Module: JotPDF::Document

Defined in:

lib/jot_pdf/document.rb

Defined Under Namespace

Classes: DocumentWriter, FontManager, ImageContext, NonstandardFont, PageContext, StandardFont, TextContext

Class Method Summary

• .generate_unicode_cmap(mapping) ⇒ Object
• .write(io, &block) ⇒ Object

Class Method Details

.generate_unicode_cmap(mapping) ⇒ Object

# File 'lib/jot_pdf/document.rb', line 356

def self.generate_unicode_cmap(mapping)
  <<~CMAP
    /CIDInit /ProcSet findresource begin
    12 dict begin
    begincmap
    /CIDSystemInfo 3 dict dup begin
      /Registry (Adobe) def
      /Ordering (UCS) def
      /Supplement 0 def
    end def
    /CMapName /Adobe-Identity-UCS def
    /CMapType 2 def

    1 begincodespacerange
    <00> <FF>
    endcodespacerange

    #{mapping.length} beginbfchar
    #{mapping.map do |code, codepoint|
        format("<%<code>02X><%<codepoint>s>", code:, codepoint: codepoint.chr(::Encoding::UTF_16BE).unpack1("H*"))
      end.join("\n")}
    endbfchar

    endcmap
    CMapName currentdict /CMap defineresource pop
    end
    end
  CMAP
end

.write(io, &block) ⇒ Object

# File 'lib/jot_pdf/document.rb', line 386

def self.write(io, &block)
  Core.write(io) do
    header

    alloc_obj => resources_obj
    alloc_obj => pages_obj
    writer = Document::DocumentWriter.new(self, resources_obj:, pages_obj:)
    writer.dsl(&block)

    # @type var font_file_objs: Hash[::String | Symbol, ObjectRef]
    # @type var widths_objs: Hash[::String | Symbol, ObjectRef]
    # @type var tounicode_objs: Hash[::String | Symbol, ObjectRef]
    font_file_objs = {}
    widths_objs = {}
    tounicode_objs = {}
    writer.font_manager.loaded_fonts.each do |n, f|
      # TODO: How can Steep use is_a? on _Font?
      # rubocop:disable Style/CaseEquality
      next unless NonstandardFont === f
      # rubocop:enable Style/CaseEquality

      subset_data = f.encode_subset
      obj do
        dict do
          entry("Length").of_num subset_data.bytesize
          entry("Length1").of_num subset_data.bytesize # always required for TrueType
        end
        stream do |stream|
          stream << subset_data
        end
      end => font_file_obj
      font_file_objs[n] = font_file_obj

      subset = TTFunk::File.new(subset_data)
      obj.of_array do
        (subset.os2.first_char_index..subset.os2.last_char_index).each do |code|
          gid = subset.cmap.tables.first[code]
          width_in_units = subset.horizontal_metrics.for(gid).advance_width
          num (Float(width_in_units) * 1000 / subset.header.units_per_em).to_i
        end
      end => widths_obj
      widths_objs[n] = widths_obj

      alloc_obj => length_obj
      stream_size = nil
      obj do
        dict { entry("Length").of_ref length_obj }
        stream do |w|
          w << generate_unicode_cmap(f.subset.to_unicode_map)
        end => stream_size
      end => tounicode_obj
      obj(length_obj).of_num stream_size
      tounicode_objs[n] = tounicode_obj
    end

    obj(resources_obj).of_dict do
      entry("XObject").of_dict do
        writer.images.each do |n, r|
          entry(n).of_ref r
        end
      end
      entry("ProcSet").of_array { name "PDF"; name "Text"; name "ImageB"; name "ImageC"; name "ImageI" }
      entry("Font").of_dict do
        writer.font_manager.loaded_fonts.each do |n, f|
          entry(n.to_s).of_dict do
            entry("Type") { name "Font" }
            case f
            when StandardFont
              entry("Subtype") { name "Type1" }
              entry("BaseFont") { name n.to_s }
            when NonstandardFont
              subset = TTFunk::File.new(f.encode_subset)
              # https://github.com/prawnpdf/prawn/blob/aaea7f6beda092ba48001414125a576dcf891362/lib/prawn/fonts/ttf.rb#L446-L447
              base_name = subset.name.postscript_name[0, 33].delete("\0")
              entry("Subtype").of_name "TrueType"
              entry("FirstChar").of_num subset.os2.first_char_index
              entry("LastChar").of_num subset.os2.last_char_index
              entry("ToUnicode").of_ref tounicode_objs[n]
              entry("BaseFont").of_name base_name
              entry("Widths").of_ref widths_objs[n]
              entry("FontDescriptor").of_dict do
                entry("Ascent").of_num subset.ascent
                entry("Descent").of_num subset.descent
                entry("CapHeight").of_num subset.os2.cap_height
                entry("StemV").of_num 0
                entry("ItalicAngle").of_num 0
                entry("Flags").of_num 0b100
                entry("FontBBox").of_array do
                  subset.bbox.each do |i|
                    num i
                  end
                end
                entry("FontName").of_name base_name
                entry("XHeight").of_num subset.os2.x_height
                entry("FontFile2").of_ref font_file_objs[n]
              end
            end
          end
        end
      end
    end => resources_obj

    obj(pages_obj).of_dict do
      entry("Type") { name "Pages" }
      entry("Kids").of_array do
        writer.pages.each do |page|
          ref page
        end
      end
      entry("Count") { num writer.pages.size }
    end
    obj.of_dict do
      entry("Type") { name "Catalog" }
      entry("Pages") { ref pages_obj }
    end => root_obj
    xref
    trailer do
      entry("Root") { ref root_obj }
    end
  end
end