line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
# ##################################################################### Otakar Smrz, 2003/08/05 |
2
|
|
|
|
|
|
|
# |
3
|
|
|
|
|
|
|
# Encoding of Arabic: ArabTeX Notation by Klaus Lagally, ZDMG ################################# |
4
|
|
|
|
|
|
|
|
5
|
|
|
|
|
|
|
package Encode::Arabic::ArabTeX::ZDMG; |
6
|
|
|
|
|
|
|
|
7
|
|
|
|
|
|
|
our $VERSION = '14.1'; |
8
|
|
|
|
|
|
|
|
9
|
2
|
|
|
2
|
|
20260
|
use 5.008; |
|
2
|
|
|
|
|
5
|
|
10
|
|
|
|
|
|
|
|
11
|
2
|
|
|
2
|
|
6
|
use strict; |
|
2
|
|
|
|
|
1
|
|
|
2
|
|
|
|
|
30
|
|
12
|
2
|
|
|
2
|
|
4
|
use warnings; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
35
|
|
13
|
|
|
|
|
|
|
|
14
|
2
|
|
|
2
|
|
5
|
use Carp; |
|
2
|
|
|
|
|
1
|
|
|
2
|
|
|
|
|
97
|
|
15
|
|
|
|
|
|
|
|
16
|
2
|
|
|
2
|
|
625
|
use Encode::Arabic::ArabTeX (); |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
34
|
|
17
|
2
|
|
|
2
|
|
6
|
use base 'Encode::Arabic::ArabTeX'; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
122
|
|
18
|
|
|
|
|
|
|
|
19
|
|
|
|
|
|
|
|
20
|
2
|
|
|
2
|
|
6
|
use Encode::Encoding; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
30
|
|
21
|
2
|
|
|
2
|
|
6
|
use base 'Encode::Encoding'; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
61
|
|
22
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
__PACKAGE__->Define('ZDMG', 'ArabTeX-ZDMG'); |
24
|
|
|
|
|
|
|
|
25
|
|
|
|
|
|
|
|
26
|
2
|
|
|
2
|
|
6
|
use Encode::Mapper ':others', ':silent', ':join'; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
7
|
|
27
|
|
|
|
|
|
|
|
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
our %options; # records of options per package .. global register |
30
|
|
|
|
|
|
|
our %option; # options of the caller package .. used with local |
31
|
|
|
|
|
|
|
|
32
|
|
|
|
|
|
|
|
33
|
|
|
|
|
|
|
sub import { # perform import as if Encode were used one level before this module |
34
|
|
|
|
|
|
|
|
35
|
2
|
100
|
66
|
2
|
|
14
|
if (defined $_[1] and $_[1] eq ':xml') { # interfere little with possible Encode's options |
36
|
|
|
|
|
|
|
|
37
|
|
|
|
|
|
|
Encode::Mapper->options ( |
38
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
'override' => [ # override rules of these LHS .. no other tricks ^^ |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
( # combinations of '<' and '>' with the other bytes |
42
|
|
|
|
|
|
|
map { |
43
|
|
|
|
|
|
|
|
44
|
1
|
|
|
|
|
2
|
my $x = chr $_; |
|
254
|
|
|
|
|
171
|
|
45
|
|
|
|
|
|
|
|
46
|
254
|
|
|
|
|
539
|
"<" . $x, [ "<" . $x, ">" ], # propagate the '>' sign implying .. |
47
|
|
|
|
|
|
|
">" . $x, [ $x, ">" ], # .. preservation of the bytes |
48
|
|
|
|
|
|
|
|
49
|
|
|
|
|
|
|
} 0x00 .. 0x3B, 0x3D, 0x3F .. 0xFF |
50
|
|
|
|
|
|
|
), |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
">>", ">", # stop the whole process .. |
53
|
|
|
|
|
|
|
"<>", "<>", # .. do not even start it |
54
|
|
|
|
|
|
|
|
55
|
|
|
|
|
|
|
"><", [ "<", ">" ], # rather than nested '<' and '>', .. |
56
|
|
|
|
|
|
|
"<<", [ "<<", ">" ], |
57
|
|
|
|
|
|
|
|
58
|
|
|
|
|
|
|
">\\<", [ "<", ">" ], # .. prefer these escape sequences |
59
|
|
|
|
|
|
|
">\\\\", [ "\\", ">" ], |
60
|
|
|
|
|
|
|
">\\>", [ ">", ">" ], |
61
|
|
|
|
|
|
|
|
62
|
|
|
|
|
|
|
">", ">", # singular symbols may migrate right .. |
63
|
|
|
|
|
|
|
"<", "<", # .. or preserve the rest of the data |
64
|
|
|
|
|
|
|
] |
65
|
|
|
|
|
|
|
|
66
|
|
|
|
|
|
|
); |
67
|
|
|
|
|
|
|
|
68
|
1
|
|
|
|
|
32
|
splice @_, 1, 1; |
69
|
|
|
|
|
|
|
} |
70
|
|
|
|
|
|
|
|
71
|
2
|
50
|
33
|
|
|
6
|
if (defined $_[1] and $_[1] eq ':describe') { |
72
|
|
|
|
|
|
|
|
73
|
0
|
|
|
|
|
0
|
__PACKAGE__->options($_[1]); |
74
|
0
|
|
|
|
|
0
|
splice @_, 1, 1; |
75
|
|
|
|
|
|
|
} |
76
|
|
|
|
|
|
|
|
77
|
2
|
|
|
|
|
10
|
require Encode; |
78
|
|
|
|
|
|
|
|
79
|
2
|
100
|
|
|
|
21
|
push @Encode::ISA, 'Exporter' unless Encode->can('export_to_level'); |
80
|
|
|
|
|
|
|
|
81
|
2
|
|
|
|
|
170
|
Encode->export_to_level(1, @_); |
82
|
|
|
|
|
|
|
} |
83
|
|
|
|
|
|
|
|
84
|
|
|
|
|
|
|
|
85
|
|
|
|
|
|
|
sub encoder ($;%) { |
86
|
1
|
|
|
1
|
1
|
1101
|
my ($cls, %opt) = @_; |
87
|
|
|
|
|
|
|
|
88
|
1
|
|
|
|
|
3
|
my $encoder = []; |
89
|
|
|
|
|
|
|
|
90
|
|
|
|
|
|
|
|
91
|
1
|
|
|
|
|
23
|
$encoder->[0] = Encode::Mapper->compile ( |
92
|
|
|
|
|
|
|
|
93
|
|
|
|
|
|
|
[ |
94
|
|
|
|
|
|
|
'silent' => 0, |
95
|
|
|
|
|
|
|
], |
96
|
|
|
|
|
|
|
|
97
|
|
|
|
|
|
|
"\x{0054}", "\\cap t", "\x{0074}", "t", |
98
|
|
|
|
|
|
|
|
99
|
|
|
|
|
|
|
"\x{1E6E}", "\\cap _t", "\x{1E6F}", "_t", |
100
|
|
|
|
|
|
|
"\x{0054}\x{0331}", "\\cap _t", "\x{0074}\x{0331}", "_t", |
101
|
|
|
|
|
|
|
|
102
|
|
|
|
|
|
|
"\x{0044}", "\\cap d", "\x{0064}", "d", |
103
|
|
|
|
|
|
|
|
104
|
|
|
|
|
|
|
"\x{1E0E}", "\\cap _d", "\x{1E0F}", "_d", |
105
|
|
|
|
|
|
|
"\x{0044}\x{0331}", "\\cap _d", "\x{0064}\x{0331}", "_d", |
106
|
|
|
|
|
|
|
|
107
|
|
|
|
|
|
|
"\x{0052}", "\\cap r", "\x{0072}", "r", |
108
|
|
|
|
|
|
|
|
109
|
|
|
|
|
|
|
"\x{005A}", "\\cap z", "\x{007A}", "z", |
110
|
|
|
|
|
|
|
|
111
|
|
|
|
|
|
|
"\x{0053}", "\\cap s", "\x{0073}", "s", |
112
|
|
|
|
|
|
|
|
113
|
|
|
|
|
|
|
"\x{0160}", "\\cap ^s", "\x{0161}", "^s", |
114
|
|
|
|
|
|
|
"\x{0053}\x{030C}", "\\cap ^s", "\x{0073}\x{030C}", "^s", |
115
|
|
|
|
|
|
|
|
116
|
|
|
|
|
|
|
"\x{1E62}", "\\cap .s", "\x{1E63}", ".s", |
117
|
|
|
|
|
|
|
"\x{0053}\x{0323}", "\\cap .s", "\x{0073}\x{0323}", ".s", |
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
"\x{1E0C}", "\\cap .d", "\x{1E0D}", ".d", |
120
|
|
|
|
|
|
|
"\x{0044}\x{0323}", "\\cap .d", "\x{0064}\x{0323}", ".d", |
121
|
|
|
|
|
|
|
|
122
|
|
|
|
|
|
|
"\x{1E6C}", "\\cap .t", "\x{1E6D}", ".t", |
123
|
|
|
|
|
|
|
"\x{0054}\x{0323}", "\\cap .t", "\x{0074}\x{0323}", ".t", |
124
|
|
|
|
|
|
|
|
125
|
|
|
|
|
|
|
"\x{1E92}", "\\cap .z", "\x{1E93}", ".z", |
126
|
|
|
|
|
|
|
"\x{005A}\x{0323}", "\\cap .z", "\x{007A}\x{0323}", ".z", |
127
|
|
|
|
|
|
|
|
128
|
|
|
|
|
|
|
"\x{004C}", "\\cap l", "\x{006C}", "l", |
129
|
|
|
|
|
|
|
|
130
|
|
|
|
|
|
|
"\x{004E}", "\\cap n", "\x{006E}", "n", |
131
|
|
|
|
|
|
|
|
132
|
|
|
|
|
|
|
# "\x{0054}", "\\cap T", "\x{0074}", "T", |
133
|
|
|
|
|
|
|
# "\x{004E}", "\\cap N", "\x{006E}", "N", |
134
|
|
|
|
|
|
|
# "\x{0057}", "\\cap W", "\x{0077}", "W", |
135
|
|
|
|
|
|
|
|
136
|
|
|
|
|
|
|
"\x{0041}", "\\cap a", "\x{0061}", "a", |
137
|
|
|
|
|
|
|
|
138
|
|
|
|
|
|
|
"\x{0045}", "\\cap e", "\x{0065}", "e", |
139
|
|
|
|
|
|
|
|
140
|
|
|
|
|
|
|
"\x{0049}", "\\cap i", "\x{0069}", "i", |
141
|
|
|
|
|
|
|
|
142
|
|
|
|
|
|
|
"\x{004F}", "\\cap o", "\x{006F}", "o", |
143
|
|
|
|
|
|
|
|
144
|
|
|
|
|
|
|
"\x{0055}", "\\cap u", "\x{0075}", "u", |
145
|
|
|
|
|
|
|
|
146
|
|
|
|
|
|
|
"\x{0100}", "\\cap A", "\x{0101}", "A", |
147
|
|
|
|
|
|
|
"\x{0041}\x{0304}", "\\cap A", "\x{0061}\x{0304}", "A", |
148
|
|
|
|
|
|
|
|
149
|
|
|
|
|
|
|
"\x{0112}", "\\cap E", "\x{0113}", "E", |
150
|
|
|
|
|
|
|
"\x{0045}\x{0304}", "\\cap E", "\x{0065}\x{0304}", "E", |
151
|
|
|
|
|
|
|
|
152
|
|
|
|
|
|
|
"\x{012A}", "\\cap I", "\x{012B}", "I", |
153
|
|
|
|
|
|
|
"\x{0049}\x{0304}", "\\cap I", "\x{0069}\x{0304}", "I", |
154
|
|
|
|
|
|
|
|
155
|
|
|
|
|
|
|
"\x{014C}", "\\cap O", "\x{014D}", "O", |
156
|
|
|
|
|
|
|
"\x{004F}\x{0304}", "\\cap O", "\x{006F}\x{0304}", "O", |
157
|
|
|
|
|
|
|
|
158
|
|
|
|
|
|
|
"\x{016A}", "\\cap U", "\x{016B}", "U", |
159
|
|
|
|
|
|
|
"\x{0055}\x{0304}", "\\cap U", "\x{0075}\x{0304}", "U", |
160
|
|
|
|
|
|
|
|
161
|
|
|
|
|
|
|
"\x{02BC}", "\"", |
162
|
|
|
|
|
|
|
"\x{02BE}", "'", |
163
|
|
|
|
|
|
|
"\x{02BF}", "`", |
164
|
|
|
|
|
|
|
|
165
|
|
|
|
|
|
|
"\x{0042}", "\\cap b", "\x{0062}", "b", |
166
|
|
|
|
|
|
|
|
167
|
|
|
|
|
|
|
"\x{01E6}", "\\cap ^g", "\x{01E7}", "^g", |
168
|
|
|
|
|
|
|
"\x{0047}\x{030C}", "\\cap ^g", "\x{0067}\x{030C}", "^g", |
169
|
|
|
|
|
|
|
|
170
|
|
|
|
|
|
|
"\x{1E24}", "\\cap .h", "\x{1E25}", ".h", |
171
|
|
|
|
|
|
|
"\x{0048}\x{0323}", "\\cap .h", "\x{0068}\x{0323}", ".h", |
172
|
|
|
|
|
|
|
|
173
|
|
|
|
|
|
|
"\x{1E2A}", "\\cap _h", "\x{1E2B}", "_h", |
174
|
|
|
|
|
|
|
"\x{0048}\x{032E}", "\\cap _h", "\x{0068}\x{032E}", "_h", |
175
|
|
|
|
|
|
|
|
176
|
|
|
|
|
|
|
"\x{0120}", "\\cap .g", "\x{0121}", ".g", |
177
|
|
|
|
|
|
|
"\x{0047}\x{0307}", "\\cap .g", "\x{0067}\x{0307}", ".g", |
178
|
|
|
|
|
|
|
|
179
|
|
|
|
|
|
|
"\x{0046}", "\\cap f", "\x{0066}", "f", |
180
|
|
|
|
|
|
|
|
181
|
|
|
|
|
|
|
"\x{0051}", "\\cap q", "\x{0071}", "q", |
182
|
|
|
|
|
|
|
|
183
|
|
|
|
|
|
|
"\x{004B}", "\\cap k", "\x{006B}", "k", |
184
|
|
|
|
|
|
|
|
185
|
|
|
|
|
|
|
"\x{004D}", "\\cap m", "\x{006D}", "m", |
186
|
|
|
|
|
|
|
|
187
|
|
|
|
|
|
|
"\x{0048}", "\\cap h", "\x{0068}", "h", |
188
|
|
|
|
|
|
|
|
189
|
|
|
|
|
|
|
"\x{0057}", "\\cap w", "\x{0077}", "w", |
190
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
"\x{0059}", "\\cap y", "\x{0079}", "y", |
192
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
|
194
|
|
|
|
|
|
|
"\x{0050}", "\\cap p", "\x{0070}", "p", |
195
|
|
|
|
|
|
|
|
196
|
|
|
|
|
|
|
"\x{0056}", "\\cap v", "\x{0076}", "v", |
197
|
|
|
|
|
|
|
|
198
|
|
|
|
|
|
|
"\x{0047}", "\\cap g", "\x{0067}", "g", |
199
|
|
|
|
|
|
|
|
200
|
|
|
|
|
|
|
|
201
|
|
|
|
|
|
|
"\x{0043}", "\\cap c", "\x{0063}", "c", |
202
|
|
|
|
|
|
|
|
203
|
|
|
|
|
|
|
"\x{010C}", "\\cap ^c", "\x{010D}", "^c", |
204
|
|
|
|
|
|
|
"\x{0043}\x{030C}", "\\cap ^c", "\x{0063}\x{030C}", "^c", |
205
|
|
|
|
|
|
|
|
206
|
|
|
|
|
|
|
"\x{0106}", "\\cap ,c", "\x{0107}", ",c", |
207
|
|
|
|
|
|
|
"\x{0043}\x{0301}", "\\cap ,c", "\x{0063}\x{0301}", ",c", |
208
|
|
|
|
|
|
|
|
209
|
|
|
|
|
|
|
"\x{017D}", "\\cap ^z", "\x{017E}", "^z", |
210
|
|
|
|
|
|
|
"\x{005A}\x{030C}", "\\cap ^z", "\x{007A}\x{030C}", "^z", |
211
|
|
|
|
|
|
|
|
212
|
|
|
|
|
|
|
"\x{00D1}", "\\cap ^n", "\x{00F1}", "^n", |
213
|
|
|
|
|
|
|
"\x{004E}\x{0303}", "\\cap ^n", "\x{006E}\x{0303}", "^n", |
214
|
|
|
|
|
|
|
|
215
|
|
|
|
|
|
|
"\x{004C}\x{0303}", "\\cap ^l", "\x{006C}\x{0303}", "^l", |
216
|
|
|
|
|
|
|
|
217
|
|
|
|
|
|
|
"\x{0052}\x{0307}", "\\cap .r", "\x{0072}\x{0307}", ".r", |
218
|
|
|
|
|
|
|
|
219
|
|
|
|
|
|
|
); |
220
|
|
|
|
|
|
|
|
221
|
|
|
|
|
|
|
|
222
|
2
|
|
|
2
|
|
10
|
no strict 'refs'; |
|
2
|
|
|
|
|
1
|
|
|
2
|
|
|
|
|
3094
|
|
223
|
|
|
|
|
|
|
|
224
|
1
|
|
|
|
|
2
|
${ $cls . '::encoder' } = $encoder; |
|
1
|
|
|
|
|
6
|
|
225
|
|
|
|
|
|
|
|
226
|
1
|
50
|
|
|
|
4
|
if ($option{'describe'}) { |
227
|
|
|
|
|
|
|
|
228
|
0
|
|
|
|
|
0
|
$_->describe('') foreach @{${ $cls . '::encoder' }}; |
|
0
|
|
|
|
|
0
|
|
|
0
|
|
|
|
|
0
|
|
229
|
|
|
|
|
|
|
} |
230
|
|
|
|
|
|
|
|
231
|
1
|
|
|
|
|
1
|
return ${ $cls . '::encoder' }; |
|
1
|
|
|
|
|
4
|
|
232
|
|
|
|
|
|
|
} |
233
|
|
|
|
|
|
|
|
234
|
|
|
|
|
|
|
|
235
|
|
|
|
|
|
|
sub decoder ($;$$) { |
236
|
1
|
|
|
1
|
1
|
5
|
my ($cls, undef, undef) = @_; |
237
|
|
|
|
|
|
|
|
238
|
1
|
|
|
|
|
2
|
my $decoder = []; |
239
|
|
|
|
|
|
|
|
240
|
|
|
|
|
|
|
|
241
|
1
|
|
|
|
|
8
|
my @sunny = ( |
242
|
|
|
|
|
|
|
[ "t", "\x{0074}" ], |
243
|
|
|
|
|
|
|
[ "_t", "\x{0074}\x{0331}" ], # "\x{1E6F}" |
244
|
|
|
|
|
|
|
[ "d", "\x{0064}" ], |
245
|
|
|
|
|
|
|
[ "_d", "\x{0064}\x{0331}" ], # "\x{1E0F}" |
246
|
|
|
|
|
|
|
[ "r", "\x{0072}" ], |
247
|
|
|
|
|
|
|
[ "z", "\x{007A}" ], |
248
|
|
|
|
|
|
|
[ "s", "\x{0073}" ], |
249
|
|
|
|
|
|
|
[ "^s", "\x{0073}\x{030C}" ], # "\x{0161}" |
250
|
|
|
|
|
|
|
[ ".s", "\x{0073}\x{0323}" ], # "\x{1E63}" |
251
|
|
|
|
|
|
|
[ ".d", "\x{0064}\x{0323}" ], # "\x{1E0D}" |
252
|
|
|
|
|
|
|
[ ".t", "\x{0074}\x{0323}" ], # "\x{1E6D}" |
253
|
|
|
|
|
|
|
[ ".z", "\x{007A}\x{0323}" ], # "\x{1E93}" |
254
|
|
|
|
|
|
|
[ "l", "\x{006C}" ], |
255
|
|
|
|
|
|
|
[ "n", "\x{006E}" ], |
256
|
|
|
|
|
|
|
); |
257
|
|
|
|
|
|
|
|
258
|
|
|
|
|
|
|
|
259
|
1
|
|
|
|
|
5
|
my @extra = ( |
260
|
|
|
|
|
|
|
[ "T", "\x{0074}" ], |
261
|
|
|
|
|
|
|
[ "H", "\x{0068}" ], # "" |
262
|
|
|
|
|
|
|
[ "N", "\x{006E}" ], |
263
|
|
|
|
|
|
|
[ "W", "\x{0077}" ], # "" |
264
|
|
|
|
|
|
|
); |
265
|
|
|
|
|
|
|
|
266
|
|
|
|
|
|
|
|
267
|
1
|
|
|
|
|
10
|
my @vowel = ( |
268
|
|
|
|
|
|
|
[ "a", "\x{0061}" ], |
269
|
|
|
|
|
|
|
[ "_a", "\x{0061}\x{0304}" ], # "\x{0101}" |
270
|
|
|
|
|
|
|
[ "_aA", "\x{0061}\x{0304}" ], # "\x{0101}" |
271
|
|
|
|
|
|
|
[ "_aY", "\x{0061}\x{0304}" ], # "\x{0101}" |
272
|
|
|
|
|
|
|
[ "_aU", "\x{0061}\x{0304}" ], # "\x{0101}" |
273
|
|
|
|
|
|
|
[ "_aI", "\x{0061}\x{0304}" ], # "\x{0101}" |
274
|
|
|
|
|
|
|
[ "A", "\x{0061}\x{0304}" ], # "\x{0101}" |
275
|
|
|
|
|
|
|
[ "^A", "\x{0061}\x{0304}" ], # "\x{0101}" |
276
|
|
|
|
|
|
|
[ "_A", "\x{0061}\x{0304}" ], # "\x{0101}" |
277
|
|
|
|
|
|
|
[ "e", "\x{0065}" ], |
278
|
|
|
|
|
|
|
[ "E", "\x{0065}\x{0304}" ], # "\x{0113}" |
279
|
|
|
|
|
|
|
[ "i", "\x{0069}" ], |
280
|
|
|
|
|
|
|
[ "_i", "\x{0069}\x{0304}" ], # "\x{012B}" |
281
|
|
|
|
|
|
|
[ "I", "\x{0069}\x{0304}" ], # "\x{012B}" |
282
|
|
|
|
|
|
|
[ "^I", "\x{0069}\x{0304}" ], # "\x{012B}" |
283
|
|
|
|
|
|
|
[ "_I", "\x{0069}" ], |
284
|
|
|
|
|
|
|
[ "o", "\x{006F}" ], |
285
|
|
|
|
|
|
|
[ "O", "\x{006F}\x{0304}" ], # "\x{014D}" |
286
|
|
|
|
|
|
|
[ "u", "\x{0075}" ], |
287
|
|
|
|
|
|
|
[ "_u", "\x{0075}\x{0304}" ], # "\x{016B}" |
288
|
|
|
|
|
|
|
[ "U", "\x{0075}\x{0304}" ], # "\x{016B}" |
289
|
|
|
|
|
|
|
[ "^U", "\x{0075}\x{0304}" ], # "\x{016B}" |
290
|
|
|
|
|
|
|
[ "_U", "\x{0075}" ], |
291
|
|
|
|
|
|
|
[ "Y", "\x{0061}\x{0304}" ], # "\x{0101}" |
292
|
|
|
|
|
|
|
); |
293
|
|
|
|
|
|
|
|
294
|
|
|
|
|
|
|
|
295
|
1
|
|
|
|
|
3
|
my @minor = ( |
296
|
|
|
|
|
|
|
[ "'", "\x{02BE}" ], # "\x{02BC}" |
297
|
|
|
|
|
|
|
[ "`", "\x{02BF}" ], # "\x{02BB}" |
298
|
|
|
|
|
|
|
); |
299
|
|
|
|
|
|
|
|
300
|
|
|
|
|
|
|
|
301
|
1
|
|
|
|
|
2
|
my @empty = ( |
302
|
|
|
|
|
|
|
[ "\"", "", ], # "\x{02BC}" |
303
|
|
|
|
|
|
|
[ "|", "", ], |
304
|
|
|
|
|
|
|
[ "B", "", ], |
305
|
|
|
|
|
|
|
); |
306
|
|
|
|
|
|
|
|
307
|
|
|
|
|
|
|
|
308
|
1
|
|
|
|
|
10
|
my @moony = ( |
309
|
|
|
|
|
|
|
[ "b", "\x{0062}" ], |
310
|
|
|
|
|
|
|
[ "^g", "\x{0067}\x{030C}" ], # "\x{01E7}" |
311
|
|
|
|
|
|
|
[ ".h", "\x{0068}\x{0323}" ], # "\x{1E25}" |
312
|
|
|
|
|
|
|
[ "_h", "\x{0068}\x{032E}" ], # "\x{1E2B}" |
313
|
|
|
|
|
|
|
[ ".g", "\x{0067}\x{0307}" ], # "\x{0121}" |
314
|
|
|
|
|
|
|
[ "f", "\x{0066}" ], |
315
|
|
|
|
|
|
|
[ "q", "\x{0071}" ], |
316
|
|
|
|
|
|
|
[ "k", "\x{006B}" ], |
317
|
|
|
|
|
|
|
[ "m", "\x{006D}" ], |
318
|
|
|
|
|
|
|
[ "h", "\x{0068}" ], |
319
|
|
|
|
|
|
|
[ "w", "\x{0077}" ], |
320
|
|
|
|
|
|
|
[ "y", "\x{0079}" ], |
321
|
|
|
|
|
|
|
|
322
|
|
|
|
|
|
|
[ "p", "\x{0070}" ], |
323
|
|
|
|
|
|
|
[ "v", "\x{0076}" ], |
324
|
|
|
|
|
|
|
[ "g", "\x{0067}" ], |
325
|
|
|
|
|
|
|
|
326
|
|
|
|
|
|
|
[ "c", "\x{0063}" ], |
327
|
|
|
|
|
|
|
[ "^c", "\x{0063}\x{030C}" ], # "\x{010D}" |
328
|
|
|
|
|
|
|
[ ",c", "\x{0063}\x{0301}" ], # "\x{0107}" |
329
|
|
|
|
|
|
|
[ "^z", "\x{007A}\x{030C}" ], # "\x{017E}" |
330
|
|
|
|
|
|
|
[ "^n", "\x{006E}\x{0303}" ], # "\x{00F1}" |
331
|
|
|
|
|
|
|
[ "^l", "\x{006C}\x{0303}" ], |
332
|
|
|
|
|
|
|
[ ".r", "\x{0072}\x{0307}" ], |
333
|
|
|
|
|
|
|
); |
334
|
|
|
|
|
|
|
|
335
|
|
|
|
|
|
|
|
336
|
|
|
|
|
|
|
$decoder->[0] = Encode::Mapper->compile ( |
337
|
|
|
|
|
|
|
|
338
|
|
|
|
|
|
|
[ |
339
|
|
|
|
|
|
|
'silent' => 0, |
340
|
|
|
|
|
|
|
], |
341
|
|
|
|
|
|
|
|
342
|
|
|
|
|
|
|
# definite article assimilation .. non-linguistic |
343
|
|
|
|
|
|
|
( |
344
|
|
|
|
|
|
|
map { |
345
|
|
|
|
|
|
|
|
346
|
36
|
|
|
|
|
54
|
"l-" . $_->[0] x 2, [ "", $_->[0] . "-" . $_->[0] ], |
347
|
|
|
|
|
|
|
|
348
|
|
|
|
|
|
|
} @sunny, @moony |
349
|
|
|
|
|
|
|
), |
350
|
|
|
|
|
|
|
|
351
|
|
|
|
|
|
|
# initial vowel tying |
352
|
|
|
|
|
|
|
( |
353
|
|
|
|
|
|
|
map { |
354
|
|
|
|
|
|
|
|
355
|
24
|
|
|
|
|
16
|
my $x = $_; |
356
|
|
|
|
|
|
|
|
357
|
|
|
|
|
|
|
map { |
358
|
|
|
|
|
|
|
|
359
|
24
|
|
|
|
|
23
|
my $y = $_; |
|
120
|
|
|
|
|
84
|
|
360
|
|
|
|
|
|
|
|
361
|
|
|
|
|
|
|
map { |
362
|
|
|
|
|
|
|
|
363
|
120
|
|
|
|
|
76
|
$x->[0] . $_ . $y, $x->[1] . $_ . "\x{02BC}", # "\x{02C8}" |
|
1080
|
|
|
|
|
4975
|
|
364
|
|
|
|
|
|
|
|
365
|
|
|
|
|
|
|
"\\cap\x09" . $x->[0] . $_ . $y, ucfirst $x->[1] . $_ . "\x{02BC}", # "\x{02C8}" |
366
|
|
|
|
|
|
|
"\\cap\x0A" . $x->[0] . $_ . $y, ucfirst $x->[1] . $_ . "\x{02BC}", # "\x{02C8}" |
367
|
|
|
|
|
|
|
"\\cap\x0D" . $x->[0] . $_ . $y, ucfirst $x->[1] . $_ . "\x{02BC}", # "\x{02C8}" |
368
|
|
|
|
|
|
|
"\\cap\x20" . $x->[0] . $_ . $y, ucfirst $x->[1] . $_ . "\x{02BC}", # "\x{02C8}" |
369
|
|
|
|
|
|
|
|
370
|
|
|
|
|
|
|
} "-", "\x09", "\x0A", "\x0D", "\x20", "\x0D\x0A", |
371
|
|
|
|
|
|
|
"\x20\x20", "\x20\x20\x20", "\x20\x20\x20\x20" |
372
|
|
|
|
|
|
|
|
373
|
|
|
|
|
|
|
} "a", "e", "i", "o", "u" |
374
|
|
|
|
|
|
|
|
375
|
|
|
|
|
|
|
} @vowel |
376
|
|
|
|
|
|
|
), |
377
|
|
|
|
|
|
|
|
378
|
|
|
|
|
|
|
# silence the silent |
379
|
|
|
|
|
|
|
|
380
|
|
|
|
|
|
|
"_W", "", |
381
|
|
|
|
|
|
|
|
382
|
|
|
|
|
|
|
"WA", [ "", "W" ], |
383
|
|
|
|
|
|
|
|
384
|
|
|
|
|
|
|
"UW", [ "", "U" ], |
385
|
|
|
|
|
|
|
"UA", [ "", "U" ], |
386
|
|
|
|
|
|
|
|
387
|
|
|
|
|
|
|
"NA", [ "", "N" ], |
388
|
|
|
|
|
|
|
"NY", [ "", "N" ], |
389
|
|
|
|
|
|
|
"NU", [ "", "N" ], |
390
|
|
|
|
|
|
|
"N_A", [ "", "N" ], |
391
|
|
|
|
|
|
|
|
392
|
|
|
|
|
|
|
# regular capitalization |
393
|
|
|
|
|
|
|
( |
394
|
|
|
|
|
|
|
map { |
395
|
|
|
|
|
|
|
|
396
|
67
|
|
|
|
|
171
|
$_->[0], $_->[1], |
397
|
|
|
|
|
|
|
|
398
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0], ucfirst $_->[1], |
399
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0], ucfirst $_->[1], |
400
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0], ucfirst $_->[1], |
401
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0], ucfirst $_->[1], |
402
|
|
|
|
|
|
|
|
403
|
|
|
|
|
|
|
} @sunny, @moony, @empty, @vowel, @extra |
404
|
|
|
|
|
|
|
), |
405
|
|
|
|
|
|
|
|
406
|
|
|
|
|
|
|
( |
407
|
|
|
|
|
|
|
map { |
408
|
|
|
|
|
|
|
|
409
|
39
|
|
|
|
|
412
|
$_->[0] . "i", $_->[1] . "i", |
410
|
|
|
|
|
|
|
$_->[0] . "u", $_->[1] . "u", |
411
|
|
|
|
|
|
|
|
412
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0] . "i", ucfirst $_->[1] . "i", |
413
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0] . "i", ucfirst $_->[1] . "i", |
414
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0] . "i", ucfirst $_->[1] . "i", |
415
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0] . "i", ucfirst $_->[1] . "i", |
416
|
|
|
|
|
|
|
|
417
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0] . "u", ucfirst $_->[1] . "u", |
418
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0] . "u", ucfirst $_->[1] . "u", |
419
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0] . "u", ucfirst $_->[1] . "u", |
420
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0] . "u", ucfirst $_->[1] . "u", |
421
|
|
|
|
|
|
|
|
422
|
|
|
|
|
|
|
} @sunny, @moony, @empty |
423
|
|
|
|
|
|
|
), |
424
|
|
|
|
|
|
|
|
425
|
|
|
|
|
|
|
( |
426
|
|
|
|
|
|
|
map { |
427
|
|
|
|
|
|
|
|
428
|
39
|
|
|
|
|
30
|
my $x = $_; |
429
|
|
|
|
|
|
|
|
430
|
|
|
|
|
|
|
map { |
431
|
|
|
|
|
|
|
|
432
|
39
|
|
|
|
|
28
|
$x->[0] . "i" . $_, [ $x->[1], "i" . $_ ], |
|
195
|
|
|
|
|
1903
|
|
433
|
|
|
|
|
|
|
$x->[0] . "u" . $_, [ $x->[1], "u" . $_ ], |
434
|
|
|
|
|
|
|
|
435
|
|
|
|
|
|
|
"\\cap\x09" . $x->[0] . "i" . $_, [ ucfirst $x->[1], "i" . $_ ], |
436
|
|
|
|
|
|
|
"\\cap\x0A" . $x->[0] . "i" . $_, [ ucfirst $x->[1], "i" . $_ ], |
437
|
|
|
|
|
|
|
"\\cap\x0D" . $x->[0] . "i" . $_, [ ucfirst $x->[1], "i" . $_ ], |
438
|
|
|
|
|
|
|
"\\cap\x20" . $x->[0] . "i" . $_, [ ucfirst $x->[1], "i" . $_ ], |
439
|
|
|
|
|
|
|
|
440
|
|
|
|
|
|
|
"\\cap\x09" . $x->[0] . "u" . $_, [ ucfirst $x->[1], "u" . $_ ], |
441
|
|
|
|
|
|
|
"\\cap\x0A" . $x->[0] . "u" . $_, [ ucfirst $x->[1], "u" . $_ ], |
442
|
|
|
|
|
|
|
"\\cap\x0D" . $x->[0] . "u" . $_, [ ucfirst $x->[1], "u" . $_ ], |
443
|
|
|
|
|
|
|
"\\cap\x20" . $x->[0] . "u" . $_, [ ucfirst $x->[1], "u" . $_ ], |
444
|
|
|
|
|
|
|
|
445
|
|
|
|
|
|
|
} "-", "\x09", "\x0A", "\x0D", "\x20" |
446
|
|
|
|
|
|
|
|
447
|
|
|
|
|
|
|
} @sunny, @moony, @empty |
448
|
|
|
|
|
|
|
), |
449
|
|
|
|
|
|
|
|
450
|
|
|
|
|
|
|
# initial vowel assimilation |
451
|
|
|
|
|
|
|
( |
452
|
|
|
|
|
|
|
map { |
453
|
|
|
|
|
|
|
|
454
|
2
|
|
|
|
|
3
|
my $fix = $_; |
455
|
|
|
|
|
|
|
|
456
|
|
|
|
|
|
|
"i" . $_, [ "", "I" ], |
457
|
|
|
|
|
|
|
"u" . $_, [ "", "U" ], |
458
|
|
|
|
|
|
|
|
459
|
|
|
|
|
|
|
"\\cap\x09" . "i" . $_, [ "", "\\cap\x09" . "I" ], |
460
|
|
|
|
|
|
|
"\\cap\x0A" . "i" . $_, [ "", "\\cap\x0A" . "I" ], |
461
|
|
|
|
|
|
|
"\\cap\x0D" . "i" . $_, [ "", "\\cap\x0D" . "I" ], |
462
|
|
|
|
|
|
|
"\\cap\x20" . "i" . $_, [ "", "\\cap\x20" . "I" ], |
463
|
|
|
|
|
|
|
|
464
|
|
|
|
|
|
|
"\\cap\x09" . "u" . $_, [ "", "\\cap\x09" . "U" ], |
465
|
|
|
|
|
|
|
"\\cap\x0A" . "u" . $_, [ "", "\\cap\x0A" . "U" ], |
466
|
|
|
|
|
|
|
"\\cap\x0D" . "u" . $_, [ "", "\\cap\x0D" . "U" ], |
467
|
|
|
|
|
|
|
"\\cap\x20" . "u" . $_, [ "", "\\cap\x20" . "U" ], |
468
|
|
|
|
|
|
|
|
469
|
|
|
|
|
|
|
map { |
470
|
|
|
|
|
|
|
|
471
|
2
|
|
|
|
|
13
|
"i" . $fix . $_->[0], [ "i", $fix . $_->[0] ], |
|
50
|
|
|
|
|
425
|
|
472
|
|
|
|
|
|
|
"u" . $fix . $_->[0], [ "u", $fix . $_->[0] ], |
473
|
|
|
|
|
|
|
|
474
|
|
|
|
|
|
|
"\\cap\x09" . "i" . $fix . $_->[0], [ "I", $fix . $_->[0] ], |
475
|
|
|
|
|
|
|
"\\cap\x0A" . "i" . $fix . $_->[0], [ "I", $fix . $_->[0] ], |
476
|
|
|
|
|
|
|
"\\cap\x0D" . "i" . $fix . $_->[0], [ "I", $fix . $_->[0] ], |
477
|
|
|
|
|
|
|
"\\cap\x20" . "i" . $fix . $_->[0], [ "I", $fix . $_->[0] ], |
478
|
|
|
|
|
|
|
|
479
|
|
|
|
|
|
|
"\\cap\x09" . "u" . $fix . $_->[0], [ "U", $fix . $_->[0] ], |
480
|
|
|
|
|
|
|
"\\cap\x0A" . "u" . $fix . $_->[0], [ "U", $fix . $_->[0] ], |
481
|
|
|
|
|
|
|
"\\cap\x0D" . "u" . $fix . $_->[0], [ "U", $fix . $_->[0] ], |
482
|
|
|
|
|
|
|
"\\cap\x20" . "u" . $fix . $_->[0], [ "U", $fix . $_->[0] ], |
483
|
|
|
|
|
|
|
|
484
|
|
|
|
|
|
|
} @vowel, $empty[0] |
485
|
|
|
|
|
|
|
|
486
|
|
|
|
|
|
|
} "y", "w" # "'" |
487
|
|
|
|
|
|
|
), |
488
|
|
|
|
|
|
|
|
489
|
|
|
|
|
|
|
# capitalization of minors |
490
|
|
|
|
|
|
|
( |
491
|
|
|
|
|
|
|
map { |
492
|
|
|
|
|
|
|
|
493
|
2
|
|
|
|
|
37
|
$_->[0], $_->[1], |
494
|
|
|
|
|
|
|
|
495
|
|
|
|
|
|
|
$_->[0] . "i", $_->[1] . "i", |
496
|
|
|
|
|
|
|
$_->[0] . "u", $_->[1] . "u", |
497
|
|
|
|
|
|
|
|
498
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0], [ $_->[1], "\\cap " ], |
499
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0], [ $_->[1], "\\cap " ], |
500
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0], [ $_->[1], "\\cap " ], |
501
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0], [ $_->[1], "\\cap " ], |
502
|
|
|
|
|
|
|
|
503
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0] . "i", $_->[1] . ucfirst "i", |
504
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0] . "i", $_->[1] . ucfirst "i", |
505
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0] . "i", $_->[1] . ucfirst "i", |
506
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0] . "i", $_->[1] . ucfirst "i", |
507
|
|
|
|
|
|
|
|
508
|
|
|
|
|
|
|
"\\cap\x09" . $_->[0] . "u", $_->[1] . ucfirst "u", |
509
|
|
|
|
|
|
|
"\\cap\x0A" . $_->[0] . "u", $_->[1] . ucfirst "u", |
510
|
|
|
|
|
|
|
"\\cap\x0D" . $_->[0] . "u", $_->[1] . ucfirst "u", |
511
|
|
|
|
|
|
|
"\\cap\x20" . $_->[0] . "u", $_->[1] . ucfirst "u", |
512
|
|
|
|
|
|
|
|
513
|
|
|
|
|
|
|
} @minor |
514
|
|
|
|
|
|
|
), |
515
|
|
|
|
|
|
|
|
516
|
|
|
|
|
|
|
( |
517
|
|
|
|
|
|
|
map { |
518
|
|
|
|
|
|
|
|
519
|
2
|
|
|
|
|
1
|
my $x = $_; |
520
|
|
|
|
|
|
|
|
521
|
|
|
|
|
|
|
map { |
522
|
|
|
|
|
|
|
|
523
|
2
|
|
|
|
|
2
|
$x->[0] . "i" . $_, [ $x->[1], "i" . $_ ], |
|
10
|
|
|
|
|
98
|
|
524
|
|
|
|
|
|
|
$x->[0] . "u" . $_, [ $x->[1], "u" . $_ ], |
525
|
|
|
|
|
|
|
|
526
|
|
|
|
|
|
|
"\\cap\x09" . $x->[0] . "i" . $_, [ $x->[1], "\\cap i" . $_ ], |
527
|
|
|
|
|
|
|
"\\cap\x0A" . $x->[0] . "i" . $_, [ $x->[1], "\\cap i" . $_ ], |
528
|
|
|
|
|
|
|
"\\cap\x0D" . $x->[0] . "i" . $_, [ $x->[1], "\\cap i" . $_ ], |
529
|
|
|
|
|
|
|
"\\cap\x20" . $x->[0] . "i" . $_, [ $x->[1], "\\cap i" . $_ ], |
530
|
|
|
|
|
|
|
|
531
|
|
|
|
|
|
|
"\\cap\x09" . $x->[0] . "u" . $_, [ $x->[1], "\\cap u" . $_ ], |
532
|
|
|
|
|
|
|
"\\cap\x0A" . $x->[0] . "u" . $_, [ $x->[1], "\\cap u" . $_ ], |
533
|
|
|
|
|
|
|
"\\cap\x0D" . $x->[0] . "u" . $_, [ $x->[1], "\\cap u" . $_ ], |
534
|
|
|
|
|
|
|
"\\cap\x20" . $x->[0] . "u" . $_, [ $x->[1], "\\cap u" . $_ ], |
535
|
|
|
|
|
|
|
|
536
|
|
|
|
|
|
|
} "-", "\x09", "\x0A", "\x0D", "\x20" |
537
|
|
|
|
|
|
|
|
538
|
|
|
|
|
|
|
} @minor |
539
|
|
|
|
|
|
|
), |
540
|
|
|
|
|
|
|
|
541
|
|
|
|
|
|
|
# white-space collapsing |
542
|
|
|
|
|
|
|
( |
543
|
|
|
|
|
|
|
map { |
544
|
|
|
|
|
|
|
|
545
|
1
|
|
|
|
|
3
|
"\\cap\x09" . $_, [ "", "\\cap " ], |
|
4
|
|
|
|
|
138
|
|
546
|
|
|
|
|
|
|
"\\cap\x0A" . $_, [ "", "\\cap " ], |
547
|
|
|
|
|
|
|
"\\cap\x0D" . $_, [ "", "\\cap " ], |
548
|
|
|
|
|
|
|
"\\cap\x20" . $_, [ "", "\\cap " ], |
549
|
|
|
|
|
|
|
|
550
|
|
|
|
|
|
|
} "\x09", "\x0A", "\x0D", "\x20" |
551
|
|
|
|
|
|
|
), |
552
|
|
|
|
|
|
|
|
553
|
|
|
|
|
|
|
); |
554
|
|
|
|
|
|
|
|
555
|
|
|
|
|
|
|
|
556
|
2
|
|
|
2
|
|
9
|
no strict 'refs'; |
|
2
|
|
|
|
|
2
|
|
|
2
|
|
|
|
|
380
|
|
557
|
|
|
|
|
|
|
|
558
|
1
|
|
|
|
|
1111
|
${ $cls . '::decoder' } = $decoder; |
|
1
|
|
|
|
|
9
|
|
559
|
|
|
|
|
|
|
|
560
|
1
|
50
|
|
|
|
5
|
if ($option{'describe'}) { |
561
|
|
|
|
|
|
|
|
562
|
0
|
|
|
|
|
0
|
$_->describe('') foreach @{${ $cls . '::decoder' }}; |
|
0
|
|
|
|
|
0
|
|
|
0
|
|
|
|
|
0
|
|
563
|
|
|
|
|
|
|
} |
564
|
|
|
|
|
|
|
|
565
|
1
|
|
|
|
|
1
|
return ${ $cls . '::decoder' }; |
|
1
|
|
|
|
|
19
|
|
566
|
|
|
|
|
|
|
} |
567
|
|
|
|
|
|
|
|
568
|
|
|
|
|
|
|
|
569
|
|
|
|
|
|
|
1; |
570
|
|
|
|
|
|
|
|
571
|
|
|
|
|
|
|
__END__ |