hexapdf 0.42.0 → 0.44.0

data/lib/hexapdf/layout/text_box.rb

@@ -43,6 +43,11 @@ module HexaPDF
     # objects of a Frame.
     #
     # This class uses TextLayouter behind the scenes to do the hard work.
+    #
+    # == Used Box Properties
+    #
+    # The spacing after the last line can be controlled via the style property +last_line_gap+. Also
+    # see TextLayouter#style for other style properties taken into account.
     class TextBox < Box
 
       # Creates a new TextBox object with the given inline items (e.g. TextFragment and InlineBox
@@ -52,6 +57,7 @@ module HexaPDF
         @tl = TextLayouter.new(style)
         @items = items
         @result = nil
+        @x_offset = 0
       end
 
       # Returns the text that will be drawn.
@@ -66,21 +72,27 @@ module HexaPDF
         true
       end
 
+      # :nodoc:
+      def draw(canvas, x, y)
+        super(canvas, x + @x_offset, y)
+      end
+
+      # :nodoc:
+      def empty?
+        super && (!@result || @result.lines.empty?)
+      end
+
+      private
+
       # Fits the text box into the Frame.
       #
       # Depending on the 'position' style property, the text is either fit into the current region
       # of the frame using +available_width+ and +available_height+, or fit to the shape of the
       # frame starting from the top (when 'position' is set to :flow).
-      #
-      # The spacing after the last line can be controlled via the style property +last_line_gap+.
-      #
-      # Also see TextLayouter#style for other style properties taken into account.
-      def fit(available_width, available_height, frame)
-        return false if (@initial_width > 0 && @initial_width > available_width) ||
-          (@initial_height > 0 && @initial_height > available_height)
-
+      def fit_content(available_width, available_height, frame)
         frame = frame.child_frame(box: self)
-        @width = @height = 0
+        @width = @x_offset = @height = 0
+
         @result = if style.position == :flow
                     @tl.fit(@items, frame.width_specification, frame.shape.bbox.height,
                             apply_first_text_indent: !split_box?, frame: frame)
@@ -91,8 +103,17 @@ module HexaPDF
                     height = (@initial_height > 0 ? @initial_height : available_height) - @height
                     @tl.fit(@items, width, height, apply_first_text_indent: !split_box?, frame: frame)
                   end
+
         @width += if @initial_width > 0 || style.text_align == :center || style.text_align == :right
                     width
+                  elsif style.position == :flow
+                    min_x = +Float::INFINITY
+                    max_x = -Float::INFINITY
+                    @result.lines.each do |line|
+                      min_x = [min_x, line.x_offset].min
+                      max_x = [max_x, line.x_offset + line.width].max
+                    end
+                    min_x.finite? ? (@x_offset = min_x; max_x - min_x) : 0
                   else
                     @result.lines.max_by(&:width)&.width || 0
                   end
@@ -105,44 +126,22 @@ module HexaPDF
           @height += style.line_spacing.gap(@result.lines.last, @result.lines.last)
         end
 
-        @result.status == :success ||
-          (@result.status == :height && @initial_height > 0 && style.overflow == :truncate)
-      end
-
-      # Splits the text box into two boxes if necessary and possible.
-      def split(available_width, available_height, frame)
-        fit(available_width, available_height, frame) unless @result
-
-        if style.position != :flow && (float_compare(@width, available_width) > 0 ||
-                                       float_compare(@height, available_height) > 0)
-          [nil, self]
-        elsif @result.remaining_items.empty?
-          [self]
-        elsif @result.lines.empty?
-          [nil, self]
-        else
-          [self, create_box_for_remaining_items]
+        if @result.status == :success
+          fit_result.success!
+        elsif @result.status == :height && !@result.lines.empty?
+          fit_result.overflow!
         end
       end
 
-      # :nodoc:
-      def empty?
-        super && (!@result || @result.lines.empty?)
+      # Splits the text box into two.
+      def split_content
+        [self, create_box_for_remaining_items]
       end
 
-      private
-
       # Draws the text into the box.
       def draw_content(canvas, x, y)
-        return unless @result
-
-        if @result.status == :height && @initial_height > 0 && style.overflow == :error
-          raise HexaPDF::Error, "Text doesn't fit into box with limited height and " \
-            "style property overflow is set to :error"
-        end
-
         return if @result.lines.empty?
-        @result.draw(canvas, x, y + content_height)
+        @result.draw(canvas, x - @x_offset, y + content_height)
       end
 
       # Creates a new TextBox instance for the items remaining after fitting the box.

data/lib/hexapdf/parser.rb

@@ -362,29 +362,35 @@ module HexaPDF
         pos = @io.pos
         lines = @io.read(step_size + 40).split(/[\r\n]+/)
 
-        eof_index = lines.rindex {|l| l.strip == '%%EOF' }
-        if !eof_index
-          eof_not_found = true
-        elsif lines[eof_index - 1].strip =~ /\Astartxref\s(\d+)\z/
-          startxref_offset = $1.to_i
-          startxref_mangled = true
-          break # we found it even if it the syntax is not entirely correct
-        elsif eof_index < 2 || lines[eof_index - 2].strip != "startxref"
-          startxref_missing = true
-        else
-          startxref_offset = lines[eof_index - 1].to_i
-          break # we found it
+        # Need to iterate through the whole lines array in case there are multiple %%EOF to try
+        eof_index = 0
+        while (eof_index = lines[0..(eof_index - 1)].rindex {|l| l.strip == '%%EOF' })
+          if eof_index > 0 && lines[eof_index - 1].strip =~ /\Astartxref\s(\d+)\z/
+            startxref_offset = $1.to_i
+            startxref_mangled = true
+            break # we found it even if it the syntax is not entirely correct
+          elsif eof_index < 2
+            startxref_missing = true
+            break
+          elsif lines[eof_index - 2].strip != "startxref"
+            startxref_missing = true
+          else
+            startxref_offset = lines[eof_index - 1].to_i
+            break # we found it
+          end
         end
+        eof_not_found ||= !eof_index
+        break if startxref_offset
       end
 
-      if eof_not_found
-        maybe_raise("PDF file trailer with end-of-file marker not found", pos: pos,
-                    force: !eof_index)
-      elsif startxref_mangled
+      if startxref_mangled
         maybe_raise("PDF file trailer keyword startxref on same line as value", pos: pos)
       elsif startxref_missing
         maybe_raise("PDF file trailer is missing startxref keyword", pos: pos,
-                    force: eof_index < 2 || lines[eof_index - 2].strip != "startxref")
+                    force: !startxref_offset)
+      elsif eof_not_found
+        maybe_raise("PDF file trailer with end-of-file marker not found", pos: pos,
+                    force: !startxref_offset)
       end
 
       @startxref_offset = startxref_offset

data/lib/hexapdf/type/acro_form/form.rb

@@ -163,10 +163,21 @@ module HexaPDF
           field
         end
 
+        # Creates an untyped namespace field for creating hierarchies.
+        #
+        # Example:
+        #
+        #   form.create_namespace_field('text')
+        #   form.create_text_field('text.a1')
+        def create_namespace_field(name)
+          create_field(name)
+        end
+
         # Creates a new text field with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field:
         #
@@ -202,8 +213,9 @@ module HexaPDF
 
         # Creates a new multiline text field with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field, see
         # #create_text_field for details.
@@ -221,8 +233,9 @@ module HexaPDF
         # The +max_chars+ argument defines the maximum number of characters the comb text field can
         # accommodate.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field, see
         # #create_text_field for details.
@@ -238,8 +251,9 @@ module HexaPDF
 
         # Creates a new file select field with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field, see
         # #create_text_field for details.
@@ -254,8 +268,9 @@ module HexaPDF
 
         # Creates a new password field with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field, see
         # #create_text_field for details.
@@ -270,8 +285,9 @@ module HexaPDF
 
         # Creates a new check box with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # Before a field value other than +false+ can be assigned to the check box, a widget needs
         # to be created.
@@ -281,8 +297,9 @@ module HexaPDF
 
         # Creates a radio button with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # Before a field value other than +nil+ can be assigned to the radio button, at least one
         # widget needs to be created.
@@ -292,8 +309,9 @@ module HexaPDF
 
         # Creates a combo box with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field:
         #
@@ -319,8 +337,9 @@ module HexaPDF
 
         # Creates a list box with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         #
         # The optional keyword arguments allow setting often used properties of the field:
         #
@@ -345,10 +364,38 @@ module HexaPDF
 
         # Creates a signature field with the given name and adds it to the form.
         #
-        # The +name+ may contain dots to signify a field hierarchy. If so, the referenced parent
-        # fields must already exist. If it doesn't contain dots, a top-level field is created.
+        # The +name+ may contain dots to signify a field hierarchy. If the parent fields don't
+        # already exist, they are created as pure namespace fields (see #create_namespace_field). If
+        # the +name+ doesn't contain dots, a top-level field is created.
         def create_signature_field(name)
-          create_field(name, :Sig) {}
+          create_field(name, :Sig)
+        end
+
+        # :call-seq:
+        #    form.delete_field(name)
+        #    form.delete_field(field)
+        #
+        # Deletes the field specified by the given name or via the given field object.
+        #
+        # If the field is a signature field, the associated signature dictionary is also deleted.
+        def delete_field(name_or_field)
+          field = (name_or_field.kind_of?(String) ? field_by_name(name_or_field) : name_or_field)
+          document.delete(field[:V]) if field.field_type == :Sig
+
+          to_delete = field.each_widget(direct_only: false).to_a
+          document.pages.each do |page|
+            next unless page.key?(:Annots)
+            page_annots = page[:Annots].to_a - to_delete
+            page[:Annots].value.replace(page_annots)
+          end
+          to_delete.each {|widget| document.delete(widget) }
+
+          if field[:Parent]
+            field[:Parent][:Kids].delete(field)
+          else
+            self[:Fields].delete(field)
+          end
+          document.delete(field)
         end
 
         # Fills form fields with the values from the given +data+ hash.
@@ -485,23 +532,27 @@ module HexaPDF
 
         private
 
-        # Creates a new field with the full name +name+ and the field type +type+.
-        def create_field(name, type)
+        # Creates a new field with the full name +name+ and the optional field type +type+.
+        def create_field(name, type = nil)
           parent_name, _, name = name.rpartition('.')
           parent_field = parent_name.empty? ? nil : field_by_name(parent_name)
           if !parent_name.empty? && !parent_field
-            raise HexaPDF::Error, "Parent field '#{parent_name}' not found"
+            parent_field = create_namespace_field(parent_name)
           end
 
-          field = document.add({FT: type, T: name, Parent: parent_field},
-                               type: :XXAcroFormField, subtype: type)
+          field = if type
+                    document.add({FT: type, T: name, Parent: parent_field},
+                                 type: :XXAcroFormField, subtype: type)
+                  else
+                    document.add({T: name, Parent: parent_field}, type: :XXAcroFormField)
+                  end
           if parent_field
             (parent_field[:Kids] ||= []) << field
           else
             (self[:Fields] ||= []) << field
           end
 
-          yield(field)
+          yield(field) if block_given?
 
           field
         end

data/lib/hexapdf/type/file_specification.rb

@@ -158,11 +158,11 @@ module HexaPDF
       end
 
       # :call-seq:
-      #   file_spec.embed(filename, name: File.basename(filename), register: true)   -> ef_stream
-      #   file_spec.embed(io, name:, register: true)                                 -> ef_stream
+      #   file_spec.embed(filename, name: File.basename(filename), mime_type: nil, register: true)   -> ef_stream
+      #   file_spec.embed(io, name:, mime_type: nil, register: true)                                 -> ef_stream
       #
-      # Embeds the given file or IO stream into the PDF file, sets the path accordingly and returns
-      # the created stream object.
+      # Embeds the given file or IO stream into the PDF file, sets the path and MIME type
+      # accordingly and returns the created stream object.
       #
       # If a file is given, the +name+ option defaults to the basename of the file. However, if an
       # IO object is given, the +name+ argument is mandatory.
@@ -177,13 +177,16 @@ module HexaPDF
       # name::
       #     The name that should be used as path value and when registering.
       #
+      # mime_type::
+      #     Optionally specifies the MIME type of the file.
+      #
       # register::
       #     Specifies whether the embedded file will be added to the EmbeddedFiles name tree under
       #     the +name+. If the name is already taken, it's value is overwritten.
       #
       # The file has to be available until the PDF document gets written because reading and
       # writing is done lazily.
-      def embed(file_or_io, name: nil, register: true)
+      def embed(file_or_io, name: nil, mime_type: nil, register: true)
         name ||= File.basename(file_or_io) if file_or_io.kind_of?(String)
         if name.nil?
           raise ArgumentError, "The name argument is mandatory when given an IO object"
@@ -194,6 +197,7 @@ module HexaPDF
 
         self[:EF] ||= {}
         ef_stream = self[:EF][:UF] = self[:EF][:F] = document.add({Type: :EmbeddedFile})
+        ef_stream[:Subtype] = mime_type.to_sym if mime_type
         stat = if file_or_io.kind_of?(String)
                  File.stat(file_or_io)
                elsif file_or_io.respond_to?(:stat)

data/lib/hexapdf/type/graphics_state_parameter.rb

@@ -51,7 +51,7 @@ module HexaPDF
 
       define_type :ExtGState
 
-      define_field :Type,          type: Symbol, required: true, default: type
+      define_field :Type,          type: Symbol, default: type
       define_field :LW,            type: Numeric, version: "1.3"
       define_field :LC,            type: Integer, version: "1.3"
       define_field :LJ,            type: Integer, version: "1.3"

data/lib/hexapdf/version.rb

@@ -37,6 +37,6 @@
 module HexaPDF
 
   # The version of HexaPDF.
-  VERSION = '0.42.0'
+  VERSION = '0.44.0'
 
 end

data/test/hexapdf/document/test_files.rb

@@ -43,6 +43,11 @@ describe HexaPDF::Document::Files do
       assert_equal('Some file', spec[:Desc])
     end
 
+    it "optionally sets the MIME type of an embedded file" do
+      spec = @doc.files.add(@file.path, mime_type: 'application/pdf')
+      assert_equal(:'application/pdf', spec.embedded_file_stream[:Subtype])
+    end
+
     it "requires the name argument when given an IO object" do
       assert_raises(ArgumentError) { @doc.files.add(StringIO.new) }
     end

data/test/hexapdf/document/test_metadata.rb

@@ -187,6 +187,27 @@ describe HexaPDF::Document::Metadata do
       assert_equal(metadata, @doc.catalog[:Metadata].stream.sub(/(?<=id=")\w+/, ''))
     end
 
+    it "writes the custom metadata" do
+      @metadata.delete
+      @metadata.custom_metadata("<rdf:Description>Test</rdf:Description>")
+      @metadata.custom_metadata("<rdf:Description>Test2</rdf:Description>")
+      @doc.write(StringIO.new, update_fields: false)
+      metadata = <<~XMP
+        <?xpacket begin="" id=""?>
+        <x:xmpmeta xmlns:x="adobe:ns:meta/">
+        <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+        <rdf:Description rdf:about="" xmlns:pdf="http://ns.adobe.com/pdf/1.3/">
+        <pdf:Producer>HexaPDF version #{HexaPDF::VERSION}</pdf:Producer>
+        </rdf:Description>
+        <rdf:Description>Test</rdf:Description>
+        <rdf:Description>Test2</rdf:Description>
+        </rdf:RDF>
+        </x:xmpmeta>
+        <?xpacket end="r"?>
+      XMP
+      assert_equal(metadata, @doc.catalog[:Metadata].stream.sub(/(?<=id=")\w+/, ''))
+    end
+
     it "writes the XMP metadata" do
       title = HexaPDF::Document::Metadata::LocalizedString.new('Der Titel')
       title.language = 'de'