0
+          if (remainder_length = data.length % 4) != 0
+            checksum = (data[-remainder_length, remainder_length] << "\0" * (4 - remainder_length)).
+              unpack1('N')
+          end
+          checksum + data.unpack('N*').inject(0) {|sum, long| sum + long } % 2**32
         end
 
         # The TrueType font object associated with this table.

data/lib/hexapdf/font/true_type_wrapper.rb

@@ -239,6 +239,11 @@ module HexaPDF
             raise HexaPDF::MissingGlyphError.new(glyph) if glyph.kind_of?(InvalidGlyph)
             @subsetter.use_glyph(glyph.id) if @subsetter
             @last_char_code += 1
+            # Handle codes for ASCII characters \r (13), (, ) (40, 41) and \ (92) specially so that
+            # they never appear in the output (PDF serialization would need to escape them)
+            if @last_char_code == 13 || @last_char_code == 40 || @last_char_code == 92
+              @last_char_code += (@last_char_code == 40 ? 2 : 1)
+            end
             [[@last_char_code].pack('n'), @last_char_code]
           end)[0]
       end
@@ -376,7 +381,11 @@ module HexaPDF
           dict[:Encoding] = :'Identity-H'
         else
           stream = HexaPDF::StreamData.new { HexaPDF::Font::CMap.create_cid_cmap(mapping) }
-          stream_obj = document.add({}, stream: stream)
+          stream_obj = document.add({Type: :CMap,
+                                     CMapName: :Custom,
+                                     CIDSystemInfo: {Registry: "Adobe", Ordering: "Identity",
+                                                     Supplement: 0},
+                                    }, stream: stream)
           stream_obj.set_filter(:FlateDecode)
           dict[:Encoding] = stream_obj
         end

data/lib/hexapdf/type/cid_font.rb

@@ -70,7 +70,7 @@ module HexaPDF
       define_field :W,               type: PDFArray
       define_field :DW2,             type: PDFArray, default: [880, -1100]
       define_field :W2,              type: PDFArray
-      define_field :CIDToGIDMap,     type: [Symbol, Stream]
+      define_field :CIDToGIDMap,     type: [Stream, Symbol]
 
       # Returns the unscaled width of the given CID in glyph units, or 0 if the width for the CID is
       # missing.

data/lib/hexapdf/type/cmap.rb

@@ -0,0 +1,58 @@
+# -*- encoding: utf-8; frozen_string_literal: true -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2024 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#
+# If the GNU Affero General Public License doesn't fit your need,
+# commercial licenses are available at <https://gettalong.at/hexapdf/>.
+#++
+
+require 'hexapdf/stream'
+
+module HexaPDF
+  module Type
+
+    # Represents an embedded CMap file.
+    #
+    # See: PDF2.0 s9.7.5.3
+    class CMap < Stream
+
+      define_type :CMap
+
+      define_field :Type, type: Symbol, required: true, default: type
+      define_field :CMapName, type: Symbol, required: true
+      define_field :CIDSystemInfo, type: :XXCIDSystemInfo, required: true
+      define_field :WMode, type: Integer
+      define_field :UseCMap, type: [Stream, Symbol]
+
+    end
+
+  end
+end

data/lib/hexapdf/type.rb

@@ -82,6 +82,7 @@ module HexaPDF
     autoload(:OptionalContentConfiguration, 'hexapdf/type/optional_content_configuration')
     autoload(:Metadata, 'hexapdf/type/metadata')
     autoload(:OutputIntent, 'hexapdf/type/output_intent')
+    autoload(:CMap, 'hexapdf/type/cmap')
 
   end
 

data/lib/hexapdf/version.rb

@@ -37,6 +37,6 @@
 module HexaPDF
 
   # The version of HexaPDF.
-  VERSION = '1.0.1'
+  VERSION = '1.0.2'
 
 end

data/test/hexapdf/font/test_true_type_wrapper.rb

@@ -119,6 +119,11 @@ describe HexaPDF::Font::TrueTypeWrapper do
       assert_equal([3].pack('n'), code)
     end
 
+    it "doesn't use char codes 13, 40, 41 and 92 because they would need to be escaped" do
+      codes = 1.upto(93).map {|i| @font_wrapper.encode(@font_wrapper.glyph(i)) }.join
+      assert_equal([1..12, 14..39, 42..91, 93..97].flat_map(&:to_a).pack('n*'), codes)
+    end
+
     it "raises an error if an InvalidGlyph is encoded" do
       exp = assert_raises(HexaPDF::MissingGlyphError) do
         @font_wrapper.encode(@font_wrapper.decode_utf8("ö").first)

data/test/hexapdf/font/true_type/test_subsetter.rb

@@ -27,16 +27,6 @@ describe HexaPDF::Font::TrueType::Subsetter do
     assert_equal(value, @subsetter.subset_glyph_id(5))
   end
 
-  it "doesn't use certain subset glyph IDs for performance reasons" do
-    1.upto(93) {|i| @subsetter.use_glyph(i) }
-    # glyph 0, 93 used glyph, 4 special glyphs
-    assert_equal(1 + 93 + 4, @subsetter.instance_variable_get(:@glyph_map).size)
-    1.upto(12) {|i| assert_equal(i, @subsetter.subset_glyph_id(i), "id=#{i}") }
-    13.upto(38) {|i| assert_equal(i + 1, @subsetter.subset_glyph_id(i), "id=#{i}") }
-    39.upto(88) {|i| assert_equal(i + 3, @subsetter.subset_glyph_id(i), "id=#{i}") }
-    89.upto(93) {|i| assert_equal(i + 4, @subsetter.subset_glyph_id(i), "id=#{i}") }
-  end
-
   it "creates the subset font file" do
     gid = @font[:cmap].preferred_table[0x41]
     @subsetter.use_glyph(gid)

data/test/hexapdf/font/true_type/test_table.rb

@@ -13,6 +13,18 @@ describe HexaPDF::Font::TrueType::Table do
     @entry = HexaPDF::Font::TrueType::Table::Directory::Entry.new('tagg', 0, 0, @file.io.string.length)
   end
 
+  describe "self.calculate_checksum" do
+    it "works for data with a length divisible by four" do
+      klass = HexaPDF::Font::TrueType::Table
+      assert_equal(256, klass.calculate_checksum("\x00\x00\x00\x01\x00\x00\x00\xFF"))
+    end
+
+    it "works for data with a length not divisible by four" do
+      klass = HexaPDF::Font::TrueType::Table
+      assert_equal(512, klass.calculate_checksum("\x00\x00\x00\x01\x00\x00\x00\xFF\x00\x00\x01"))
+    end
+  end
+
   describe "initialize" do
     it "reads the data from the associated file" do
       table = TrueTypeTestTable.new(@file, @entry)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hexapdf
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Thomas Leitner
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-11-04 00:00:00.000000000 Z
+date: 2024-11-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cmdparse
@@ -500,6 +500,7 @@ files:
 - lib/hexapdf/type/annotations/widget.rb
 - lib/hexapdf/type/catalog.rb
 - lib/hexapdf/type/cid_font.rb
+- lib/hexapdf/type/cmap.rb
 - lib/hexapdf/type/embedded_file.rb
 - lib/hexapdf/type/file_specification.rb
 - lib/hexapdf/type/font.rb