hexapdf 0.1.0

data/lib/hexapdf/font/type1/afm_parser.rb

@@ -0,0 +1,230 @@
+# -*- 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/font/type1/font_metrics'
+require 'hexapdf/error'
+
+module HexaPDF
+  module Font
+    module Type1
+
+      # Parses files in the AFM file format.
+      #
+      # Note that this implementation isn't a full AFM parser, only what is needed for parsing the
+      # AFM files for the 14 PDF core fonts is implemented. However, if need be it should be
+      # adaptable to other AFM files.
+      #
+      # For information on the AFM file format have a look at Adobe technical note #5004 - Adobe
+      # Font Metrics File Format Specification Version 4.1, available at the Adobe website.
+      #
+      # == How Parsing Works
+      #
+      # AFM is a line oriented format. Each line consists of one or more values of supported types
+      # (string, name, number, integer, array, boolean) which are separated by whitespace characters
+      # (space, newline, tab) except for the string type which just uses everything until the end of
+      # the line.
+      #
+      # This parser reads in line by line and the type parsing functions parse a value from the
+      # front of the line and then remove the parsed part from the line, including trailing
+      # whitespace characters.
+      class AFMParser
+
+        # :call-seq:
+        #   Parser.parse(filename)       -> font_metrics
+        #   Parser.parse(io)             -> font_metrics
+        #
+        # Parses the IO or file and returns a FontMetrics object.
+        def self.parse(source)
+          if source.respond_to?(:read)
+            new(source).parse
+          else
+            File.open(source) {|file| new(file).parse}
+          end
+        end
+
+        # Creates a new parse for the given IO stream.
+        def initialize(io)
+          @io = io
+        end
+
+        # Parses the AFM file and returns a FontMetrics object.
+        def parse
+          @metrics = FontMetrics.new
+          sections = []
+          each_line do
+            case (command = parse_name)
+            when /\AStart/
+              sections.push(command)
+              case command
+              when 'StartCharMetrics' then parse_character_metrics
+              when 'StartKernPairs' then parse_kerning_pairs
+              end
+            when /\AEnd/
+              sections.pop
+              break if sections.empty? && command == 'EndFontMetrics.freeze'
+            else
+              if sections.empty?
+                parse_global_font_information(command.to_sym)
+              end
+            end
+          end
+
+          if @metrics.bounding_box && !@metrics.descender
+            @metrics.descender = @metrics.bounding_box[1]
+          end
+          if @metrics.bounding_box && !@metrics.ascender
+            @metrics.ascender = @metrics.bounding_box[3]
+          end
+
+          @metrics
+        end
+
+        private
+
+        # Parses global font information line for the given +command+ (a symbol).
+        #
+        # It is assumed that the command name has already been parsed from the line.
+        #
+        # Note that writing direction metrics are also processed here since the standard 14 core
+        # fonts' AFM files don't have an extra StartDirection section.
+        def parse_global_font_information(command)
+          case command
+          when :FontName then @metrics.font_name = parse_string
+          when :FullName then @metrics.full_name = parse_string
+          when :FamilyName then @metrics.family_name = parse_string
+          when :CharacterSet then @metrics.character_set = parse_string
+          when :EncodingScheme then @metrics.encoding_scheme = parse_string
+          when :Weight then @metrics.weight = parse_string
+          when :FontBBox then
+            @metrics.bounding_box = [parse_number, parse_number, parse_number, parse_number]
+          when :CapHeight then @metrics.cap_height = parse_number
+          when :XHeight then @metrics.x_height = parse_number
+          when :Ascender then @metrics.ascender = parse_number
+          when :Descender then @metrics.descender = parse_number
+          when :StdHW then @metrics.dominant_horizontal_stem_width = parse_number
+          when :StdVW then @metrics.dominant_vertical_stem_width = parse_number
+          when :UnderlinePosition then @metrics.underline_position = parse_number
+          when :UnderlineThickness then @metrics.underline_thickness = parse_number
+          when :ItalicAngle then @metrics.italic_angle = parse_number
+          when :IsFixedPitch then @metrics.is_fixed_pitch = parse_boolean
+          end
+        end
+
+        # Parses the character metrics in a StartCharMetrics section.
+        #
+        # It is assumed that the StartCharMetrics name has already been parsed from the line.
+        def parse_character_metrics
+          parse_integer.times do
+            read_line
+            char = CharacterMetrics.new
+            if @line =~ /C (\S+) ; WX (\S+) ; N (\S+) ; B (\S+) (\S+) (\S+) (\S+) ;((?: L \S+ \S+ ;)+)?/
+              char.code = $1.to_i
+              char.width = $2.to_f
+              char.name = $3.to_sym
+              char.bbox = [$4.to_i, $5.to_i, $6.to_i, $7.to_i]
+              if $8
+                $8.scan(/L (\S+) (\S+)/).each do |name, ligature|
+                  char.ligatures[name] = ligature
+                end
+              end
+            end
+            @metrics.character_metrics[char.name] = char if char.name
+            @metrics.character_metrics[char.code] = char if char.code != -1
+          end
+        end
+
+        # Parses the kerning pairs in a StartKernPairs section.
+        #
+        # It is assumed that the StartKernPairs name has already been parsed from the line.
+        def parse_kerning_pairs
+          parse_integer.times do
+            read_line
+            if @line =~ /KPX (\S+) (\S+) (\S+)/
+              @metrics.kerning_pairs[$1][$2] = $3.to_i
+            end
+          end
+        end
+
+        # Iterates over all the lines in the IO, yielding every time a line has been read into the
+        # internal buffer.
+        def each_line
+          read_line
+          unless parse_name == 'StartFontMetrics'.freeze
+            raise HexaPDF::Error, "The AFM file has to start with StartFontMetrics, not #{@line}"
+          end
+          until @io.eof?
+            read_line
+            yield
+          end
+        end
+
+        # Reads the next line into the current line variable.
+        def read_line
+          @line = @io.readline
+        end
+
+        # Parses and returns the name at the start of the line, with whitespace stripped.
+        def parse_name
+          result = @line[/\S+\s*/].to_s
+          @line[0, result.size] = ''.freeze
+          result.strip!
+          result
+        end
+
+        # Returns the rest of the line, with whitespace stripped.
+        def parse_string
+          line = @line.strip!
+          @line = ''
+          line
+        end
+
+        # Parses the integer at the start of the line.
+        def parse_integer
+          parse_name.to_i
+        end
+
+        # Parses the float number at the start of the line.
+        def parse_number
+          parse_name.to_f
+        end
+
+        # Parses the boolean at the start of the line.
+        def parse_boolean
+          parse_name == 'true'.freeze
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/type1/character_metrics.rb

@@ -0,0 +1,67 @@
+# -*- 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.
+#++
+
+module HexaPDF
+  module Font
+    module Type1
+
+      # Represents the character metrics for an individual character.
+      class CharacterMetrics
+
+        # Decimal value of the default character code (-1 if not encoded).
+        attr_accessor :code
+
+        # Character width in x-direction (y-direction is implicitly 0).
+        attr_accessor :width
+
+        # PostScript language character name.
+        attr_accessor :name
+
+        # Character bounding box as array of four numbers, specifying the x- and y-coordinates of
+        # the lower-left corner and the x- and y-coordinates of the upper-right corner.
+        attr_accessor :bbox
+
+        # Mapping of possible ligatures. This character combined with the character specified by a
+        # key forms the ligature character stored as value of that key. Both keys and values are
+        # character names.
+        attr_accessor :ligatures
+
+        def initialize #:nodoc:
+          @ligatures = {}
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/type1/font.rb

@@ -0,0 +1,123 @@
+# -*- 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 'forwardable'
+require 'hexapdf/font/type1'
+require 'hexapdf/font/encoding'
+
+module HexaPDF
+  module Font
+    module Type1
+
+      # Represents a Type1 font.
+      #
+      # This class abstracts from the specifics of the Type1 font and allows working with it in a
+      # standardized way.
+      #
+      # The following method calls are forwarded to the contained FontMetrics object:
+      #
+      # * font_name
+      # * full_name
+      # * family_name
+      # * weight
+      # * font_bbox
+      # * italic_angle
+      # * ascender
+      # * descender
+      # * cap_height
+      # * x_height
+      # * horizontal_dominant_width
+      # * vertical_dominant_width
+      class Font
+
+        extend Forwardable
+
+        # Creates a Type1 font object from an AFM source.
+        def self.from_afm(source)
+          new(AFMParser.parse(source))
+        end
+
+        # The associated FontMetrics object.
+        attr_reader :metrics
+
+        def_delegators :@metrics, :font_name, :full_name, :family_name
+        def_delegators :@metrics, :weight, :bounding_box, :italic_angle
+        def_delegators :@metrics, :ascender, :descender, :cap_height, :x_height
+        def_delegators :@metrics, :dominant_horizontal_stem_width, :dominant_vertical_stem_width
+
+        # Creates a new Type1 font object with the given font metrics.
+        def initialize(metrics)
+          @metrics = metrics
+        end
+
+        # Returns the built-in encoding of the font.
+        def encoding
+          @encoding ||=
+            begin
+              if @metrics.encoding_scheme == 'AdobeStandardEncoding'.freeze
+                Encoding.for_name(:StandardEncoding)
+              elsif font_name == 'ZapfDingbats' || font_name == 'Symbol'
+                Encoding.for_name((font_name + "Encoding").to_sym)
+              else
+                encoding = Encoding::Base.new
+                @metrics.character_metrics.each do |key, char_metric|
+                  next unless key.kind_of?(Integer) && key >= 0
+                  encoding.code_to_name[key] = char_metric.name
+                end
+                encoding
+              end
+            end
+        end
+
+        # :call-seq:
+        #   font.width(glyph_name)        ->  width or nil
+        #   font.width(glyph_code)        ->  width or nil
+        #
+        # Returns the width of the glyph which can either be specified by glyph name or by an
+        # integer that is interpreted according to the built-in encoding.
+        #
+        # If there is no glyph found for the name or code, +nil+ is returned.
+        def width(glyph)
+          (metric = @metrics.character_metrics[glyph]) && metric.width
+        end
+
+        # Returns the name/id of the missing glyph, i.e. .notdef.
+        def missing_glyph_id
+          :'.notdef'
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/type1/font_metrics.rb

@@ -0,0 +1,117 @@
+# -*- 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/font/type1/character_metrics'
+
+module HexaPDF
+  module Font
+    module Type1
+
+      # Represents the information stored in an AFM font metrics file for a Type1 font that is
+      # needed for working with that font in context of the PDF format.
+      class FontMetrics
+
+        # PostScript name of the font.
+        attr_accessor :font_name
+
+        # Full text name of the font.
+        attr_accessor :full_name
+
+        # Name of the typeface family to which the font belongs.
+        attr_accessor :family_name
+
+        # A string describing the character set of the font.
+        attr_accessor :character_set
+
+        # A string indicating the default encoding used for the font.
+        attr_accessor :encoding_scheme
+
+        # Weight of the font.
+        attr_accessor :weight
+
+        # The font bounding box as array of four numbers, specifying the x- and y-coordinates of the
+        # lower-left corner and the x- and y-coordinates of the upper-right corner.
+        attr_accessor :bounding_box
+
+        # The y-value of the top of the capital H (or 0 or nil if the font doesn't contain a capital
+        # H).
+        attr_accessor :cap_height
+
+        # The y-value of the top of the lowercase x (or 0 or nil if the font doesnt' contain a
+        # lowercase x)
+        attr_accessor :x_height
+
+        # Ascender of the font.
+        attr_accessor :ascender
+
+        # Descender of the font.
+        attr_accessor :descender
+
+        # Dominant width of horizontal stems.
+        attr_accessor :dominant_horizontal_stem_width
+
+        # Dominant width of vertical stems.
+        attr_accessor :dominant_vertical_stem_width
+
+
+        # Distance from the baseline for centering underlining strokes.
+        attr_accessor :underline_position
+
+        # Stroke width for underlining.
+        attr_accessor :underline_thickness
+
+        # Angle (in degrees counter-clockwise from the vertical) of the dominant vertical strokes of
+        # the font.
+        attr_accessor :italic_angle
+
+        # Boolean specifying if the font is a fixed pitch (monospaced) font.
+        attr_accessor :is_fixed_pitch
+
+
+        # Mapping of character codes and names to CharacterMetrics objects.
+        attr_accessor :character_metrics
+
+        # Nested mapping of kerning pairs, ie. each key is a character name and each value is a
+        # mapping from the second character name to the kerning amount.
+        attr_accessor :kerning_pairs
+
+        def initialize #:nodoc:
+          @character_metrics = {}
+          @kerning_pairs = Hash.new {|h, k| h[k] = {}}
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/type1/pfb_parser.rb

@@ -0,0 +1,71 @@
+# -*- 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/font/encoding'
+require 'hexapdf/error'
+require 'strscan'
+
+module HexaPDF
+  module Font
+    module Type1
+
+      # Parses files in the PFB file format.
+      #
+      # Note that this implementation isn't a full PFB parser. It is currently just used for
+      # extracting the font encoding.
+      class PFBParser
+
+        # :call-seq:
+        #   PFBParser.encoding(data)       -> encoding
+        #
+        # Parses the PFB data given as string and returns the found Encoding.
+        def self.encoding(data)
+          enc = Encoding::Base.new
+          ss = StringScanner.new(data)
+          if ss.skip_until(/\/Encoding\s+\d+\s+array.+?(?=\bdup\b)/m)
+            while ss.skip(/dup\s+(\d+)\s+\/(\w+)\s+put\s+/)
+              enc.code_to_name[ss[1].to_i] = ss[2].intern
+            end
+          elsif ss.skip_until(/\/Encoding\s+StandardEncoding\s+def/)
+            enc = Encoding.for_name(:StandardEncoding)
+          else
+            raise HexaPDF::Error, "Unknown Type1 encoding"
+          end
+          enc
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/type1.rb

@@ -0,0 +1,52 @@
+# -*- 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.
+#++
+
+module HexaPDF
+  module Font
+
+    # This module provides classes for handling Type1 fonts.
+    #
+    # Note that not all parts of the file format are supported, only those needed for using the
+    # fonts with PDF.
+    module Type1
+
+      autoload(:AFMParser, 'hexapdf/font/type1/afm_parser')
+      autoload(:FontMetrics, 'hexapdf/font/type1/font_metrics')
+      autoload(:CharacterMetrics, 'hexapdf/font/type1/character_metrics')
+      autoload(:PFBParser, 'hexapdf/font/type1/pfb_parser')
+      autoload(:Font, 'hexapdf/font/type1/font')
+
+    end
+
+  end
+end