hexapdf 0.21.1 → 0.24.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9792b3c8be5fd3c3521aa5fe1a66e1315f677494f199e3e8b0e1eb85c9b967c7
-  data.tar.gz: a66f1d6751cac4ca2fc6a35bf493ba60eefee96edca090ae92ed810b756d8761
+  metadata.gz: 9be9871c8033a23eb240dc0b6300bcb33ba8ccef107f35189cb8af3faf308a61
+  data.tar.gz: 875797999dc46cefdb39dd31f1649525a11716915af5a83a6c38c0dc100cca2e
 SHA512:
-  metadata.gz: 111570ec411684ffe5214833419128b697721c4e5fdd16b61578c3d459a8ab9dde411780dd582e06620d52a260062df30a116b7c3c8544647f5e61f131c6bdc5
-  data.tar.gz: 3d098cb4098f6a02bc832cbe70aebc0b28a40a21b33b53c8e8e055f240fd513a5d96f53846c62ebbc2a00d17d6f99271dd3850e98a70cebb6f32e1a7e279cc87
+  metadata.gz: 8700678297a316b14a604045ab7da8c371d7cbcebb771d8c878fff4306e36ff7e72b898fb4c63e98599493a7b93480a34bd099dc102ef0e431d825fe1e11ae41
+  data.tar.gz: 4892bb8868475b4bfe65c5938097589f9544bb4b7b9bef568b1ac60a7932eced09f2eee53edc38212654e522c4cc4e5edd8fde7cb6b6078e27ccf18e131e96aa

data/CHANGELOG.md

@@ -1,3 +1,140 @@
+## 0.24.0 - 2022-08-01
+
+### Added
+
+* [HexaPDF::Layout::ListBox] for rendering ordered and unordered lists
+* [HexaPDF::Layout::ColumnBox] for rendering content inside columns
+* [HexaPDF::Layout::BoxFitter] for placing boxes into multiple frames
+* New configuration option 'debug' for enabling debug output
+* [HexaPDF::Document::Pages#move] for moving pages around the same document
+* [HexaPDF::Composer#box] for drawing arbitrary, registered boxes
+* [HexaPDF::Layout::Box#split_box?] for determining whether a box is a split
+  box, i.e. the continuation of another box
+* [HexaPDF::Document::Layout::ChildrenCollector] to provide an easy method for
+  defining children boxes of a container box
+
+### Changed
+
+* **Breaking change**: Refactored [HexaPDF::Layout::Frame] and associated data
+  structures so that the complete result of fitting a box is returned
+* [HexaPDF::Layout::Frame] to use a better algorithm for trimming the shape
+* [HexaPDF::Layout::Frame::new] to allow setting the initial shape
+* **Breaking change**: Removed contour line from [HexaPDF::Layout::Frame]
+* **Breaking change**: Changed positional arguments of
+  [HexaPDF::Layout::TextBox::new] and [HexaPDF::Layout::ImageBox::new] to
+  keyword arguments for a consistent box initialization interface
+* [HexaPDF::Layout::Box#split] to provide a default implementation that is
+  useful for most subclasses
+* Layout box implementations to provide a `#supports_position_flow?` method that
+  indicates whether the box supports flowing its content around other content.
+* `hexapdf info --check` to only check the current version of each object
+* [HexaPDF::Writer] to make sure the producer information is written when
+  writing the file incrementally
+
+### Fixed
+
+* [HexaPDF::Layout::TextLayouter] to freeze the new items when a text fragment
+  needs to be split
+* [HexaPDF::Layout::TextLayouter] to avoid the possible splitting of a text
+  fragment if there would not be enough height left anyway
+* [HexaPDF::Layout::WidthFromPolygon] to work correctly in case of very small
+  floating point errors
+* HexaPDF::Layout::TextFragment#inspect to work in case of interspersed
+  numbers
+* [HexaPDF::Layout::TextBox#split] to work for position :flow when box is wider
+  than the initial available width
+* [HexaPDF::Layout::Frame#fit] to create minimally sized mask rectangles
+* [HexaPDF::Content::GraphicObject::Geom2D] to close the path when drawing
+  polygons
+* [HexaPDF::Layout::WidthFromPolygon] to work for all counterclockwise polygons
+* [HexaPDF::Type::PageTreeNode#move_page] to work in case the parent node of the
+  moved node doesn't change
+* [HexaPDF::Type::PageTreeNode#move_page] to use the correct target position
+  when the moved node is before the target position
+* [HexaPDF::Document::Signatures#add] to work in case the signature object is
+  the last object written
+* CLI command `hexapdf inspect` to show correct byte range of the last revision
+* [HexaPDF::Writer#write_incremental] to only use a cross-reference stream if a
+  revision directly used one and not through an `/XRefStm` entry
+* [HexaPDF::Encryption::FastARC4] to use RubyARC4 as fallback if OpenSSL has RC4
+  disabled
+* [HexaPDF::Font::Encoding::GlyphList] to use binary reading to avoid problems
+  on Windows
+* [HexaPDF::Document::Signatures#add] to use binary writing to avoid problems on
+  Windows
+
+
+## 0.23.0 - 2022-05-26
+
+### Added
+
+- [HexaPDF::Composer#create_stamp] for creating a form Xobject
+- [HexaPDF::Revision#reset_objects] for deleting all live loaded and added
+  objects
+- Support for removing or flattening annotations to the `hexapdf modify` command
+- Option to CLI command `hexapdf form` to allow generation of a template file
+- Support for centering a floating box in [HexaPDF::Layout::Frame]
+- [HexaPDF::Type::Catalog#names] for easier access to the name dictionary
+- [HexaPDF::Type::Names#destinations] for easier access to the destinations name
+  tree
+- [HexaPDF::Document::Destinations], accessible via
+  [HexaPDF::Document#destinations], as convenience interface for working with
+  destination arrays
+
+### Changed
+
+- **Breaking change**: Refactored the [HexaPDF::Document] interface for working
+  with objects and move parts into [HexaPDF::Revisions]
+- **Breaking change**: [HexaPDF::Layout::TextBox] to use whole available width
+  when aligning to the center or right
+- **Breaking change**: [HexaPDF::Layout::TextBox] to use whole available height
+  when vertically aligning to the center or bottom
+- CLI command `hexapdf inspect` to show the type of revisions, as well as the
+  number of objects per revision
+- [HexaPDF::Task::Optimize] to allow skipping invalid content stream operations
+- [HexaPDF::Composer#image] to allow using a form xobject in place of the image
+
+### Fixed
+
+- [HexaPDF::Writer#write] to write modified objects into the correct revision
+- [HexaPDF::Revisions::from_io] to correctly handle hybrid-reference files
+- [HexaPDF::Writer] to assign a valid object number to a created cross-reference
+  stream in all cases
+* [HexaPDF::Type::AcroForm::TextField] to validate the existence of a /MaxLen
+  value for comb text fields
+* [HexaPDF::Type::AcroForm::TextField#field_value=] to check for the existence
+  of /MaxLen when setting a value for a comb text field
+* [HexaPDF::Type::AcroForm::TextField#field_value=] to check the value against
+  /MaxLen
+* [HexaPDF::Layout::TextLayouter#fit] to not use style valign when doing
+  variable width layouting
+* [HexaPDF::Utils::SortedTreeNode#find_entry] to work in case of a node without
+  a container name or kids key
+* CLI command `hexapdf form` to allow setting array values when using a template
+* CLI command `hexapdf form` to allow setting file select fields
+
+
+## 0.22.0 - 2022-03-26
+
+### Added
+
+- Support for writing images with an ICCBased color space
+- Support for writing images with soft masks
+
+### Changed
+
+- CLI command `hexapdf form` to show a warning when working with a file
+  containing an XFA form
+
+### Fixed
+
+- [HexaPDF::Type::AcroForm::Form#field_by_name] to work correctly when field
+  name parts are UTF-16BE encoded
+- `hexapdf inspect` command 'revision' to correctly detect the end of revisions
+- [HexaPDF::DictionaryFields::StringConverter] to use correct method name
+  `HexaPDF::Document#config`
+
+
 ## 0.21.1 - 2022-03-12
 
 ### Fixed

data/LICENSE

@@ -1,5 +1,5 @@
 HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-Copyright (C) 2014-2021 Thomas Leitner
+Copyright (C) 2014-2022 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

data/Rakefile

@@ -47,7 +47,7 @@ namespace :dev do
   end
 
   task :test_all do
-    versions = `rbenv versions --bare | grep -i 2.[567]\\\\\\|3.`.split("\n")
+    versions = `rbenv versions --bare | grep -i 2.[67]\\\\\\|3.`.split("\n")
     versions.each do |version|
       sh "eval \"$(rbenv init -)\"; rbenv shell #{version} && ruby -v && rake test"
     end

data/examples/016-frame_automatic_box_placement.rb

@@ -43,8 +43,13 @@ draw_box = lambda do |**args|
 
   drawn = false
   until drawn
-    drawn = frame.draw(canvas, b)
-    frame.find_next_region unless drawn
+    result = frame.fit(b)
+    if result.success?
+      frame.draw(canvas, result)
+      drawn = true
+    else
+      frame.find_next_region
+    end
   end
 
   canvas.line_width(3).draw(:geom2d, object: frame.shape)

data/examples/017-frame_text_flow.rb

@@ -19,31 +19,18 @@ include HexaPDF::Utils::GraphicsHelpers
 
 doc = HexaPDF::Document.new
 
-sample_text = "Lorem ipsum dolor sit amet, con\u{00AD}sectetur
-adipis\u{00AD}cing elit, sed do eiusmod tempor incididunt ut labore et
-dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation
-ullamco laboris nisi ut aliquip ex ea commodo consequat.
-".tr("\n", ' ') * 10
-items = [TextFragment.create(sample_text, font: doc.fonts.add("Times"))]
-
 page = doc.pages.add
 media_box = page.box(:media)
-canvas = page.canvas
 frame = Frame.new(media_box.left + 20, media_box.bottom + 20,
                   media_box.width - 40, media_box.height - 40)
 
-image = doc.images.add(File.join(__dir__, 'machupicchu.jpg'))
-iw, ih = calculate_dimensions(image.width, image.height, rwidth: 100)
-
 boxes = []
-boxes << Box.create(width: iw, height: ih,
-                    margin: [10, 30], position: :float) do |canv, box|
-  canv.image(image, at: [0, 0], width: 100)
-end
+boxes << doc.layout.image_box(File.join(__dir__, 'machupicchu.jpg'),
+                              width: 100, margin: [10, 30], position: :float)
 boxes << Box.create(width: 50, height: 50, margin: 20,
                     position: :float, position_hint: :right,
                     border: {width: 1, color: [[255, 0, 0]]})
-boxes << TextBox.new(items, style: {position: :flow, align: :justify})
+boxes << doc.layout.lorem_ipsum_box(count: 3, position: :flow, align: :justify)
 
 i = 0
 frame_filled = false
@@ -51,8 +38,13 @@ until frame_filled
   box = boxes[i]
   drawn = false
   until drawn || frame_filled
-    drawn = frame.draw(canvas, box)
-    frame_filled = !frame.find_next_region unless drawn
+    result = frame.fit(box)
+    if result.success?
+      frame.draw(page.canvas, result)
+      drawn = true
+    else
+      frame_filled = !frame.find_next_region
+    end
   end
   i = (i + 1) % boxes.length
 end

data/examples/020-column_box.rb

@@ -1,57 +1,40 @@
-# ## Column Box
+# # Column Box
 #
-# This example shows how [HexaPDF::Layout::Frame] and [HexaPDF::Layout::TextBox]
-# can be used to flow text around objects.
+# This example shows how [HexaPDF::Layout::ColumnBox] can be used to place
+# contents into columns.
 #
 # Three boxes are placed repeatedly onto the frame until it is filled: two
 # floating boxes (one left, one right) and a text box. The text box is styled to
 # flow its content around the other two boxes.
 #
 # Usage:
-# : `ruby frame_text_flow.rb`
+# : `ruby column_box.rb`
 #
 
 require 'hexapdf'
-require 'hexapdf/utils/graphics_helpers'
-
-include HexaPDF::Layout
-include HexaPDF::Utils::GraphicsHelpers
 
 doc = HexaPDF::Document.new
-
-sample_text = "Lorem ipsum dolor sit amet, con\u{00AD}sectetur
-adipis\u{00AD}cing elit, sed do eiusmod tempor incididunt ut labore et
-dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation
-ullamco laboris nisi ut aliquip ex ea commodo consequat.
-".tr("\n", ' ') * 5
-items = [TextFragment.create(sample_text, font: doc.fonts.add("Times"))]
-
 page = doc.pages.add
 media_box = page.box(:media)
-canvas = page.canvas
-frame = Frame.new(media_box.left + 20, media_box.bottom + 20,
-                  media_box.width - 40, media_box.height - 40)
-
-image = doc.images.add(File.join(__dir__, 'machupicchu.jpg'))
-iw, ih = calculate_dimensions(image.width, image.height, rwidth: 100)
+frame = HexaPDF::Layout::Frame.new(media_box.left + 20, media_box.bottom + 20,
+                                   media_box.width - 40, media_box.height - 40)
 
 boxes = []
-3.times do
-  boxes << Box.create(width: iw, height: ih,
-    margin: [10, 30], position: :float) do |canv, box|
-    canv.image(image, at: [0, 0], width: 100)
-  end
-  boxes << Box.create(width: 50, height: 50, margin: 20,
-    position: :float, position_hint: :right,
-    border: {width: 1, color: [[255, 0, 0]]})
-  boxes << TextBox.new(items, style: {position: :flow, align: :justify})
+5.times do
+  boxes << doc.layout.image_box(File.join(__dir__, 'machupicchu.jpg'), width: 100,
+                                style: {margin: [10, 30], position: :float})
+  boxes << HexaPDF::Layout::Box.create(width: 50, height: 50, margin: 20,
+                                       position: :float, position_hint: :right,
+                                       border: {width: 1, color: [[255, 0, 0]]})
+  boxes << doc.layout.lorem_ipsum_box(count: 2, position: :flow, align: :justify)
 end
-columns = ColumnBox.new(boxes) #, style: {position: :flow})
-polygon = Geom2D::Polygon([250, 350], [350, 350], [350, 500], [250, 500])
-#frame.remove_area(polygon)
-#canvas.draw(:geom2d, object: polygon)
+
+polygon = Geom2D::Polygon([200, 350], [400, 350], [400, 450], [200, 450])
+frame.remove_area(polygon)
+page.canvas.draw(:geom2d, object: polygon)
+
+columns = doc.layout.box(:column, children: boxes, columns: 2, style: {position: :flow})
 result = frame.fit(columns)
-p result.success?
-frame.draw(canvas, result)
+frame.draw(page.canvas, result)
 
 doc.write("column_box.pdf", optimize: true)

data/examples/021-list_box.rb

@@ -0,0 +1,26 @@
+# # List Box
+#
+# This example shows how [HexaPDF::Layout::ListBox] can be used to place
+# contents into lists.
+#
+# The list box class provides several options to style the item marker
+# and its general appearance.
+#
+# Usage:
+# : `ruby list_box.rb`
+#
+
+require 'hexapdf'
+
+HexaPDF::Composer.create("list_box.pdf") do |composer|
+  composer.box(:list, content_indentation: 40, item_spacing: 20) do |list|
+    list.lorem_ipsum_box
+    list.image(File.join(__dir__, 'machupicchu.jpg'), height: 100)
+    list.box(:list, item_type: :decimal) do |sub_list|
+      1.upto(10) {|i| sub_list.text("Item #{i}") }
+    end
+    list.box(:column) do |column|
+      column.lorem_ipsum_box(count: 3)
+    end
+  end
+end

data/lib/hexapdf/cli/batch.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/command.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/files.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/fonts.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/form.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -70,6 +70,9 @@ module HexaPDF
           @template = template
           @fill = true
         end
+        options.on('--generate-template', 'Print a template for use with --template') do
+          @generate_template = true
+        end
         options.on('--flatten', 'Flatten the form fields') do
           @flatten = true
         end
@@ -85,6 +88,7 @@ module HexaPDF
         @password = nil
         @fill = false
         @flatten = false
+        @generate_template = false
         @template = nil
         @need_appearances = nil
         @incremental = true
@@ -97,6 +101,10 @@ module HexaPDF
         end
         with_document(in_file, password: @password, out_file: out_file,
                       incremental: @incremental) do |doc|
+          if doc.acro_form[:XFA]
+            $stderr.puts "Warning: Unsupported XFA form detected, some things may not work correctly"
+          end
+
           if !doc.acro_form
             raise "This PDF doesn't contain an interactive form"
           elsif out_file
@@ -113,6 +121,15 @@ module HexaPDF
               doc.catalog.delete(:AcroForm)
               doc.delete(doc.acro_form)
             end
+          elsif @generate_template
+            unsupported_fields = [:signature_field, :password_field]
+            each_field(doc) do |_, _, field, _|
+              next if unsupported_fields.include?(field.concrete_field_type)
+              name = field.full_field_name.gsub(':', "\\:")
+              Array(field.field_value).each do |val|
+                puts "#{name}: #{val.to_s.gsub(/(\r|\r\n|\n)/, '\1  ')}"
+              end
+            end
           else
             list_form_fields(doc)
           end
@@ -216,8 +233,16 @@ module HexaPDF
           field_name = scanner.scan(/(\\:|[^:])*?:/)
           break unless field_name
           field_name.gsub!(/\\:/, ':')
+          field_name.chop!
           field_value = scanner.scan(/.*?(?=^\S|\z)/m)
-          data[field_name.chop] = field_value.strip.gsub(/^\s*/, '') if field_value
+          next unless field_value
+          field_value = field_value.strip.gsub(/^\s*/, '')
+          if data.key?(field_name)
+            data[field_name] = [data[field_name]] unless data[field_name].kind_of?(Array)
+            data[field_name] << field_value
+          else
+            data[field_name] = field_value
+          end
         end
         if !scanner.eos? && command_parser.verbosity_warning?
           $stderr.puts "Warning: Some template could not be parsed"
@@ -228,8 +253,8 @@ module HexaPDF
       # Applies the given value to the field.
       def apply_field_value(field, value)
         case field.concrete_field_type
-        when :single_line_text_field, :multiline_text_field, :comb_text_field, :combo_box,
-            :list_box, :editable_combo_box
+        when :single_line_text_field, :multiline_text_field, :comb_text_field, :file_select_field,
+            :combo_box, :list_box, :editable_combo_box
           field.field_value = value
         when :check_box
           field.field_value = case value
@@ -245,6 +270,8 @@ module HexaPDF
         else
           raise "Field type #{field.concrete_field_type} not yet supported"
         end
+      rescue StandardError
+        raise "Error while setting '#{field.full_field_name}': #{$!.message}"
       end
 
       # Iterates over all non-push button fields in page order. If a field appears on multiple

data/lib/hexapdf/cli/image2pdf.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/images.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/info.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -103,7 +103,7 @@ module HexaPDF
                 "#{correctable ? '(correctable)' : ''}"
             end
             doc.trailer.validate(auto_correct: true, &validation_block)
-            doc.each(only_current: false, only_loaded: false) do |obj|
+            doc.each(only_current: true, only_loaded: false) do |obj|
               indirect_object = obj
               obj.validate(auto_correct: true, &validation_block)
             end

data/lib/hexapdf/cli/inspect.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -229,10 +229,19 @@ module HexaPDF
               end
               IO.copy_stream(@doc.revisions.parser.io, $stdout, length, 0)
             else
-              puts "Document has #{@doc.revisions.size} revision#{@doc.revisions.size == 1 ? '' : 's'}"
-              revision_information do |_, index, count, signature, end_offset|
+              puts "Document has #{@doc.revisions.count} revision#{@doc.revisions.count == 1 ? '' : 's'}"
+              revision_information do |rev, index, count, signature, end_offset|
+                type = if rev.trailer[:XRefStm]
+                         "xref table + stream"
+                       elsif rev.trailer[:Type] == :XRef
+                         "xref stream"
+                       else
+                         "xref table"
+                       end
                 puts "Revision #{index + 1}"
+                puts "  Type      : #{type}"
                 puts "  Objects   : #{count}"
+                puts "  Size      : #{rev.trailer[:Size]}"
                 puts "  Signed    : yes" if signature
                 puts "  Byte range: 0-#{end_offset}"
               end
@@ -342,13 +351,17 @@ module HexaPDF
             end_index = sig[:ByteRange][-2] + sig[:ByteRange][-1]
           else
             io.seek(startxrefs[index], IO::SEEK_SET)
+            buffer = ''.b
             while io.pos < startxrefs[index + 1]
-              if io.gets =~ /^\s*%%EOF\s*$/
-                end_index = io.pos
+              buffer << io.read(1_000)
+              if (buffer_index = buffer.index(/(?:\n|\r\n?)\s*%%EOF\s*(?:\n|\r\n?)?/))
+                end_index = io.pos - buffer.size + buffer_index + $~[0].size
+                break
               end
+              buffer = buffer[-20..-1]
             end
           end
-          yield(rev, index, rev.next_free_oid - 1, sig, end_index)
+          yield(rev, index, rev.each.count, sig, end_index)
         end
       end
 

data/lib/hexapdf/cli/merge.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/modify.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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
@@ -53,14 +53,15 @@ module HexaPDF
         super('modify', takes_commands: false)
         short_desc("Modify a PDF file")
         long_desc(<<~EOF)
-          This command modifies a PDF file. It can be used to select pages that should appear in
-          the output file and/or rotate them. The output file can also be encrypted/decrypted and
-          optimized in various ways.
+          This command modifies a PDF file. It can be used, for example, to select pages that should
+          appear in the output file and/or rotate them. The output file can also be
+          encrypted/decrypted and optimized in various ways.
         EOF
 
         @password = nil
         @pages = '1-e'
         @embed_files = []
+        @annotation_mode = nil
 
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|
@@ -74,6 +75,10 @@ module HexaPDF
                    "used multiple times)") do |file|
           @embed_files << file
         end
+        options.on("--annotations MODE", [:remove, :flatten], "Handling of annotations (either " \
+                   "remove or flatten)") do |mode|
+          @annotation_mode = mode
+        end
         define_optimization_options
         define_encryption_options
       end
@@ -82,6 +87,7 @@ module HexaPDF
         maybe_raise_on_existing_file(out_file)
         with_document(in_file, password: @password, out_file: out_file) do |doc|
           arrange_pages(doc) unless @pages == '1-e'
+          handle_annotations(doc)
           @embed_files.each {|file| doc.files.add(file, embed: true) }
           apply_encryption_options(doc)
           apply_optimization_options(doc)
@@ -109,6 +115,20 @@ module HexaPDF
         doc.pages.add unless doc.pages.count > 0
       end
 
+      # Handles the annotations of all selected pages by doing nothing, removing them or flattening
+      # them.
+      def handle_annotations(doc)
+        return unless @annotation_mode
+
+        doc.pages.each do |page|
+          if @annotation_mode == :remove
+            page.delete(:Annots)
+          else
+            page.flatten_annotations
+          end
+        end
+      end
+
     end
 
   end

data/lib/hexapdf/cli/optimize.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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

data/lib/hexapdf/cli/split.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2014-2021 Thomas Leitner
+# Copyright (C) 2014-2022 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