glaemscribe 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/LICENSE.txt +19 -0
- data/bin/glaemscribe +307 -0
- data/glaemresources/charsets/cirth_ds.cst +205 -0
- data/glaemresources/charsets/sarati_eldamar.cst +256 -0
- data/glaemresources/charsets/tengwar_ds.cst +318 -0
- data/glaemresources/charsets/unicode_gothic.cst +64 -0
- data/glaemresources/charsets/unicode_runes.cst +120 -0
- data/glaemresources/modes/adunaic.glaem +251 -0
- data/glaemresources/modes/blackspeech-annatar.glaem +318 -0
- data/glaemresources/modes/blackspeech.glaem +260 -0
- data/glaemresources/modes/gothic.glaem +78 -0
- data/glaemresources/modes/khuzdul.glaem +141 -0
- data/glaemresources/modes/mercian.glaem +419 -0
- data/glaemresources/modes/oldnorse-medieval.glaem +127 -0
- data/glaemresources/modes/quenya-sarati.glaem +320 -0
- data/glaemresources/modes/quenya.glaem +307 -0
- data/glaemresources/modes/sindarin-beleriand.glaem +285 -0
- data/glaemresources/modes/sindarin-classical.glaem +276 -0
- data/glaemresources/modes/sindarin-daeron.glaem +182 -0
- data/glaemresources/modes/telerin.glaem +302 -0
- data/glaemresources/modes/valarin-sarati.glaem +210 -0
- data/glaemresources/modes/westron.glaem +340 -0
- data/glaemresources/modes/westsaxon.glaem +342 -0
- data/lib/api/charset.rb +84 -0
- data/lib/api/charset_parser.rb +55 -0
- data/lib/api/constants.rb +29 -0
- data/lib/api/debug.rb +36 -0
- data/lib/api/eval.rb +268 -0
- data/lib/api/fragment.rb +113 -0
- data/lib/api/glaeml.rb +200 -0
- data/lib/api/if_tree.rb +96 -0
- data/lib/api/mode.rb +112 -0
- data/lib/api/mode_parser.rb +314 -0
- data/lib/api/option.rb +64 -0
- data/lib/api/post_processor/reverse.rb +36 -0
- data/lib/api/pre_processor/downcase.rb +35 -0
- data/lib/api/pre_processor/elvish_numbers.rb +47 -0
- data/lib/api/pre_processor/rxsubstitute.rb +40 -0
- data/lib/api/pre_processor/substitute.rb +38 -0
- data/lib/api/pre_processor/up_down_tehta_split.rb +138 -0
- data/lib/api/resource_manager.rb +130 -0
- data/lib/api/rule.rb +99 -0
- data/lib/api/rule_group.rb +159 -0
- data/lib/api/sheaf.rb +70 -0
- data/lib/api/sheaf_chain.rb +86 -0
- data/lib/api/sheaf_chain_iterator.rb +108 -0
- data/lib/api/sub_rule.rb +40 -0
- data/lib/api/transcription_pre_post_processor.rb +118 -0
- data/lib/api/transcription_processor.rb +137 -0
- data/lib/api/transcription_tree_node.rb +91 -0
- data/lib/glaemscribe.rb +70 -0
- metadata +112 -0
@@ -0,0 +1,260 @@
|
|
1
|
+
\**
|
2
|
+
|
3
|
+
Glǽmscribe (also written Glaemscribe) is a software dedicated to
|
4
|
+
the transcription of texts between writing systems, and more
|
5
|
+
specifically dedicated to the transcription of J.R.R. Tolkien's
|
6
|
+
invented languages to some of his devised writing systems.
|
7
|
+
|
8
|
+
Copyright (C) 2015 Benjamin Babut (Talagan).
|
9
|
+
|
10
|
+
This program is free software: you can redistribute it and/or modify
|
11
|
+
it under the terms of the GNU Affero General Public License as published by
|
12
|
+
the Free Software Foundation, either version 3 of the License, or
|
13
|
+
any later version.
|
14
|
+
|
15
|
+
This program is distributed in the hope that it will be useful,
|
16
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
17
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
18
|
+
GNU Affero General Public License for more details.
|
19
|
+
|
20
|
+
You should have received a copy of the GNU Affero General Public License
|
21
|
+
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
22
|
+
|
23
|
+
**\
|
24
|
+
|
25
|
+
\** BlackSpeech ring mode for glaemscribe (MAY BE INCOMPLETE) **\
|
26
|
+
|
27
|
+
\language "Black Speech"
|
28
|
+
\writing "Tengwar"
|
29
|
+
\mode "General Use"
|
30
|
+
\version "0.0.1"
|
31
|
+
\authors "Talagan (Benjamin Babut)"
|
32
|
+
|
33
|
+
\charset tengwar_ds true
|
34
|
+
|
35
|
+
\beg options
|
36
|
+
\option reverse_numbers true
|
37
|
+
\beg option numbers_base BASE_12
|
38
|
+
\value BASE_10 10
|
39
|
+
\value BASE_12 12
|
40
|
+
\end
|
41
|
+
\end
|
42
|
+
|
43
|
+
\beg preprocessor
|
44
|
+
\** Work exclusively downcase **\
|
45
|
+
\downcase
|
46
|
+
|
47
|
+
\** Simplify trema vowels **\
|
48
|
+
\substitute "ä" "a"
|
49
|
+
\substitute "ë" "e"
|
50
|
+
\substitute "ï" "i"
|
51
|
+
\substitute "ö" "o"
|
52
|
+
\substitute "ü" "u"
|
53
|
+
\substitute "ÿ" "y"
|
54
|
+
|
55
|
+
\** Dis-ambiguate long vowels **\
|
56
|
+
\rxsubstitute "(ā|â|aa)" "á"
|
57
|
+
\rxsubstitute "(ē|ê|ee)" "é"
|
58
|
+
\rxsubstitute "(ī|î|ii)" "í"
|
59
|
+
\rxsubstitute "(ō|ô|oo)" "ó"
|
60
|
+
\rxsubstitute "(ū|û|uu)" "ú"
|
61
|
+
|
62
|
+
\** Preprocess numbers **\
|
63
|
+
\elvish_numbers "\\eval numbers_base" "\\eval reverse_numbers"
|
64
|
+
\end
|
65
|
+
|
66
|
+
\beg processor
|
67
|
+
|
68
|
+
\beg rules litteral
|
69
|
+
{A} === a
|
70
|
+
{AA} === á
|
71
|
+
{E} === e
|
72
|
+
{EE} === é
|
73
|
+
{I} === i
|
74
|
+
{II} === í
|
75
|
+
{O} === o
|
76
|
+
{OO} === ó
|
77
|
+
{U} === u
|
78
|
+
{UU} === ú
|
79
|
+
|
80
|
+
{AI} === {A}{I} \** attested **\
|
81
|
+
{AU} === {A}{U} \** attested **\
|
82
|
+
{OI} === {O}{I} \** Not quite sure (dushgoi) **\
|
83
|
+
|
84
|
+
{K} === (c,k)
|
85
|
+
|
86
|
+
{VOWELS} === {A} * {E} * {I} * {O} * {U}
|
87
|
+
{LVOWELS} === {AA} * {EE} * {II} * {OO} * {UU}
|
88
|
+
|
89
|
+
\** Revers o and u **\
|
90
|
+
{TEHTA_XS} === A_TEHTA_XS * E_TEHTA_XS * I_TEHTA_XS * U_TEHTA_XS * O_TEHTA_XS
|
91
|
+
{TEHTA__S} === A_TEHTA_S * E_TEHTA_S * I_TEHTA_S * U_TEHTA_S * O_TEHTA_S
|
92
|
+
{TEHTA__L} === A_TEHTA_L * E_TEHTA_L * I_TEHTA_L * U_TEHTA_L * O_TEHTA_L
|
93
|
+
{TEHTA_XL} === A_TEHTA_XL * E_TEHTA_XL * I_TEHTA_XL * U_TEHTA_XL * O_TEHTA_XL
|
94
|
+
|
95
|
+
{DIPHTHONGS} === {AI} * {AU} * {OI}
|
96
|
+
{DIPHTHENGS} === YANTA A_TEHTA_L * URE A_TEHTA_L * YANTA U_TEHTA_L
|
97
|
+
|
98
|
+
{V_D_KER} === [ {VOWELS} * {DIPHTHONGS} ]
|
99
|
+
{V_D_IMG_XS} === [ {TEHTA_XS} * {DIPHTHENGS} ]
|
100
|
+
{V_D_IMG__S} === [ {TEHTA__L} * {DIPHTHENGS} ]
|
101
|
+
{V_D_IMG__L} === [ {TEHTA__S} * {DIPHTHENGS} ]
|
102
|
+
{V_D_IMG_XL} === [ {TEHTA_XL} * {DIPHTHENGS} ]
|
103
|
+
|
104
|
+
[{VOWELS}] --> TELCO [{TEHTA_XS}] \** Replace isolated short vowels **\
|
105
|
+
[{LVOWELS}] --> ARA [{TEHTA_XS}] \** Replace long vowels **\
|
106
|
+
[{DIPHTHONGS}] --> [{DIPHTHENGS}] \** Replace diphthongs **\
|
107
|
+
|
108
|
+
b --> UMBAR
|
109
|
+
[{VOWELS}] b --> UMBAR [{TEHTA_XL}]
|
110
|
+
|
111
|
+
d --> ANDO
|
112
|
+
[{VOWELS}] d --> ANDO [{TEHTA_XL}]
|
113
|
+
|
114
|
+
f --> FORMEN
|
115
|
+
[{VOWELS}] f --> FORMEN_EXT [{TEHTA__S}] \** Beware. **\
|
116
|
+
|
117
|
+
g --> UNGWE
|
118
|
+
[{VOWELS}] g --> UNGWE [{TEHTA_XL}]
|
119
|
+
|
120
|
+
gh --> UNGWE_EXT
|
121
|
+
[{VOWELS}] gh --> UNGWE_EXT [{TEHTA_XL}]
|
122
|
+
|
123
|
+
h --> HYARMEN
|
124
|
+
[{VOWELS}] h --> HYARMEN [{TEHTA_XS}]
|
125
|
+
|
126
|
+
\** ======================== **\
|
127
|
+
|
128
|
+
{K} --> QUESSE
|
129
|
+
[{VOWELS}]{K} --> QUESSE [{TEHTA__L}]
|
130
|
+
|
131
|
+
{K}h --> HWESTA
|
132
|
+
[{VOWELS}]{K}h --> HWESTA_EXT [{TEHTA__L}] \** Take care. **\
|
133
|
+
|
134
|
+
\** ======================== **\
|
135
|
+
|
136
|
+
l --> LAMBE
|
137
|
+
[{VOWELS}] l --> LAMBE [{TEHTA__L}]
|
138
|
+
|
139
|
+
\** ======================== **\
|
140
|
+
|
141
|
+
m --> MALTA
|
142
|
+
[{VOWELS}] m --> MALTA [{TEHTA_XL}]
|
143
|
+
|
144
|
+
mb --> UMBAR TILD_SUP_L
|
145
|
+
[{VOWELS}] mb --> UMBAR TILD_SUP_L [{TEHTA_XL}]
|
146
|
+
|
147
|
+
mp --> PARMA TILD_SUP_S
|
148
|
+
[{VOWELS}] mp --> PARMA TILD_SUP_S [{TEHTA__L}]
|
149
|
+
|
150
|
+
\** ======================== **\
|
151
|
+
|
152
|
+
n --> NUMEN
|
153
|
+
[{VOWELS}]n --> NUMEN [{TEHTA_XL}]
|
154
|
+
|
155
|
+
n{K} --> QUESSE TILD_SUP_S
|
156
|
+
[{VOWELS}]n{K} --> QUESSE TILD_SUP_S [{TEHTA__S}]
|
157
|
+
|
158
|
+
\** ======================== **\
|
159
|
+
|
160
|
+
p --> PARMA
|
161
|
+
|
162
|
+
r --> ROMEN
|
163
|
+
r_ --> ORE
|
164
|
+
[{VOWELS}]r --> ORE [{TEHTA__S}]
|
165
|
+
|
166
|
+
[{VOWELS}]rb --> ORE [{TEHTA__L}] UMBAR
|
167
|
+
[{LVOWELS}]rb --> ARA [{TEHTA_XS}] ORE UMBAR
|
168
|
+
|
169
|
+
[{VOWELS}]rz --> ORE [{TEHTA__L}] ESSE
|
170
|
+
[{LVOWELS}]rz --> ARA [{TEHTA_XS}] ORE ESSE
|
171
|
+
|
172
|
+
\** ======================== **\
|
173
|
+
|
174
|
+
s --> SILME
|
175
|
+
|
176
|
+
\** ======================== **\
|
177
|
+
|
178
|
+
sh --> AHA
|
179
|
+
[{VOWELS}] sh --> AHA_EXT [{TEHTA__L}] \** BEWARE. **\
|
180
|
+
|
181
|
+
t --> TINCO
|
182
|
+
[{VOWELS}]t --> TINCO [{TEHTA__L}]
|
183
|
+
|
184
|
+
th --> SULE
|
185
|
+
|
186
|
+
y --> ANNA
|
187
|
+
|
188
|
+
z --> ESSE
|
189
|
+
[{VOWELS}] z --> ESSE_NUQUERNA [{TEHTA__L}]
|
190
|
+
|
191
|
+
\end
|
192
|
+
|
193
|
+
\beg rules punctuation
|
194
|
+
. --> PUNCT_DDOT
|
195
|
+
.. --> PUNCT_DOT PUNCT_DDOT PUNCT_DOT
|
196
|
+
… --> PUNCT_TILD
|
197
|
+
... --> PUNCT_TILD
|
198
|
+
.... --> PUNCT_TILD
|
199
|
+
..... --> PUNCT_TILD
|
200
|
+
...... --> PUNCT_TILD
|
201
|
+
....... --> PUNCT_TILD
|
202
|
+
|
203
|
+
, --> PUNCT_DOT
|
204
|
+
: --> PUNCT_DOT
|
205
|
+
; --> PUNCT_DOT
|
206
|
+
! --> PUNCT_EXCLAM
|
207
|
+
? --> PUNCT_INTERR
|
208
|
+
· --> PUNCT_DOT
|
209
|
+
|
210
|
+
\** Apostrophe **\
|
211
|
+
|
212
|
+
' --> {NULL}
|
213
|
+
’ --> {NULL}
|
214
|
+
|
215
|
+
\** Quotes **\
|
216
|
+
|
217
|
+
“ --> DQUOT_OPEN
|
218
|
+
” --> DQUOT_CLOSE
|
219
|
+
« --> DQUOT_OPEN
|
220
|
+
» --> DQUOT_CLOSE
|
221
|
+
|
222
|
+
- --> {NULL}
|
223
|
+
– --> PUNCT_TILD
|
224
|
+
— --> PUNCT_TILD
|
225
|
+
|
226
|
+
[ --> PUNCT_PAREN_L
|
227
|
+
] --> PUNCT_PAREN_R
|
228
|
+
( --> PUNCT_PAREN_L
|
229
|
+
) --> PUNCT_PAREN_R
|
230
|
+
{ --> PUNCT_PAREN_L
|
231
|
+
} --> PUNCT_PAREN_R
|
232
|
+
< --> PUNCT_PAREN_L
|
233
|
+
> --> PUNCT_PAREN_R
|
234
|
+
|
235
|
+
\** Not universal between fonts ... **\
|
236
|
+
$ --> BOOKMARK_SIGN
|
237
|
+
≤ --> RING_MARK_L \** Ring inscription left beautiful stuff **\
|
238
|
+
≥ --> RING_MARK_R \** Ring inscription right beautiful stuff **\
|
239
|
+
|
240
|
+
\end
|
241
|
+
|
242
|
+
\beg rules numbers
|
243
|
+
0 --> NUM_0
|
244
|
+
1 --> NUM_1
|
245
|
+
2 --> NUM_2
|
246
|
+
3 --> NUM_3
|
247
|
+
4 --> NUM_4
|
248
|
+
5 --> NUM_5
|
249
|
+
6 --> NUM_6
|
250
|
+
7 --> NUM_7
|
251
|
+
8 --> NUM_8
|
252
|
+
9 --> NUM_9
|
253
|
+
A --> NUM_10
|
254
|
+
B --> NUM_11
|
255
|
+
\end
|
256
|
+
|
257
|
+
\end
|
258
|
+
|
259
|
+
|
260
|
+
|
@@ -0,0 +1,78 @@
|
|
1
|
+
\**
|
2
|
+
|
3
|
+
Glǽmscribe (also written Glaemscribe) is a software dedicated to
|
4
|
+
the transcription of texts between writing systems, and more
|
5
|
+
specifically dedicated to the transcription of J.R.R. Tolkien's
|
6
|
+
invented languages to some of his devised writing systems.
|
7
|
+
|
8
|
+
Copyright (C) 2015 Benjamin Babut (Talagan).
|
9
|
+
|
10
|
+
This program is free software: you can redistribute it and/or modify
|
11
|
+
it under the terms of the GNU Affero General Public License as published by
|
12
|
+
the Free Software Foundation, either version 3 of the License, or
|
13
|
+
any later version.
|
14
|
+
|
15
|
+
This program is distributed in the hope that it will be useful,
|
16
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
17
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
18
|
+
GNU Affero General Public License for more details.
|
19
|
+
|
20
|
+
You should have received a copy of the GNU Affero General Public License
|
21
|
+
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
22
|
+
|
23
|
+
**\
|
24
|
+
|
25
|
+
\language "Gothic"
|
26
|
+
\writing "Gothic Alphabet"
|
27
|
+
\mode "Standard"
|
28
|
+
\version "0.0.1"
|
29
|
+
\authors "Talagan (Benjamin Babut)"
|
30
|
+
|
31
|
+
\charset unicode_gothic true
|
32
|
+
|
33
|
+
\beg preprocessor
|
34
|
+
\downcase
|
35
|
+
\end
|
36
|
+
|
37
|
+
\beg processor
|
38
|
+
|
39
|
+
\beg rules litteral
|
40
|
+
(a,ā) --> AZA
|
41
|
+
b --> BERCNA
|
42
|
+
d --> DAAZ
|
43
|
+
(e,ē) --> EYZ
|
44
|
+
f --> FE
|
45
|
+
g --> GEUUA
|
46
|
+
h --> HAAL
|
47
|
+
i --> IIZ
|
48
|
+
j --> GAAR
|
49
|
+
k --> CHOZMA
|
50
|
+
l --> LAAZ
|
51
|
+
m --> MANNA
|
52
|
+
n --> NOICZ
|
53
|
+
(o,ō) --> UTAL
|
54
|
+
p --> PERTRA
|
55
|
+
q --> QUETRA
|
56
|
+
r --> REDA
|
57
|
+
s --> SUGIL
|
58
|
+
t --> TYZ
|
59
|
+
þ --> THYTH
|
60
|
+
u --> URAZ
|
61
|
+
x --> ENGUZ
|
62
|
+
(w,y) --> UUINNE
|
63
|
+
z --> EZEC
|
64
|
+
ƕ --> UUAER
|
65
|
+
ï --> IIZ_TREMA
|
66
|
+
_i --> IIZ_TREMA
|
67
|
+
\end
|
68
|
+
|
69
|
+
\beg rules punctuation
|
70
|
+
, --> COMA
|
71
|
+
. --> PERIOD
|
72
|
+
; --> SEMICOLON
|
73
|
+
: --> COLON
|
74
|
+
\end
|
75
|
+
|
76
|
+
\end
|
77
|
+
|
78
|
+
|
@@ -0,0 +1,141 @@
|
|
1
|
+
\**
|
2
|
+
|
3
|
+
Glǽmscribe (also written Glaemscribe) is a software dedicated to
|
4
|
+
the transcription of texts between writing systems, and more
|
5
|
+
specifically dedicated to the transcription of J.R.R. Tolkien's
|
6
|
+
invented languages to some of his devised writing systems.
|
7
|
+
|
8
|
+
Copyright (C) 2015 Benjamin Babut (Talagan).
|
9
|
+
|
10
|
+
This program is free software: you can redistribute it and/or modify
|
11
|
+
it under the terms of the GNU Affero General Public License as published by
|
12
|
+
the Free Software Foundation, either version 3 of the License, or
|
13
|
+
any later version.
|
14
|
+
|
15
|
+
This program is distributed in the hope that it will be useful,
|
16
|
+
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
17
|
+
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
18
|
+
GNU Affero General Public License for more details.
|
19
|
+
|
20
|
+
You should have received a copy of the GNU Affero General Public License
|
21
|
+
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
22
|
+
|
23
|
+
**\
|
24
|
+
|
25
|
+
\** Khuzdul mode for glaemscribe **\
|
26
|
+
|
27
|
+
\language "Khuzdul"
|
28
|
+
\writing "Cirth"
|
29
|
+
\mode "Angerthas Moria"
|
30
|
+
\version "0.0.1"
|
31
|
+
\authors "Talagan (Benjamin Babut)"
|
32
|
+
|
33
|
+
\charset cirth_ds true
|
34
|
+
|
35
|
+
\beg preprocessor
|
36
|
+
\** Work exclusively downcase **\
|
37
|
+
\downcase
|
38
|
+
|
39
|
+
\** Simplify trema vowels **\
|
40
|
+
\substitute "ä" "a"
|
41
|
+
\substitute "ë" "e"
|
42
|
+
\substitute "ï" "i"
|
43
|
+
\substitute "ö" "o"
|
44
|
+
\substitute "ü" "u"
|
45
|
+
\substitute "ÿ" "y"
|
46
|
+
|
47
|
+
\** Dis-ambiguate long vowels **\
|
48
|
+
\rxsubstitute "(ā|â|aa)" "â"
|
49
|
+
\rxsubstitute "(ē|ê|ee)" "ê"
|
50
|
+
\rxsubstitute "(ī|î|ii)" "î"
|
51
|
+
\rxsubstitute "(ō|ô|oo)" "ô"
|
52
|
+
\rxsubstitute "(ū|û|uu)" "û"
|
53
|
+
\rxsubstitute "(ȳ|ŷ|yy)" "ŷ"
|
54
|
+
\end
|
55
|
+
|
56
|
+
\beg processor
|
57
|
+
|
58
|
+
\** We redefine the output space to have something beautiful, especially with erebor1 and erebor2 **\
|
59
|
+
\outspace CIRTH_SPACE_BIG
|
60
|
+
|
61
|
+
\beg rules litteral
|
62
|
+
a --> CIRTH_48
|
63
|
+
â --> CIRTH_49
|
64
|
+
e --> CIRTH_46
|
65
|
+
ê --> CIRTH_47
|
66
|
+
|
67
|
+
i --> CIRTH_39
|
68
|
+
î --> CIRTH_39 CIRTH_39
|
69
|
+
|
70
|
+
o --> CIRTH_50
|
71
|
+
|
72
|
+
u --> CIRTH_42
|
73
|
+
û --> CIRTH_43
|
74
|
+
|
75
|
+
b --> CIRTH_2
|
76
|
+
d --> CIRTH_9
|
77
|
+
f --> CIRTH_3
|
78
|
+
g --> CIRTH_19
|
79
|
+
h --> CIRTH_34
|
80
|
+
gh --> CIRTH_19 CIRTH_34
|
81
|
+
k --> CIRTH_18
|
82
|
+
l --> CIRTH_31
|
83
|
+
m --> CIRTH_6
|
84
|
+
n --> CIRTH_22
|
85
|
+
nd --> CIRTH_33
|
86
|
+
r --> CIRTH_12
|
87
|
+
s --> CIRTH_54
|
88
|
+
t --> CIRTH_8
|
89
|
+
sh --> CIRTH_15
|
90
|
+
th --> CIRTH_8 CIRTH_59
|
91
|
+
z --> CIRTH_17
|
92
|
+
|
93
|
+
k --> CIRTH_18
|
94
|
+
kh --> CIRTH_18 CIRTH_59
|
95
|
+
\end
|
96
|
+
|
97
|
+
\beg rules punctuation
|
98
|
+
. --> CIRTH_PUNCT_THREE_DOTS
|
99
|
+
.. --> CIRTH_PUNCT_THREE_DOTS
|
100
|
+
... --> CIRTH_PUNCT_THREE_DOTS
|
101
|
+
… --> CIRTH_PUNCT_THREE_DOTS
|
102
|
+
.... --> CIRTH_PUNCT_THREE_DOTS
|
103
|
+
..... --> CIRTH_PUNCT_THREE_DOTS
|
104
|
+
...... --> CIRTH_PUNCT_THREE_DOTS
|
105
|
+
....... --> CIRTH_PUNCT_THREE_DOTS
|
106
|
+
|
107
|
+
, --> CIRTH_PUNCT_MID_DOT
|
108
|
+
: --> CIRTH_PUNCT_TWO_DOTS
|
109
|
+
; --> CIRTH_PUNCT_TWO_DOTS
|
110
|
+
! --> CIRTH_PUNCT_THREE_DOTS
|
111
|
+
? --> CIRTH_PUNCT_THREE_DOTS
|
112
|
+
· --> CIRTH_PUNCT_MID_DOT
|
113
|
+
|
114
|
+
- --> CIRTH_PUNCT_MID_DOT
|
115
|
+
– --> CIRTH_PUNCT_TWO_DOTS
|
116
|
+
— --> CIRTH_PUNCT_TWO_DOTS
|
117
|
+
|
118
|
+
\** Apostrophe **\
|
119
|
+
|
120
|
+
' --> {NULL}
|
121
|
+
’ --> {NULL}
|
122
|
+
|
123
|
+
\** Quotes **\
|
124
|
+
|
125
|
+
“ --> {NULL}
|
126
|
+
” --> {NULL}
|
127
|
+
« --> {NULL}
|
128
|
+
» --> {NULL}
|
129
|
+
|
130
|
+
[ --> CIRTH_PUNCT_THREE_DOTS_L
|
131
|
+
] --> CIRTH_PUNCT_THREE_DOTS_L
|
132
|
+
( --> CIRTH_PUNCT_THREE_DOTS_L
|
133
|
+
) --> CIRTH_PUNCT_THREE_DOTS_L
|
134
|
+
{ --> CIRTH_PUNCT_THREE_DOTS_L
|
135
|
+
} --> CIRTH_PUNCT_THREE_DOTS_L
|
136
|
+
< --> CIRTH_PUNCT_THREE_DOTS_L
|
137
|
+
> --> CIRTH_PUNCT_THREE_DOTS_L
|
138
|
+
|
139
|
+
/ --> CIRTH_PUNCT_FOUR_DOTS
|
140
|
+
\end
|
141
|
+
\end
|