summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/source/generic/hyph-utf8/lib/tex/hyphen/texlive/loader.rb
blob: 878bf0ef0d3c5af0c267e603399b40acb6f4041a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
module TeX
  module Hyphen
    module TeXLive
      module Loader

        def unicode_only? # TODO Spec out
          ['cu', 'sa','as','bn','gu','hi','hy','kn','lo','mul-ethi','ml','mr','or','pa','ta','te', 'pi', 'mk'].include? @bcp47
        end

        def string_enc
          (encoding == nil) ? "" : encoding.upcase + " "
        end

        def lcchars
          if isgreek?
            # some catcodes for XeTeX
            return {
              lccode: {
                0x0027 => '\'',
                0x2019 => '’',
                0x02BC => 'ʼ',
                0x1FBD => '᾽',
                0x1FBF => '᾿',
              }
            }
          end

          return { } unless unicode_only?

          default = {
            comment: 'Set \lccode for ZWNJ and ZWJ.',
            lccode: {
              0x200C => false,
              0x200D => false,
            }
          }

          {
            'mul-ethi' => {
              comment: 'Set \lccode for Ethiopian word space.',
              lccode: {
                0x1361 => false,
                0x1362 => false,
              }
            },
            'cu' => {
              comment: 'fix lccodes for some characters (they were recently included in Unicode)',
              lccode: {
                0x1C82 => 'sharp o in lowercase "uk"',
                0x1DF6 => false,
                0x1DF7 => false,
                0x1DF8 => false,
                0x1DF9 => false,
                0xA69E => false,
                0x1C86 => false,
                0xA67E => false,
                0xFE2E => false,
                0xFE2F => false,
              }
            },
            'sa' => {
              comment: 'Set \lccode for ZWNJ and ZWJ.',
              lccode: {
                0x200C => false,
                0x200D => "\n% Set \\lccode for KANNADA SIGN JIHVAMULIYA and KANNADA SIGN UPADHMANIYA.",
                0x0CF1 => false,
                0x0CF2 => false,
              }
            },
        }[@bcp47] || default
        end

        def utf8_engine_message
          if serbian?
            'UTF-8 Serbian hyphenation patterns'
          else
            sprintf('UTF-8 %s', message)
          end
        end

        def non_utf8_engine_message
          if unicode_only?
            sprintf('No %s - only for Unicode engines', message)
          else
            sprintf('%s%s', string_enc, message)
          end
        end

        def engine_message(engine)
          if engine == 'UTF-8'
            {
              comment: 'Unicode-aware engine (such as XeTeX or LuaTeX) only sees a single (2-byte) argument',
              message: utf8_engine_message
            }
          else # engine is 8-bit or pTeX
            {
              comment: engine +
                if engine == '8-bit' then " engine (such as TeX or pdfTeX)" else "" end,
              message: non_utf8_engine_message
            }
          end
        end

        def input_8bit_file
          if @bcp47 == 'la-x-liturgic'
            {
              input: [pTeX_patterns]
            }
          elsif use_old_patterns_comment
            # explain why we are still using the old patterns
            {
              comment: use_old_patterns_comment,
              input: [legacy_patterns]
            }
          elsif !italic?
            {
              input: [sprintf('conv-utf8-%s.tex', encoding), sprintf('hyph-%s.tex', @bcp47)]
            }
          else
            {
              input: [sprintf('hyph-%s.tex', @bcp47)]
            }
          end
        end

        def input_utf8_line
          if serbian?
            {
              comment: 'We load both scripts at the same time to simplify usage',
              input: ['hyph-sh-latn.tex', 'hyph-sh-cyrl.tex']
            }
          else
            {
              input: [sprintf('hyph-%s.tex', @bcp47)]
            }
          end
        end

        def format_inputs(specification)
          if specification.is_a? Array
            return specification.map do |hash|
              format_inputs(hash)
            end
          end

          byebug unless specification.is_a? Hash
          comment = specification[:comment]
          message = specification[:message]
          if comment then [sprintf('%% %s', comment)] else [] end +
          if message then [sprintf('\\message{%s}', message)] else [] end +
          (specification[:lccode] || []).map do |code, comment|
            sprintf '\\lccode"%04X="%04X%s', code, code, if comment then sprintf ' %% %s', comment else '' end
          end +
          (specification[:input] || []).map do |input|
            sprintf '\\input %s', input
          end
        end

        def input_line(engine)
          if engine == '8-bit'
            input_8bit_file
          elsif engine == 'pTeX'
            { input: [pTeX_patterns] }
          elsif engine == 'UTF-8'
            input_utf8_line
          end
        end

        def utf8_chunk
          [
            engine_message('UTF-8'),
            # lccodes
            lcchars,
            input_line('UTF-8'),
            if has_apostrophes? then { input: [sprintf('hyph-quote-%s.tex', bcp47)] } end
          ].compact
        end

        def nonutf8_chunk(engine)
          [engine_message(engine), unless unicode_only? then input_line(engine) end].compact
        end

        def loadhyph
          if use_old_loader
            legacy_patterns
          else
            sprintf 'loadhyph-%s.tex', @bcp47.gsub(/^sh-/, 'sr-')
          end
        end
      end
    end
  end
end