hexapdf 0.1.0

data/lib/hexapdf/font/encoding/difference_encoding.rb

@@ -0,0 +1,64 @@
+# -*- 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/base'
+
+module HexaPDF
+  module Font
+    module Encoding
+
+      # The difference encoding uses a base encoding that can be overlayed with additional mappings.
+      #
+      # See: PDF1.7 s9.6.6.1
+      class DifferenceEncoding < Base
+
+        # The base encoding.
+        attr_reader :base_encoding
+
+        # Initializes the Differences object with the given base encoding object.
+        def initialize(base_encoding)
+          super()
+          @base_encoding = base_encoding
+        end
+
+        # Returns the name for the given code, either from this object, if it contains the code, or
+        # from the base encoding.
+        def name(code)
+          code_to_name[code] || base_encoding.name(code)
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/encoding/glyph_list.rb

@@ -0,0 +1,150 @@
+# -*- 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'
+
+module HexaPDF
+  module Font
+    module Encoding
+
+      # Provides access to and mapping functionality for the Adobe Glyph List.
+      #
+      # The Adobe Glyph List is used for mapping glyph names to Unicode values. The mapping itself
+      # is not a one-to-one mapping because some glyphs are mapped to the same Unicode sequence,
+      # e.g. the glyph name for 'A' and the glyph name for 'small capital A'.
+      #
+      # Since a reverse mapping is needed for converting UTF-8 strings to glyph names when encoding
+      # text, this (not unique) reverse mapping is also available. However, only the first occurence
+      # of a particular Unicode string is reverse-mapped.
+      #
+      # See:
+      # * https://github.com/adobe-type-tools/agl-aglfn
+      # * https://github.com/adobe-type-tools/agl-specification
+      class GlyphList
+
+        # Creates and returns the single GlyphList instance.
+        def self.new
+          @instance ||= super
+        end
+
+        # See #name_to_unicode
+        def self.name_to_unicode(name, zapf_dingbats: false)
+          new.name_to_unicode(name, zapf_dingbats: zapf_dingbats)
+        end
+
+        # See #unicode_to_name
+        def self.unicode_to_name(unicode, zapf_dingbats: false)
+          new.unicode_to_name(unicode, zapf_dingbats: zapf_dingbats)
+        end
+
+        def initialize #:nodoc:
+          load
+        end
+
+        # Maps the given name to a string by following the Adobe Glyph Specification. An empty
+        # string is returned if the name has no correct mapping.
+        #
+        # If this method is invoked when dealing with the ZapfDingbats font, the +zapf_dingbats+
+        # option needs to be set to +true+.
+        #
+        # Assumes that the name is a Symbol and that it includes just one component (no
+        # underscores)!
+        def name_to_unicode(name, zapf_dingbats: false)
+          if zapf_dingbats && @zapf_name_to_uni.key?(name)
+            @zapf_name_to_uni[name]
+          elsif @standard_name_to_uni.key?(name)
+            @standard_name_to_uni[name]
+          else
+            name = name.to_s
+            if name =~ /\Auni([0-9A-F]{4})\Z/ || name =~ /\Au([0-9A-f]{4,6})\Z/
+              '' << $1.hex
+            else
+              ''
+            end
+          end
+        end
+
+        # Maps the given Unicode codepoint/string to a name in the Adobe Glyph List, or to .notdef
+        # if there is no mapping.
+        #
+        # If this method is invoked when dealing with the ZapfDingbats font, the +zapf_dingbats+
+        # option needs to be set to +true+.
+        def unicode_to_name(unicode, zapf_dingbats: false)
+          if zapf_dingbats
+            @zapf_uni_to_name.fetch(unicode, :'.notdef')
+          else
+            @standard_uni_to_name.fetch(unicode, :'.notdef')
+          end
+        end
+
+        private
+
+        # Loads the needed Adobe Glyph List files.
+        def load
+          @standard_name_to_uni, @standard_uni_to_name =
+            load_file(File.join(HexaPDF.data_dir, 'encoding', 'glyphlist.txt'))
+          @zapf_name_to_uni, @zapf_uni_to_name =
+            load_file(File.join(HexaPDF.data_dir, 'encoding', 'zapfdingbats.txt'))
+        end
+
+        # Loads an Adobe Glyph List from the specified file and returns the name-to-unicode and
+        # unicode-to-name mappings.
+        #
+        # Regarding the mappings:
+        #
+        # * The name-to-unicode mapping maps a name (Symbol) to an UTF-8 string consisting of one or
+        #   more characters.
+        #
+        # * The unicode-to-name mapping is *not* unique! It only uses the first occurence of a
+        #   Unicode sequence.
+        def load_file(file)
+          name2uni = {}
+          uni2name = {}
+          File.open(file, 'rb') do |f|
+            while (line = f.gets)
+              next if line.start_with?('#'.freeze)
+              index = line.index(';'.freeze)
+              name = line[0, index].to_sym
+              codes = line[index + 1, 50].split(" ".freeze).map(&:hex).pack('U*'.freeze)
+              name2uni[name] = codes
+              uni2name[codes] = name unless uni2name.key?(codes)
+            end
+          end
+          [name2uni.freeze, uni2name.freeze]
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/encoding/mac_expert_encoding.rb

@@ -0,0 +1,221 @@
+# -*- 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/base'
+
+module HexaPDF
+  module Font
+    module Encoding
+
+      # The MacExpertEncoding for Latin texts.
+      #
+      # See: PDF1.7 sD.4
+      class MacExpertEncoding < Base
+
+        def initialize #:nodoc:
+          super
+          @encoding_name = :MacExpertEncoding
+          @code_to_name = {
+            0276  => :AEsmall,
+            0207  => :Aacutesmall,
+            0211  => :Acircumflexsmall,
+            0047  => :Acutesmall,
+            0212  => :Adieresissmall,
+            0210  => :Agravesmall,
+            0214  => :Aringsmall,
+            0141  => :Asmall,
+            0213  => :Atildesmall,
+            0363  => :Brevesmall,
+            0142  => :Bsmall,
+            0256  => :Caronsmall,
+            0215  => :Ccedillasmall,
+            0311  => :Cedillasmall,
+            0136  => :Circumflexsmall,
+            0143  => :Csmall,
+            0254  => :Dieresissmall,
+            0372  => :Dotaccentsmall,
+            0144  => :Dsmall,
+            0216  => :Eacutesmall,
+            0220  => :Ecircumflexsmall,
+            0221  => :Edieresissmall,
+            0217  => :Egravesmall,
+            0145  => :Esmall,
+            0104  => :Ethsmall,
+            0146  => :Fsmall,
+            0140  => :Gravesmall,
+            0147  => :Gsmall,
+            0150  => :Hsmall,
+            0042  => :Hungarumlautsmall,
+            0222  => :Iacutesmall,
+            0224  => :Icircumflexsmall,
+            0225  => :Idieresissmall,
+            0223  => :Igravesmall,
+            0151  => :Ismall,
+            0152  => :Jsmall,
+            0153  => :Ksmall,
+            0302  => :Lslashsmall,
+            0154  => :Lsmall,
+            0364  => :Macronsmall,
+            0155  => :Msmall,
+            0156  => :Nsmall,
+            0226  => :Ntildesmall,
+            0317  => :OEsmall,
+            0227  => :Oacutesmall,
+            0231  => :Ocircumflexsmall,
+            0232  => :Odieresissmall,
+            0362  => :Ogoneksmall,
+            0230  => :Ogravesmall,
+            0277  => :Oslashsmall,
+            0157  => :Osmall,
+            0233  => :Otildesmall,
+            0160  => :Psmall,
+            0161  => :Qsmall,
+            0373  => :Ringsmall,
+            0162  => :Rsmall,
+            0247  => :Scaronsmall,
+            0163  => :Ssmall,
+            0271  => :Thornsmall,
+            0176  => :Tildesmall,
+            0164  => :Tsmall,
+            0234  => :Uacutesmall,
+            0236  => :Ucircumflexsmall,
+            0237  => :Udieresissmall,
+            0235  => :Ugravesmall,
+            0165  => :Usmall,
+            0166  => :Vsmall,
+            0167  => :Wsmall,
+            0170  => :Xsmall,
+            0264  => :Yacutesmall,
+            0330  => :Ydieresissmall,
+            0171  => :Ysmall,
+            0275  => :Zcaronsmall,
+            0172  => :Zsmall,
+            0046  => :ampersandsmall,
+            0201  => :asuperior,
+            0365  => :bsuperior,
+            0251  => :centinferior,
+            0043  => :centoldstyle,
+            0202  => :centsuperior,
+            0072  => :colon,
+            0173  => :colonmonetary,
+            0054  => :comma,
+            0262  => :commainferior,
+            0370  => :commasuperior,
+            0266  => :dollarinferior,
+            0044  => :dollaroldstyle,
+            0045  => :dollarsuperior,
+            0353  => :dsuperior,
+            0245  => :eightinferior,
+            0070  => :eightoldstyle,
+            0241  => :eightsuperior,
+            0344  => :esuperior,
+            0326  => :exclamdownsmall,
+            0041  => :exclamsmall,
+            0126  => :ff,
+            0131  => :ffi,
+            0132  => :ffl,
+            0127  => :fi,
+            0320  => :figuredash,
+            0114  => :fiveeighths,
+            0260  => :fiveinferior,
+            0065  => :fiveoldstyle,
+            0336  => :fivesuperior,
+            0130  => :fl,
+            0242  => :fourinferior,
+            0064  => :fouroldstyle,
+            0335  => :foursuperior,
+            0057  => :fraction,
+            0055  => :hyphen,
+            0137  => :hypheninferior,
+            0321  => :hyphensuperior,
+            0351  => :isuperior,
+            0361  => :lsuperior,
+            0367  => :msuperior,
+            0273  => :nineinferior,
+            0071  => :nineoldstyle,
+            0341  => :ninesuperior,
+            0366  => :nsuperior,
+            0053  => :onedotenleader,
+            0112  => :oneeighth,
+            0174  => :onefitted,
+            0110  => :onehalf,
+            0301  => :oneinferior,
+            0061  => :oneoldstyle,
+            0107  => :onequarter,
+            0332  => :onesuperior,
+            0116  => :onethird,
+            0257  => :osuperior,
+            0133  => :parenleftinferior,
+            0050  => :parenleftsuperior,
+            0135  => :parenrightinferior,
+            0051  => :parenrightsuperior,
+            0056  => :period,
+            0263  => :periodinferior,
+            0371  => :periodsuperior,
+            0300  => :questiondownsmall,
+            0077  => :questionsmall,
+            0345  => :rsuperior,
+            0175  => :rupiah,
+            0073  => :semicolon,
+            0115  => :seveneighths,
+            0246  => :seveninferior,
+            0067  => :sevenoldstyle,
+            0340  => :sevensuperior,
+            0244  => :sixinferior,
+            0066  => :sixoldstyle,
+            0337  => :sixsuperior,
+            0040  => :space,
+            0352  => :ssuperior,
+            0113  => :threeeighths,
+            0243  => :threeinferior,
+            0063  => :threeoldstyle,
+            0111  => :threequarters,
+            0075  => :threequartersemdash,
+            0334  => :threesuperior,
+            0346  => :tsuperior,
+            0052  => :twodotenleader,
+            0252  => :twoinferior,
+            0062  => :twooldstyle,
+            0333  => :twosuperior,
+            0117  => :twothirds,
+            0274  => :zeroinferior,
+            0060  => :zerooldstyle,
+            0342  => :zerosuperior,
+          }
+        end
+
+      end
+
+    end
+  end
+end

data/lib/hexapdf/font/encoding/mac_roman_encoding.rb

@@ -0,0 +1,265 @@
+# -*- 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/base'
+
+module HexaPDF
+  module Font
+    module Encoding
+
+      # The Mac Roman standard encoding for Latin texts.
+      #
+      # See: PDF1.7 sD.1, sD.2
+      class MacRomanEncoding < Base
+
+        def initialize #:nodoc:
+          super
+          @encoding_name = :MacRomanEncoding
+          @code_to_name = {
+            0101 => :A,
+            0256 => :AE,
+            0347 => :Aacute,
+            0345 => :Acircumflex,
+            0200 => :Adieresis,
+            0313 => :Agrave,
+            0201 => :Aring,
+            0314 => :Atilde,
+            0102 => :B,
+            0103 => :C,
+            0202 => :Ccedilla,
+            0104 => :D,
+            0105 => :E,
+            0203 => :Eacute,
+            0346 => :Ecircumflex,
+            0350 => :Edieresis,
+            0351 => :Egrave,
+            0106 => :F,
+            0107 => :G,
+            0110 => :H,
+            0111 => :I,
+            0352 => :Iacute,
+            0353 => :Icircumflex,
+            0354 => :Idieresis,
+            0355 => :Igrave,
+            0112 => :J,
+            0113 => :K,
+            0114 => :L,
+            0115 => :M,
+            0116 => :N,
+            0204 => :Ntilde,
+            0117 => :O,
+            0316 => :OE,
+            0356 => :Oacute,
+            0357 => :Ocircumflex,
+            0205 => :Odieresis,
+            0361 => :Ograve,
+            0257 => :Oslash,
+            0315 => :Otilde,
+            0120 => :P,
+            0121 => :Q,
+            0122 => :R,
+            0123 => :S,
+            0124 => :T,
+            0125 => :U,
+            0362 => :Uacute,
+            0363 => :Ucircumflex,
+            0206 => :Udieresis,
+            0364 => :Ugrave,
+            0126 => :V,
+            0127 => :W,
+            0130 => :X,
+            0131 => :Y,
+            0331 => :Ydieresis,
+            0132 => :Z,
+            0141 => :a,
+            0207 => :aacute,
+            0211 => :acircumflex,
+            0253 => :acute,
+            0212 => :adieresis,
+            0276 => :ae,
+            0210 => :agrave,
+            0046 => :ampersand,
+            0214 => :aring,
+            0136 => :asciicircum,
+            0176 => :asciitilde,
+            0052 => :asterisk,
+            0100 => :at,
+            0213 => :atilde,
+            0142 => :b,
+            0134 => :backslash,
+            0174 => :bar,
+            0173 => :braceleft,
+            0175 => :braceright,
+            0133 => :bracketleft,
+            0135 => :bracketright,
+            0371 => :breve,
+            0245 => :bullet,
+            0143 => :c,
+            0377 => :caron,
+            0215 => :ccedilla,
+            0374 => :cedilla,
+            0242 => :cent,
+            0366 => :circumflex,
+            0072 => :colon,
+            0054 => :comma,
+            0251 => :copyright,
+            0333 => :currency,
+            0144 => :d,
+            0240 => :dagger,
+            0340 => :daggerdbl,
+            0241 => :degree,
+            0254 => :dieresis,
+            0326 => :divide,
+            0044 => :dollar,
+            0372 => :dotaccent,
+            0365 => :dotlessi,
+            0145 => :e,
+            0216 => :eacute,
+            0220 => :ecircumflex,
+            0221 => :edieresis,
+            0217 => :egrave,
+            0070 => :eight,
+            0311 => :ellipsis,
+            0321 => :emdash,
+            0320 => :endash,
+            0075 => :equal,
+            0041 => :exclam,
+            0301 => :exclamdown,
+            0146 => :f,
+            0336 => :fi,
+            0065 => :five,
+            0337 => :fl,
+            0304 => :florin,
+            0064 => :four,
+            0332 => :fraction,
+            0147 => :g,
+            0247 => :germandbls,
+            0140 => :grave,
+            0076 => :greater,
+            0307 => :guillemotleft,
+            0310 => :guillemotright,
+            0334 => :guilsinglleft,
+            0335 => :guilsinglright,
+            0150 => :h,
+            0375 => :hungarumlaut,
+            0055 => :hyphen,
+            0151 => :i,
+            0222 => :iacute,
+            0224 => :icircumflex,
+            0225 => :idieresis,
+            0223 => :igrave,
+            0152 => :j,
+            0153 => :k,
+            0154 => :l,
+            0074 => :less,
+            0302 => :logicalnot,
+            0155 => :m,
+            0370 => :macron,
+            0265 => :mu,
+            0156 => :n,
+            0071 => :nine,
+            0226 => :ntilde,
+            0043 => :numbersign,
+            0157 => :o,
+            0227 => :oacute,
+            0231 => :ocircumflex,
+            0232 => :odieresis,
+            0317 => :oe,
+            0376 => :ogonek,
+            0230 => :ograve,
+            0061 => :one,
+            0273 => :ordfeminine,
+            0274 => :ordmasculine,
+            0277 => :oslash,
+            0233 => :otilde,
+            0160 => :p,
+            0246 => :paragraph,
+            0050 => :parenleft,
+            0051 => :parenright,
+            0045 => :percent,
+            0056 => :period,
+            0341 => :periodcentered,
+            0344 => :perthousand,
+            0053 => :plus,
+            0261 => :plusminus,
+            0161 => :q,
+            0077 => :question,
+            0300 => :questiondown,
+            0042 => :quotedbl,
+            0343 => :quotedblbase,
+            0322 => :quotedblleft,
+            0323 => :quotedblright,
+            0324 => :quoteleft,
+            0325 => :quoteright,
+            0342 => :quotesinglbase,
+            0047 => :quotesingle,
+            0162 => :r,
+            0250 => :registered,
+            0373 => :ring,
+            0163 => :s,
+            0244 => :section,
+            0073 => :semicolon,
+            0067 => :seven,
+            0066 => :six,
+            0057 => :slash,
+            0040 => :space,
+            0243 => :sterling,
+            0164 => :t,
+            0063 => :three,
+            0367 => :tilde,
+            0252 => :trademark,
+            0062 => :two,
+            0165 => :u,
+            0234 => :uacute,
+            0236 => :ucircumflex,
+            0237 => :udieresis,
+            0235 => :ugrave,
+            0137 => :underscore,
+            0166 => :v,
+            0167 => :w,
+            0170 => :x,
+            0171 => :y,
+            0330 => :ydieresis,
+            0264 => :yen,
+            0172 => :z,
+            0060 => :zero,
+            # additions due to PDF1.7 sD.2 footnote 6
+            0312 => :space,
+          }
+        end
+
+      end
+
+    end
+  end
+end