hexapdf 1.1.1 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 902a2c520a3fa1a6c0128edc938ab82f604faca6f08548d68e0226a7f9426422
-  data.tar.gz: 942551d188d12f5a841f4a1631982e813a85823570b4ba3ec085cf846cf164dd
+  metadata.gz: e0e469ae650b98b48c88b662dab27cb405b676c706639c8c1cf358d6aefc8f53
+  data.tar.gz: d170526233e1e9aa37403c1bd8d2aa38697641c1b4fb4d4a5f6d8f02f299585b
 SHA512:
-  metadata.gz: 26be23186793f7d704831969652e2392135eb5e0d8460ba7505b27fb546ac5043c10513cf358f16890723978ee0cbe28129f97185cba8a6f9c69f279f446cdd4
-  data.tar.gz: c094967af75096e58d6493d459a46ac345d109ef1feb58de0bd5ca746ce0dc39880467c7208928e881c325bbb32c9c5c5ac55738e3b5a0570ad330c2a0fd39ba
+  metadata.gz: fd18408ed2c2474e3395bf59b3a0281cb23005d16bf7d5b9d93f673dfa131fc215f342018d0cdce2de053db85c000a68c28a76ad980b0432b1a159bd51b1ed0c
+  data.tar.gz: c58b13ed27c980bb9670b9521a12b1640fc3960aea1188f6135951cfd1503a28e7633cb3f6be8c63d478d64a88e0bbdc9b84bdbc982aa3ec000aeac1a8627597

data/CHANGELOG.md

@@ -1,3 +1,82 @@
+## 1.3.0 - 2025-04-23
+
+### Added
+
+* [HexaPDF::Type::Annotations::Square] for rectangle annotations as well as
+  [HexaPDF::Document::Annotations#create_rectangle]
+* [HexaPDF::Type::Annotations::Circle] for ellipse annotations as well as
+  [HexaPDF::Document::Annotations#create_ellipse]
+* Basic appearance generation for push button fields
+* [HexaPDF::Type::Annotation::BorderEffect] type class
+* [HexaPDF::Type::Annotations::BorderEffect] module that provides convenience
+  access to the border effect dictionary
+* [HexaPDF::Document::Layout#style?] and [HexaPDF::Composer#style?] for checking
+  whether a given style (name) exists
+* [HexaPDF::Layout::Style#each_property] for iterating over all set properties
+* [HexaPDF::Layout::Style#merge] for merging another style instance
+* [HexaPDF::Layout::Style#box_options] for specifying box initialization options
+* [HexaPDF::Layout::Style#font_bold] and [HexaPDF::Layout::Style#font_italic]
+  for setting bold and/or italic variants independently of the font name
+* [HexaPDF::PDFArray#map!] for mapping elements in-place
+* [HexaPDF::PDFArray#compact!] for removing `nil` elements
+
+### Changed
+
+* **Breaking change**: [HexaPDF::Type::Annotations::Widget::MarkerStyle::new]
+  got a new positional argument
+* [HexaPDF::Type::Annotations::Widget#marker_style] to allow setting and
+  retrieving the font for push buttons
+* Extracted `#interior_color` from [HexaPDF::Type::Annotations::Line] into
+  [HexaPDF::Type::Annotations::InteriorColor]
+* CLI command `hexapdf inspect` to support decoding Form XObject streams
+* [HexaPDF::Layout::Style#line_spacing] to accept a `LineSpacing` object when
+  setting the value
+
+### Fixed
+
+* Text extraction with macOS Preview due a bug in Preview
+* [HexaPDF::PDFArray#reject!] to work according to documented method signature
+* [HexaPDF::Type::AcroForm::Field#create_widget] to ensure the proper type
+  class is stored in the document in case an embedded widget is extracted
+* [HexaPDF::Type::AcroForm::Form] validation to ensure that all field objects in
+  the field hierarchy are using a field type class
+* [HexaPDF::Type::AcroForm::Form] validation to delete merged fields
+
+
+## 1.2.0 - 2025-02-10
+
+### Added
+
+* **Breaking change**: Argument `compact` to [HexaPDF::Document#write] to
+  automatically run the 'compact' optimization task
+* [HexaPDF::Document::Annotations], accessible via
+  [HexaPDF::Document#annotations], as convenience interface for working with
+  annotations
+* [HexaPDF::Type::Annotations::AppearanceGenerator] as central class for
+  generating appearance streams
+* [HexaPDF::Type::Annotations::Line] for line annotations
+* [HexaPDF::Type::Annotation#opacity] for setting the opacity values when
+  regenerating the appearance stream
+* [HexaPDF::Type::Annotation#contents] for setting the text of the annotation
+* Configuration option 'acro_form.text_field.on_max_len_exceeded' to allow
+  custom handling of too long values
+
+### Changed
+
+* **Breaking change**: Extracted `#border_style` and associated data class from
+  [HexaPDF::Type::Annotations::Widget] into
+  [HexaPDF::Type::Annotations::BorderStyling]
+* [HexaPDF::Type::Form#canvas] to allow getting the canvas without the initial
+  translation
+
+### Fixed
+
+* AcroForm Javascript actions to gracefully handle the special values infinity
+  and NaN
+* Type1 and TrueType font wrappers to handle the case where fonts are first
+  added and later deleted
+
+
 ## 1.1.1 - 2025-01-08
 
 ### Fixed

data/README.md

@@ -82,7 +82,7 @@ canvas.text("Hello World!", at: [20, 400])
 doc.write("hello-world.pdf")
 ~~~
 
-For detailed information have a look at the [HexaPDF website][website] where you will the API
+For detailed information have a look at the [HexaPDF website][website] where you will find the API
 documentation, example code and more.
 
 It is recommend to use the HTML API documentation provided by the HexaPDF website as it is enhanced

data/lib/hexapdf/cli/command.rb

@@ -35,7 +35,6 @@
 #++
 
 require 'io/console'
-require 'ostruct'
 require 'cmdparse'
 require 'hexapdf/document'
 require 'hexapdf/font/true_type'
@@ -68,21 +67,22 @@ module HexaPDF
 
       def initialize(*args, **kwargs, &block) #:nodoc:
         super
-        @out_options = OpenStruct.new
-        @out_options.compact = true
-        @out_options.compress_pages = false
-        @out_options.object_streams = :preserve
-        @out_options.xref_streams = :preserve
-        @out_options.streams = :preserve
-        @out_options.optimize_fonts = false
-        @out_options.prune_page_resources = false
-
-        @out_options.encryption = :preserve
-        @out_options.enc_user_pwd = @out_options.enc_owner_pwd = nil
-        @out_options.enc_key_length = 128
-        @out_options.enc_algorithm = :aes
-        @out_options.enc_force_v4 = false
-        @out_options.enc_permissions = []
+        @out_options = {
+          compact: true,
+          compress_pages: false,
+          object_streams: :preserve,
+          xref_streams: :preserve,
+          streams: :preserve,
+          optimize_fonts: false,
+          prune_page_resources: false,
+          encryption: :preserve,
+          enc_user_pwd: nil,
+          enc_owner_pwd: nil,
+          enc_key_length: 128,
+          enc_algorithm: :aes,
+          enc_force_v4: false,
+          enc_permissions: [],
+        }
       end
 
       protected
@@ -163,7 +163,7 @@ module HexaPDF
           if command_parser.verbosity_info?
             puts "Creating output document #{out_file}"
           end
-          doc.write(out_file, validate: false, incremental: incremental)
+          doc.write(out_file, validate: false, compact: false, incremental: incremental)
         end
       end
 
@@ -183,35 +183,35 @@ module HexaPDF
         options.separator("")
         options.separator("Optimization options:")
         options.on("--[no-]compact", "Delete unnecessary PDF objects (default: " \
-                   "#{@out_options.compact})") do |c|
-          @out_options.compact = c
+                   "#{@out_options[:compact]})") do |c|
+          @out_options[:compact] = c
         end
         options.on("--object-streams MODE", [:generate, :preserve, :delete],
                    "Handling of object streams (either generate, preserve or delete; " \
-                     "default: #{@out_options.object_streams})") do |os|
-          @out_options.object_streams = os
+                     "default: #{@out_options[:object_streams]})") do |os|
+          @out_options[:object_streams] = os
         end
         options.on("--xref-streams MODE", [:generate, :preserve, :delete],
                    "Handling of cross-reference streams (either generate, preserve or delete; " \
-                     "default: #{@out_options.xref_streams})") do |x|
-          @out_options.xref_streams = x
+                     "default: #{@out_options[:xref_streams]})") do |x|
+          @out_options[:xref_streams] = x
         end
         options.on("--streams MODE", [:compress, :preserve, :uncompress],
                    "Handling of stream data (either compress, preserve or uncompress; default: " \
-                     "#{@out_options.streams})") do |streams|
-          @out_options.streams = streams
+                     "#{@out_options[:streams]})") do |streams|
+          @out_options[:streams] = streams
         end
         options.on("--[no-]compress-pages", "Recompress page content streams (may take a long " \
-                   "time; default: #{@out_options.compress_pages})") do |c|
-          @out_options.compress_pages = c
+                   "time; default: #{@out_options[:compress_pages]})") do |c|
+          @out_options[:compress_pages] = c
         end
         options.on("--[no-]prune-page-resources", "Prunes unused objects from the page resources " \
-                   "(may take a long time; default: #{@out_options.prune_page_resources})") do |c|
-          @out_options.prune_page_resources = c
+                   "(may take a long time; default: #{@out_options[:prune_page_resources]})") do |c|
+          @out_options[:prune_page_resources] = c
         end
         options.on("--[no-]optimize-fonts", "Optimize embedded font files; " \
-                   "default: #{@out_options.optimize_fonts})") do |o|
-          @out_options.optimize_fonts = o
+                   "default: #{@out_options[:optimize_fonts]})") do |o|
+          @out_options[:optimize_fonts] = o
         end
       end
 
@@ -222,37 +222,37 @@ module HexaPDF
         options.separator("")
         options.separator("Encryption options:")
         options.on("--decrypt", "Remove any encryption") do
-          @out_options.encryption = :remove
+          @out_options[:encryption] = :remove
         end
         options.on("--encrypt", "Encrypt the output file") do
-          @out_options.encryption = :add
+          @out_options[:encryption] = :add
         end
         options.on("--owner-password PASSWORD", String, "The owner password to be set on the " \
                    "output file (use - for reading from standard input)") do |pwd|
-          @out_options.encryption = :add
-          @out_options.enc_owner_pwd = (pwd == '-' ? read_password("Owner password") : pwd)
+          @out_options[:encryption] = :add
+          @out_options[:enc_owner_pwd] = (pwd == '-' ? read_password("Owner password") : pwd)
         end
         options.on("--user-password PASSWORD", String, "The user password to be set on the " \
                    "output file (use - for reading from standard input)") do |pwd|
-          @out_options.encryption = :add
-          @out_options.enc_user_pwd = (pwd == '-' ? read_password("User password") : pwd)
+          @out_options[:encryption] = :add
+          @out_options[:enc_user_pwd] = (pwd == '-' ? read_password("User password") : pwd)
         end
         options.on("--algorithm ALGORITHM", [:aes, :arc4],
                    "The encryption algorithm: aes or arc4 (default: " \
-                     "#{@out_options.enc_algorithm})") do |a|
-          @out_options.encryption = :add
-          @out_options.enc_algorithm = a
+                     "#{@out_options[:enc_algorithm]})") do |a|
+          @out_options[:encryption] = :add
+          @out_options[:enc_algorithm] = a
         end
         options.on("--key-length BITS", Integer,
                    "The encryption key length in bits (default: " \
-                     "#{@out_options.enc_key_length})") do |i|
-          @out_options.encryption = :add
-          @out_options.enc_key_length = i
+                     "#{@out_options[:enc_key_length]})") do |i|
+          @out_options[:encryption] = :add
+          @out_options[:enc_key_length] = i
         end
         options.on("--force-V4",
                    "Force use of encryption version 4 if key length=128 and algorithm=arc4") do
-          @out_options.encryption = :add
-          @out_options.enc_force_v4 = true
+          @out_options[:encryption] = :add
+          @out_options[:enc_force_v4] = true
         end
         syms = HexaPDF::Encryption::StandardSecurityHandler::Permissions::SYMBOL_TO_PERMISSION.keys
         options.on("--permissions PERMS", Array,
@@ -264,8 +264,8 @@ module HexaPDF
             end
             perm.to_sym
           end
-          @out_options.encryption = :add
-          @out_options.enc_permissions = perms
+          @out_options[:encryption] = :add
+          @out_options[:enc_permissions] = perms
         end
       end
 
@@ -273,12 +273,12 @@ module HexaPDF
       #
       # See: #define_optimization_options
       def apply_optimization_options(doc)
-        doc.task(:optimize, compact: @out_options.compact,
-                 object_streams: @out_options.object_streams,
-                 xref_streams: @out_options.xref_streams,
-                 compress_pages: @out_options.compress_pages,
-                 prune_page_resources: @out_options.prune_page_resources)
-        if @out_options.streams != :preserve || @out_options.optimize_fonts
+        doc.task(:optimize, compact: @out_options[:compact],
+                 object_streams: @out_options[:object_streams],
+                 xref_streams: @out_options[:xref_streams],
+                 compress_pages: @out_options[:compress_pages],
+                 prune_page_resources: @out_options[:prune_page_resources])
+        if @out_options[:streams] != :preserve || @out_options[:optimize_fonts]
           doc.each do |obj|
             optimize_stream(obj)
             optimize_font(obj)
@@ -292,15 +292,15 @@ module HexaPDF
 
       # Applies the chosen stream mode to the given object.
       def optimize_stream(obj)
-        return if @out_options.streams == :preserve || !obj.respond_to?(:set_filter) ||
+        return if @out_options[:streams] == :preserve || !obj.respond_to?(:set_filter) ||
           Array(obj[:Filter]).any? {|f| IGNORED_FILTERS[f] }
 
-        obj.set_filter(@out_options.streams == :compress ? :FlateDecode : nil)
+        obj.set_filter(@out_options[:streams] == :compress ? :FlateDecode : nil)
       end
 
       # Optimize the object if it is a font object.
       def optimize_font(obj)
-        return unless @out_options.optimize_fonts && obj.kind_of?(HexaPDF::Type::Font) &&
+        return unless @out_options[:optimize_fonts] && obj.kind_of?(HexaPDF::Type::Font) &&
           (obj[:Subtype] == :TrueType ||
            (obj[:Subtype] == :Type0 && obj.descendant_font[:Subtype] == :CIDFontType2)) &&
           obj.embedded?
@@ -319,14 +319,14 @@ module HexaPDF
       #
       # See: #define_encryption_options
       def apply_encryption_options(doc)
-        case @out_options.encryption
+        case @out_options[:encryption]
         when :add
-          doc.encrypt(algorithm: @out_options.enc_algorithm,
-                      key_length: @out_options.enc_key_length,
-                      force_v4: @out_options.enc_force_v4,
-                      permissions: @out_options.enc_permissions,
-                      owner_password: @out_options.enc_owner_pwd,
-                      user_password: @out_options.enc_user_pwd)
+          doc.encrypt(algorithm: @out_options[:enc_algorithm],
+                      key_length: @out_options[:enc_key_length],
+                      force_v4: @out_options[:enc_force_v4],
+                      permissions: @out_options[:enc_permissions],
+                      owner_password: @out_options[:enc_owner_pwd],
+                      user_password: @out_options[:enc_user_pwd])
         when :remove
           doc.encrypt(name: nil)
         end

data/lib/hexapdf/cli/inspect.rb

@@ -188,12 +188,20 @@ module HexaPDF
                   end
             serialize(obj.value, recursive: true) if obj
 
-          when 's', 'stream', 'raw', 'raw-stream'
+          when 's', 'stream', 'raw', 'raw-stream', 'sd'
             if (obj = pdf_object_from_string_reference(data.shift) rescue $stderr.puts($!.message)) &&
                 obj.kind_of?(HexaPDF::Stream)
-              source = (command.start_with?('raw') ? obj.stream_source : obj.stream_decoder)
-              while source.alive? && (stream_data = source.resume)
-                $stdout.write(stream_data)
+              if command == 'sd'
+                if obj.respond_to?(:process_contents)
+                  obj.process_contents(ContentProcessor.new)
+                else
+                  $stderr.puts("Error: The object is not a Form XObject or page")
+                end
+              else
+                source = (command.start_with?('raw') ? obj.stream_source : obj.stream_decoder)
+                while source.alive? && (stream_data = source.resume)
+                  $stdout.write(stream_data)
+                end
               end
             elsif command_parser.verbosity_info?
               $stderr.puts("Note: Object has no stream data")
@@ -396,7 +404,7 @@ module HexaPDF
         io = @doc.revisions.parser.io
 
         io.seek(0, IO::SEEK_END)
-        startxrefs = @doc.revisions.map {|rev| rev.trailer[:Prev] } <<
+        startxrefs = @doc.revisions.map {|rev| rev.trailer[:Prev].to_i } <<
                      @doc.revisions.parser.startxref_offset <<
                      io.pos
         startxrefs.sort!
@@ -427,6 +435,7 @@ module HexaPDF
         ["OID[,GEN] | o[bject] OID[,GEN]", "Print object"],
         ["r[ecursive] OID[,GEN]", "Print object recursively"],
         ["s[tream] OID[,GEN]", "Print filtered stream"],
+        ["sd OID[,GEN]", "Print the decoded stream of a Form XObject or page"],
         ["raw[-stream] OID[,GEN]", "Print raw stream"],
         ["rev[ision] [NUMBER]", "Print or extract revision"],
         ["x[ref] OID[,GEN]", "Print the cross-reference entry"],

data/lib/hexapdf/cli/modify.rb

@@ -34,7 +34,6 @@
 # commercial licenses are available at <https://gettalong.at/hexapdf/>.
 #++
 
-require 'ostruct'
 require 'hexapdf/cli/command'
 
 module HexaPDF

data/lib/hexapdf/cli/optimize.rb

@@ -53,11 +53,11 @@ module HexaPDF
         EOF
 
         @password = nil
-        @out_options.compact = true
-        @out_options.xref_streams = :generate
-        @out_options.object_streams = :generate
-        @out_options.streams = :compress
-        @out_options.optimize_fonts = true
+        @out_options[:compact] = true
+        @out_options[:xref_streams] = :generate
+        @out_options[:object_streams] = :generate
+        @out_options[:streams] = :compress
+        @out_options[:optimize_fonts] = true
 
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|

data/lib/hexapdf/composer.rb

@@ -261,6 +261,20 @@ module HexaPDF
       @document.layout.style(name, base: base, **properties)
     end
 
+    # Returns +true+ if a style with the given +name+ exists, else +false+.
+    #
+    # See HexaPDF::Document::Layout#style for details; this method is just a thin wrapper around
+    # that method.
+    #
+    # Example:
+    #
+    #   composer.style(:header, font: 'Helvetica')
+    #   composer.style?(:header)     # => true
+    #   composer.style?(:paragraph)  # => false
+    def style?(name)
+      @document.layout.style?(name)
+    end
+
     # :call-seq:
     #    composer.styles              -> styles
     #    composer.styles(**mapping)   -> styles

data/lib/hexapdf/configuration.rb

@@ -224,6 +224,21 @@ module HexaPDF
   # acro_form.text_field.default_width::
   #    A number specifying the default width of AcroForm text fields which should be auto-sized.
   #
+  # acro_form.text_field.on_max_len_exceeded::
+  #    Callback hook when the value of a text field exceeds the set maximum length.
+  #
+  #    The value needs to be an object that responds to \#call(field, value) where +field+ is the
+  #    AcroForm text field on which the value is set and +value+ is the invalid value. The returned
+  #    value is used instead of the invalid value.
+  #
+  #    The default implementation raises an error.
+  #
+  # annotation.appearance_generator::
+  #    The class that should be used for generating appearances for annotations. If the value is a
+  #    String, it should contain the name of a constant to such a class.
+  #
+  #    See HexaPDF::Type::Annotations::AppearanceGenerator
+  #
   # debug::
   #    If set to +true+, enables debug output.
   #
@@ -502,6 +517,10 @@ module HexaPDF
                           "#{field.concrete_field_type} field named '#{field.full_field_name}'"
                       end,
                       'acro_form.text_field.default_width' => 100,
+                      'acro_form.text_field.on_max_len_exceeded' => proc do |field, value|
+                        raise HexaPDF::Error, "Value exceeds maximum allowed length of #{field[:MaxLen]}"
+                      end,
+                      'annotation.appearance_generator' => 'HexaPDF::Type::Annotations::AppearanceGenerator',
                       'debug' => false,
                       'document.auto_decrypt' => true,
                       'document.on_invalid_string' => proc do |str|
@@ -690,6 +709,7 @@ module HexaPDF
                         XXAcroFormField: 'HexaPDF::Type::AcroForm::Field',
                         XXAppearanceDictionary: 'HexaPDF::Type::Annotation::AppearanceDictionary',
                         Border: 'HexaPDF::Type::Annotation::Border',
+                        XXBorderEffect: 'HexaPDF::Type::Annotation::BorderEffect',
                         SigFieldLock: 'HexaPDF::Type::AcroForm::SignatureField::LockDictionary',
                         SV: 'HexaPDF::Type::AcroForm::SignatureField::SeedValueDictionary',
                         SVCert: 'HexaPDF::Type::AcroForm::SignatureField::CertificateSeedValueDictionary',
@@ -746,6 +766,9 @@ module HexaPDF
                           Text: 'HexaPDF::Type::Annotations::Text',
                           Link: 'HexaPDF::Type::Annotations::Link',
                           Widget: 'HexaPDF::Type::Annotations::Widget',
+                          Line: 'HexaPDF::Type::Annotations::Line',
+                          Square: 'HexaPDF::Type::Annotations::Square',
+                          Circle: 'HexaPDF::Type::Annotations::Circle',
                           XML: 'HexaPDF::Type::Metadata',
                           GTS_PDFX: 'HexaPDF::Type::OutputIntent',
                           GTS_PDFA1: 'HexaPDF::Type::OutputIntent',
@@ -774,6 +797,9 @@ module HexaPDF
                           Text: 'HexaPDF::Type::Annotations::Text',
                           Link: 'HexaPDF::Type::Annotations::Link',
                           Widget: 'HexaPDF::Type::Annotations::Widget',
+                          Line: 'HexaPDF::Type::Annotations::Line',
+                          Square: 'HexaPDF::Type::Annotations::Square',
+                          Circle: 'HexaPDF::Type::Annotations::Circle',
                         },
                         XXAcroFormField: {
                           Tx: 'HexaPDF::Type::AcroForm::TextField',

data/lib/hexapdf/content/graphics_state.rb

@@ -255,7 +255,7 @@ module HexaPDF
           array.inject(0) {|m, n| m < 0 ? m : (n < 0 ? -1 : m + n) } <= 0)
           raise ArgumentError, "Invalid line dash pattern: #{array.inspect} #{phase.inspect}"
         end
-        @array = array.freeze
+        @array = array
         @phase = phase
       end
 

data/lib/hexapdf/digital_signature/signing/signed_data_creator.rb

@@ -108,7 +108,7 @@ module HexaPDF
         # +type+::
         #     The type can either be :cms when creating standard PDF CMS signatures or :pades when
         #     creating PAdES compatible signatures. PAdES signatures are part of PDF 2.0.
-        def create(data, type: :cms, &block) # :yield: digested_data
+        def create(data, type: :cms, &block) # :yield: digest_algorithm, hashed_data
           signed_attrs = create_signed_attrs(data, signing_time: (type == :cms))
           signature = digest_and_sign_data(set(*signed_attrs.value).to_der, &block)
           unsigned_attrs = create_unsigned_attrs(signature)