hexapdf 0.1.0

data/lib/hexapdf/type/font_type1.rb

@@ -0,0 +1,162 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/data_dir'
+require 'hexapdf/type/font_simple'
+require 'hexapdf/font/type1'
+
+module HexaPDF
+  module Type
+
+    # Represents a Type1 font.
+    #
+    # PDF provides 14 built-in fonts that all PDF readers must understand. These 14 fonts are
+    # known as the "Standard 14 Fonts" and are all Type1 fonts. HexaPDF supports these fonts.
+    class FontType1 < FontSimple
+
+      # Provides the names and additional mappings of the Standard 14 Fonts.
+      module StandardFonts
+
+        # The mapping from font name to Standard 14 Font name, since Adobe allows some
+        # additional names for the the Standard 14 Fonts.
+        #
+        # See: ADB1.7 sH.5.5.1
+        @mapping = {
+          %s(CourierNew) => %s(Courier),
+          %s(CourierNew,Italic) => %s(Courier-Oblique),
+          %s(CourierNew,Bold) => %s(Courier-Bold),
+          %s(CourierNew,BoldItalic) => %s(Courier-BoldOblique),
+          %s(Arial) => %s(Helvetica),
+          %s(Arial,Italic) => %s(Helvetica-Oblique),
+          %s(Arial,Bold) => %s(Helvetica-Bold),
+          %s(Arial,BoldItalic) => %s(Helvetica-BoldOblique),
+          %s(TimesNewRoman) => %s(Times-Roman),
+          %s(TimesNewRoman,Italic) => %s(Times-Italic),
+          %s(TimesNewRoman,Bold) => %s(Times-Bold),
+          %s(TimesNewRoman,BoldItalic) => %s(Times-BoldItalic),
+        }
+        %i(Times-Roman Times-Bold Times-Italic Times-BoldItalic
+           Helvetica Helvetica-Bold Helvetica-Oblique Helvetica-BoldOblique
+           Courier Courier-Bold Courier-Oblique Courier-BoldOblique
+           Symbol ZapfDingbats).each {|name| @mapping[name] = name}
+
+        # Returns +true+ if the given name is the name of a standard font.
+        def self.standard_font?(name)
+          @mapping.include?(name)
+        end
+
+        # Returns the standard name of the font in case an additional name is used, or +nil+ if
+        # the given name doesn't belong to a standard font.
+        def self.standard_name(name)
+          @mapping[name]
+        end
+
+        @cache = {}
+
+        # Returns the Type1 font object for the given standard font name, or +nil+ if the given name
+        # doesn't belong to a standard font.
+        def self.font(name)
+          name = @mapping[name]
+          if !standard_font?(name)
+            nil
+          elsif @cache.key?(name)
+            @cache[name]
+          else
+            file = File.join(HexaPDF.data_dir, 'afm', "#{name}.afm")
+            @cache[name] = HexaPDF::Font::Type1::Font.from_afm(file)
+          end
+        end
+
+      end
+
+      define_field :Subtype, type: Symbol, required: true, default: :Type1
+
+      # Returns the unscaled width of the given code point in glyph units, or 0 if the width for the
+      # code point is missing.
+      def width(code)
+        if StandardFonts.standard_font?(self[:BaseFont])
+          StandardFonts.font(self[:BaseFont]).width(encoding.name(code)) || 0
+        else
+          super
+        end
+      end
+
+      # Returns the bounding box of the font or +nil+ if it is not found.
+      def bounding_box
+        bbox = super
+        if bbox
+          bbox
+        elsif StandardFonts.standard_font?(self[:BaseFont])
+          StandardFonts.font(self[:BaseFont]).bounding_box
+        else
+          nil
+        end
+      end
+
+      # Returns +true+ if the font is a symbolic font, +false+ if it is not, and +nil+ if it is
+      # not known.
+      def symbolic?
+        symbolic = super
+        if !symbolic.nil?
+          symbolic
+        elsif StandardFonts.standard_font?(self[:BaseFont])
+          name = StandardFonts.standard_name(self[:BaseFont])
+          name == :ZapfDingbats || name == :Symbol
+        else
+          nil
+        end
+      end
+
+      private
+
+      # Reads the encoding from an embedded font file and handles the special case of the Standard
+      # 14 fonts.
+      def encoding_from_font
+        if StandardFonts.standard_font?(self[:BaseFont])
+          StandardFonts.font(self[:BaseFont]).encoding
+        elsif (obj = self[:FontDescriptor][:FontFile])
+          HexaPDF::Font::Type1::PFBParser.encoding(obj.stream)
+        else
+          raise HexaPDF::Error, "Can't read encoding because Type1 font is not embedded"
+        end
+      end
+
+      # Validates the Type1 font dictionary.
+      def perform_validation
+        super(ignore_missing_font_fields: StandardFonts.standard_font?(self[:BaseFont]))
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/type/form.rb

@@ -0,0 +1,103 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/stream'
+
+module HexaPDF
+  module Type
+
+    # Represents a form XObject of a PDF document.
+    #
+    # See: PDF1.7 s8.10
+    class Form < Stream
+
+      define_field :Type,          type: Symbol,     default: :XObject
+      define_field :Subtype,       type: Symbol,     required: true, default: :Form
+      define_field :FormType,      type: Integer,    default: 1
+      define_field :BBox,          type: Rectangle,  required: true
+      define_field :Matrix,        type: Array
+      define_field :Resources,     type: :XXResources, version: '1.2'
+      define_field :Group,         type: Dictionary, version: '1.4'
+      define_field :Ref,           type: Dictionary, version: '1.4'
+      define_field :Metadata,      type: Stream,     version: '1.4'
+      define_field :PieceInfo,     type: Dictionary, version: '1.3'
+      define_field :LastModified,  type: PDFDate,    version: '1.3'
+      define_field :StructParent,  type: Integer,    version: '1.3'
+      define_field :StructParents, type: Integer,    version: '1.3'
+      define_field :OPI,           type: Dictionary, version: '1.2'
+      define_field :OC,            type: Dictionary, version: '1.5'
+
+      # Returns the path to the PDF file that was used when creating the form object.
+      #
+      # This value is only set when the form object was created by using the image loading
+      # facility (i.e. when treating a single page PDF file as image) and not when the form object
+      # was created in any other way (i.e. manually created or already part of a loaded PDF file).
+      attr_accessor :source_path
+
+      # Returns the rectangle defining the bounding box of the form.
+      def box
+        self[:BBox]
+      end
+
+      # Returns the contents of the form XObject.
+      #
+      # Note: This is the same as #stream but here for interface compatibility with Page.
+      def contents
+        stream
+      end
+
+      # Replaces the contents of the form XObject with the given string.
+      #
+      # Note: This is the same as #stream= but here for interface compatibility with Page.
+      def contents=(data)
+        self.stream = data
+      end
+
+      # Returns the resource dictionary which is automatically created if it doesn't exist.
+      def resources
+        self[:Resources] ||= document.wrap({}, type: :XXResources)
+      end
+
+      # Processes the content streams associated with the page with the given processor object.
+      #
+      # See: HexaPDF::Content::Processor
+      def process_contents(processor)
+        self[:Resources] = {} if self[:Resources].nil?
+        processor.resources = self[:Resources]
+        Content::Parser.parse(contents, processor)
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/type/graphics_state_parameter.rb

@@ -0,0 +1,79 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/dictionary'
+
+module HexaPDF
+  module Type
+
+    # Represents a graphics state parameter dictionary.
+    #
+    # This dictionary can be used to define most graphics state parameters that are available.
+    # Some parameters can only be set by an operator, some only by the dictionary but most by
+    # both.
+    #
+    # See: PDF1.7 s8.4.5, s8.1
+    class GraphicsStateParameter < Dictionary
+
+      define_field :Type,          type: Symbol, required: true, default: :ExtGState
+      define_field :LW,            type: Numeric, version: "1.3"
+      define_field :LC,            type: Integer, version: "1.3"
+      define_field :LJ,            type: Integer, version: "1.3"
+      define_field :ML,            type: Numeric, version: "1.3"
+      define_field :D,             type: Array, version: "1.3"
+      define_field :RI,            type: Symbol, version: "1.3"
+      define_field :OP,            type: Boolean
+      define_field :op,            type: Boolean, version: "1.3"
+      define_field :OPM,           type: Integer, version: "1.3"
+      define_field :Font,          type: Array, version: "1.3"
+      define_field :BG,            type: [Dictionary, Hash, Stream]
+      define_field :BG2,           type: [Dictionary, Hash, Stream, Symbol], version: "1.3"
+      define_field :UCR,           type: [Dictionary, Hash, Stream]
+      define_field :UCR2,          type: [Dictionary, Hash, Stream, Symbol], version: "1.3"
+      define_field :TR,            type: [Dictionary, Hash, Stream, Array, Symbol]
+      define_field :TR2,           type: [Dictionary, Hash, Stream, Array, Symbol], version: "1.3"
+      define_field :HT,            type: [Dictionary, Hash, Stream, Symbol]
+      define_field :FL,            type: Numeric, version: "1.3"
+      define_field :SM,            type: Numeric, version: "1.3"
+      define_field :SA,            type: Boolean
+      define_field :BM,            type: [Symbol, Array], version: "1.4"
+      define_field :SMask,         type: [Dictionary, Hash, Symbol], version: "1.4"
+      define_field :CA,            type: Numeric, version: "1.4"
+      define_field :ca,            type: Numeric, version: "1.4"
+      define_field :AIS,           type: Boolean, version: "1.4"
+      define_field :TK,            type: Boolean, version: "1.4"
+
+    end
+
+  end
+end

data/lib/hexapdf/type/image.rb

@@ -0,0 +1,73 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/stream'
+
+module HexaPDF
+  module Type
+
+    # Represents an image XObject of a PDF document.
+    #
+    # See: PDF1.7 s8.8
+    class Image < Stream
+
+      define_field :Type,             type: Symbol,          default: :XObject
+      define_field :Subtype,          type: Symbol,          required: true, default: :Image
+      define_field :Width,            type: Integer,         required: true
+      define_field :Height,           type: Integer,         required: true
+      define_field :ColorSpace,       type: [Symbol, Array]
+      define_field :BitsPerComponent, type: Integer
+      define_field :Intent,           type: Symbol,          version: '1.1'
+      define_field :ImageMask,        type: Boolean,         default: false
+      define_field :Mask,             type: [Stream, Array], version: '1.3'
+      define_field :Decode,           type: Array
+      define_field :Interpolate,      type: Boolean,         default: false
+      define_field :Alternates,       type: Array,           version: '1.3'
+      define_field :SMask,            type: Stream,          version: '1.4'
+      define_field :SMaskInData,      type: Integer,         version: '1.5'
+      define_field :StructParent,     type: Integer,         version: '1.3'
+      define_field :ID,               type: PDFByteString,   version: '1.3'
+      define_field :OPI,              type: Dictionary,      version: '1.2'
+      define_field :Metadata,         type: Stream,          version: '1.4'
+      define_field :OC,               type: Dictionary,      version: '1.5'
+
+      # Returns the source path that was used when creating the image object.
+      #
+      # This value is only set when the image object was created by using the image loading
+      # facility and not when the image is part of a loaded PDF file.
+      attr_accessor :source_path
+
+    end
+
+  end
+end

data/lib/hexapdf/type/info.rb

@@ -0,0 +1,70 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/dictionary'
+
+module HexaPDF
+  module Type
+
+    # Represents the PDF's document information dictionary.
+    #
+    # The info dictionary is linked via the /Info entry from the Trailer and contains metadata for
+    # the document.
+    #
+    # See: PDF1.7 s14.3.3, Trailer
+    class Info < Dictionary
+
+      define_field :Title,        type: String, version: '1.1'
+      define_field :Author,       type: String
+      define_field :Subject,      type: String, version: '1.1'
+      define_field :Keywords,     type: String, version: '1.1'
+      define_field :Creator,      type: String
+      define_field :Producer,     type: String
+      define_field :CreationDate, type: PDFDate
+      define_field :ModDate,      type: PDFDate
+      define_field :Trapped,      type: Symbol, version: '1.3'
+
+      # Info dictionaries must always be indirect.
+      def must_be_indirect?
+        true
+      end
+
+      # Returns +:XXInfo+.
+      def type
+        :XXInfo
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/type/names.rb

@@ -0,0 +1,69 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2016 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.
+#++
+
+require 'hexapdf/dictionary'
+require 'hexapdf/name_tree_node'
+
+module HexaPDF
+  module Type
+
+    # Represents the PDF's names dictionary which associates names with data for various purposes.
+    #
+    # Each field corresponds to a name tree that holds the information and can be used to find,
+    # add or delete an entry.
+    #
+    # This dictionary is linked via the /Names entry from the HexaPDF::Catalog.
+    #
+    # See: PDF1.7 s7.7.4, HexaPDF::Catalog, HexaPDF::NameTreeNode
+    class Names < Dictionary
+
+      define_field :Dests,                  type: NameTreeNode, version: '1.2'
+      define_field :AP,                     type: NameTreeNode, version: '1.3'
+      define_field :JavaScript,             type: NameTreeNode, version: '1.3'
+      define_field :Pages,                  type: NameTreeNode, version: '1.3'
+      define_field :Templates,              type: NameTreeNode, version: '1.3'
+      define_field :IDS,                    type: NameTreeNode, version: '1.3'
+      define_field :URLS,                   type: NameTreeNode, version: '1.3'
+      define_field :EmbeddedFiles,          type: NameTreeNode, version: '1.4'
+      define_field :AlternatePresentations, type: NameTreeNode, version: '1.4'
+      define_field :Renditions,             type: NameTreeNode, version: '1.5'
+
+      # Returns +:XXNames+.
+      def type
+        :XXNames
+      end
+
+    end
+
+  end
+end