interscript-maps 3.2.4 → 3.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/interscript-maps.gemspec +1 -1
- data/maps/alalc-aze-Cyrl-Latn-1997.isc +48 -11
- data/maps/alalc-ben-Beng-Latn-2017.isc +68 -17
- data/maps/alalc-sat-Olck-Latn-2017.isc +7 -3
- data/maps/bsi-rus-Cyrl-Latn-2979-1958.isc +233 -0
- data/maps/din-ab-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-atv-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-az-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-ba-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-urd-Arab-Latn-31635-2011.isc +7 -1
- data/maps/iso-ben-Beng-Latn-15919-2001.isc +5 -0
- data/maps/iso-ben-Beng-Latn-15919-2026.isc +228 -0
- data/maps/iso-doi-Takr-Latn-15919-2026.isc +182 -0
- data/maps/iso-guj-Gujr-Latn-15919-2026.isc +231 -0
- data/maps/iso-heb-Hebr-Latn-259-1984.isc +426 -0
- data/maps/iso-heb-Hebr-Latn-259-2-1994.isc +469 -0
- data/maps/iso-inc-Kthi-Latn-15919-2001.isc +121 -0
- data/maps/iso-inc-Kthi-Latn-15919-2026.isc +197 -0
- data/maps/iso-jpn-Hrkt-Latn-3602-1989.isc +53 -0
- data/maps/iso-kan-Kana-Latn-15919-2001.isc +8 -4
- data/maps/iso-kan-Kana-Latn-15919-2026.isc +229 -0
- data/maps/iso-kas-Shrd-Latn-15919-2026.isc +208 -0
- data/maps/iso-mal-Mlym-Latn-15919-2001.isc +1 -0
- data/maps/iso-mal-Mlym-Latn-15919-2026.isc +223 -0
- data/maps/iso-mar-Deva-Latn-15919-2001.isc +1 -1
- data/maps/iso-mar-Modi-Latn-15919-2026.isc +204 -0
- data/maps/iso-new-Newa-Latn-15919-2026.isc +221 -0
- data/maps/iso-ori-Orya-Latn-15919-2026.isc +222 -0
- data/maps/iso-pan-Guru-Latn-15919-2026.isc +222 -0
- data/maps/iso-pra-Brah-Latn-15919-2026.isc +231 -0
- data/maps/iso-san-Deva-Latn-15919-2001.isc +5 -2
- data/maps/iso-san-Deva-Latn-15919-2026.isc +278 -0
- data/maps/iso-san-Gran-Latn-15919-2026.isc +208 -0
- data/maps/iso-sin-Sinh-Latn-15919-2001.isc +174 -0
- data/maps/iso-sin-Sinh-Latn-15919-2026.isc +238 -0
- data/maps/iso-tam-Taml-Latn-15919-2001.isc +1 -0
- data/maps/iso-tam-Taml-Latn-15919-2026.isc +178 -0
- data/maps/iso-tel-Telu-Latn-15919-2001.isc +7 -0
- data/maps/iso-tel-Telu-Latn-15919-2026.isc +229 -0
- data/maps/odni-che-Cyrl-Latn-2015.isc +19 -19
- data/maps/odni-mkd-Cyrl-Latn-2015.isc +11 -16
- data/maps/var-jpn-Hrkt-Latn-komaba-2009.isc +417 -0
- metadata +24 -2
- data/maps/bsi-rus-Cyrl-Latn-1958.isc +0 -199
|
@@ -0,0 +1,469 @@
|
|
|
1
|
+
system "ISO:heb-Hebr:Latn:259-2-1994" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 259-2-1994
|
|
6
|
+
language iso-639-2:heb
|
|
7
|
+
source_script Hebr
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO 259-2:1994 Information and documentation -- Transliteration of Hebrew characters into Latin characters -- Part 2: Simplified transliteration"
|
|
10
|
+
url https://www.iso.org/standard/4162.html
|
|
11
|
+
creation_date 1994
|
|
12
|
+
description { Specifies a simplified system for the transliteration of Hebrew characters
|
|
13
|
+
into Latin characters, relaxing the stringent prescriptions of ISO 259:1984;
|
|
14
|
+
intended for the processing of bibliographic information (catalogues, indexes,
|
|
15
|
+
references). First edition 1994-12-15, prepared by ISO/TC 46, corrected and
|
|
16
|
+
reprinted 1995-07-15. This map encodes Table 1 (consonants, 43 rows),
|
|
17
|
+
Table 2 (vowel signs, 44-55) and Table 3 (non-Hebrew phonemes and
|
|
18
|
+
abbreviation symbols).
|
|
19
|
+
}
|
|
20
|
+
|
|
21
|
+
notes {
|
|
22
|
+
note "The simplified system marks the dagesh of rows 3, 9, 20 and 31 with the dot above (Annex A, 4/7), and row 11 (shuruq) renders U+1E87 as row 52 of Table 2 (the same sequence U+05D5 U+05BC, Annex A 4/7). The dagesh of rows 5, 7, 13, 18, 24, 26 and 28 is not marked (plain letter); rows 16 and 33 keep only the dot below of their base output, rows 39 and 41 only the caron or acute, and rows 22, 35 and 43 render the plain letter. Clause 3.3: one character of constant form per letter, so final forms take their letter's row. Row 38 is a typographic variant of row 37 (one Unicode sequence U+05E9 U+05C1, raised caron, Annex A 4/15) and maps identically to row 37."
|
|
23
|
+
note "NOTE to Table 2: the shva (U+05B0) is not rendered and is deleted. Waw+holam renders U+0175 (row 51; input forms U+05D5 U+05B9, U+05BA and U+FB4B); waw+dagesh (shuruq) renders U+1E87 (rows 11 and 52 are the same sequence U+05D5 U+05BC)."
|
|
24
|
+
note "Table 3: gimel-geresh, zayin-geresh and tsadi-geresh render as their Table 1 letters plus U+02B9 (g + U+02B9, z + U+02B9, U+1E63 + U+02B9), per the recommendation to use the table 1 letters marked with the same diacritical mark as the original. Geresh U+05F3 renders as U+02B9 at the end of an abbreviation; gershayim U+05F4 renders as U+02BA between the last two letters (the Hebrew placement is preserved by pass-through); the period passes through unchanged. The standard's own unpointed examples read Gʹin / Zʹan (yod and alef as vowel bearers); this map renders the table rows strictly (g + U+02B9 + y + n; z + U+02B9 + alef + n)."
|
|
25
|
+
note "Unpointed shin U+05E9 renders as shin with sin dot (row 37, U+0161). Alphabetic Presentation Forms equal to their decompositions (U+FB2A-U+FB2D and the point-bearing letter forms U+FB30-U+FB3C, U+FB3E, U+FB40, U+FB41, U+FB43, U+FB44, U+FB46-U+FB4E) are accepted as input and render by their table rows; the rafe forms U+FB4C, U+FB4D and U+FB4E render as the bare letter (no table rafe row). Composed letter+vowel forms and the alef-lamed ligature U+FB4F are out of scope and pass through."
|
|
26
|
+
note "Marks outside Tables 1-3 are deleted: teamim (U+0591-U+05AF), meteg (U+05BD), rafe (U+05BF), upper dot (U+05C4), lower dot (U+05C5), qamats qatan (U+05C7) and residual dagesh (U+05BC), shin dot (U+05C1) and sin dot (U+05C2). Maqaf U+05BE, paseq U+05C0, sof pasuq U+05C3, nun hafukha U+05C6 and the Hebrew ligatures U+05F0-U+05F2 are outside the standard's tables and pass through unchanged."
|
|
27
|
+
note "Mark-order normalization moves dagesh and the shin/sin dots next to their base letter (canonical combining order places the vowel signs first). Letter-first legacy stacks and canonical NFC stacks are fully handled; a fully non-canonical stack (vowel, shin dot, dagesh) may leave the dagesh unrendered."
|
|
28
|
+
note "Encoded from the official ISO 259-2:1994(E) edition (corrected and reprinted 1995-07-15) and verified cell for cell against its Tables 1-3 and Annex A; the official text supersedes earlier preview-derived readings (the preview renders had been read as dotting the dagesh of rows 5, 7, 13, 18, 24, 26 and 28, which the official text shows plain). The informative Annex A (diacritical-sign positions) and Annex B (names of the Hebrew characters) are covered by the official text; clause 2.8 capitalization follows national usage and is not applied by this map."
|
|
29
|
+
}
|
|
30
|
+
}
|
|
31
|
+
|
|
32
|
+
tests {
|
|
33
|
+
# Table 1, consonant rows (the standard's row numbering)
|
|
34
|
+
"א" -> "ʾ̲"
|
|
35
|
+
"ב" -> "b"
|
|
36
|
+
"בּ" -> "ḃ"
|
|
37
|
+
"ג" -> "g"
|
|
38
|
+
# row 5 renders unmarked
|
|
39
|
+
"גּ" -> "g"
|
|
40
|
+
"ד" -> "d"
|
|
41
|
+
# row 7 renders unmarked
|
|
42
|
+
"דּ" -> "d"
|
|
43
|
+
"ה" -> "h"
|
|
44
|
+
"הּ" -> "ḣ"
|
|
45
|
+
"ו" -> "w"
|
|
46
|
+
"וּ" -> "ẇ"
|
|
47
|
+
"ז" -> "z"
|
|
48
|
+
# row 13 renders unmarked
|
|
49
|
+
"זּ" -> "z"
|
|
50
|
+
"ח" -> "ḥ"
|
|
51
|
+
"ט" -> "ṭ"
|
|
52
|
+
# row 16 renders unmarked
|
|
53
|
+
"טּ" -> "ṭ"
|
|
54
|
+
"י" -> "y"
|
|
55
|
+
# row 18 renders unmarked
|
|
56
|
+
"יּ" -> "y"
|
|
57
|
+
"כ" -> "k"
|
|
58
|
+
"כּ" -> "k̇"
|
|
59
|
+
"ל" -> "l"
|
|
60
|
+
# row 22 renders unmarked
|
|
61
|
+
"לּ" -> "l"
|
|
62
|
+
"מ" -> "m"
|
|
63
|
+
# row 24 renders unmarked
|
|
64
|
+
"מּ" -> "m"
|
|
65
|
+
"נ" -> "n"
|
|
66
|
+
# row 26 renders unmarked
|
|
67
|
+
"נּ" -> "n"
|
|
68
|
+
"ס" -> "s"
|
|
69
|
+
# row 28 renders unmarked
|
|
70
|
+
"סּ" -> "s"
|
|
71
|
+
"ע" -> "ʿ̲"
|
|
72
|
+
"פ" -> "p"
|
|
73
|
+
"פּ" -> "ṗ"
|
|
74
|
+
"צ" -> "ṣ"
|
|
75
|
+
# row 33 renders unmarked
|
|
76
|
+
"צּ" -> "ṣ"
|
|
77
|
+
"ק" -> "q"
|
|
78
|
+
# row 35 renders unmarked
|
|
79
|
+
"קּ" -> "q"
|
|
80
|
+
"ר" -> "r"
|
|
81
|
+
"שׁ" -> "š"
|
|
82
|
+
# row 38, the raised-caron typographic variant, is the same sequence as row 37;
|
|
83
|
+
# row 39 renders unmarked
|
|
84
|
+
"שּׁ" -> "š"
|
|
85
|
+
"שּׁ" -> "š"
|
|
86
|
+
"ש" -> "š"
|
|
87
|
+
"שׂ" -> "ś"
|
|
88
|
+
# row 41 renders unmarked
|
|
89
|
+
"שּׂ" -> "ś"
|
|
90
|
+
"ת" -> "t"
|
|
91
|
+
# row 43 renders unmarked
|
|
92
|
+
"תּ" -> "t"
|
|
93
|
+
# clause 3.3: final forms take their letter's constant character
|
|
94
|
+
"ך" -> "k"
|
|
95
|
+
"ם" -> "m"
|
|
96
|
+
"ן" -> "n"
|
|
97
|
+
"ף" -> "p"
|
|
98
|
+
"ץ" -> "ṣ"
|
|
99
|
+
# Table 2, vowel-sign rows (44-55), shown on bet; row 52 = row 11
|
|
100
|
+
"בַ" -> "ba"
|
|
101
|
+
"בָ" -> "ba"
|
|
102
|
+
"בֶ" -> "be"
|
|
103
|
+
"בֵ" -> "be"
|
|
104
|
+
"בִ" -> "bi"
|
|
105
|
+
"בֹ" -> "bo"
|
|
106
|
+
"בֻ" -> "bu"
|
|
107
|
+
"וֹ" -> "ŵ"
|
|
108
|
+
"וּ" -> "ẇ"
|
|
109
|
+
"בֲ" -> "ba"
|
|
110
|
+
"בֱ" -> "be"
|
|
111
|
+
"בֳ" -> "bo"
|
|
112
|
+
# NOTE to Table 2: the shva is not rendered
|
|
113
|
+
"בְ" -> "b"
|
|
114
|
+
# mark-order normalization: canonical NFC stacks and legacy letter-first stacks
|
|
115
|
+
"בַּ" -> "ḃa"
|
|
116
|
+
"בַּ" -> "ḃa"
|
|
117
|
+
"שָׁ" -> "ša"
|
|
118
|
+
"שָּׁ" -> "ša"
|
|
119
|
+
"הַּ" -> "ḣa"
|
|
120
|
+
# words exercising the composition rules
|
|
121
|
+
"תּוֹרָה" -> "tŵrah"
|
|
122
|
+
"בְּרֵאשִׁית" -> "ḃreʾ̲šiyt"
|
|
123
|
+
# Alphabetic Presentation Forms, decomposition equivalents of the rows
|
|
124
|
+
"שׁ" -> "š"
|
|
125
|
+
"שׂ" -> "ś"
|
|
126
|
+
"שּׁ" -> "š"
|
|
127
|
+
"שּׂ" -> "ś"
|
|
128
|
+
"בּ" -> "ḃ"
|
|
129
|
+
"גּ" -> "g"
|
|
130
|
+
"דּ" -> "d"
|
|
131
|
+
"זּ" -> "z"
|
|
132
|
+
"יּ" -> "y"
|
|
133
|
+
"מּ" -> "m"
|
|
134
|
+
"נּ" -> "n"
|
|
135
|
+
"סּ" -> "s"
|
|
136
|
+
"הּ" -> "ḣ"
|
|
137
|
+
"וּ" -> "ẇ"
|
|
138
|
+
"וֹ" -> "ŵ"
|
|
139
|
+
"בֿ" -> "b"
|
|
140
|
+
# Table 3: non-Hebrew phonemes and abbreviation symbols
|
|
141
|
+
# (the print shows sentence-initial capitals and mater-vowel readings for
|
|
142
|
+
# the first two examples; this map renders the table rows strictly, yod
|
|
143
|
+
# row 17 -> y and alef row 1 -> alef mark + low line)
|
|
144
|
+
"ג׳ין" -> "gʹyn"
|
|
145
|
+
"ז׳אן" -> "zʹʾ̲n"
|
|
146
|
+
"פרופ׳" -> "prwpʹ"
|
|
147
|
+
"ק״מ" -> "qʺm"
|
|
148
|
+
"ד." -> "d."
|
|
149
|
+
}
|
|
150
|
+
|
|
151
|
+
stage main {
|
|
152
|
+
|
|
153
|
+
# MARK-ORDER NORMALIZATION
|
|
154
|
+
# The canonical combining order places the vowel signs (ccc 10-20) before
|
|
155
|
+
# the dagesh (ccc 21) and the shin/sin dots (ccc 24-25). Move the dots back
|
|
156
|
+
# next to the letter so the letter+dot sequences of Tables 1-2 match.
|
|
157
|
+
sub {
|
|
158
|
+
from "ְּ"
|
|
159
|
+
to "ְּ"
|
|
160
|
+
}
|
|
161
|
+
sub {
|
|
162
|
+
from "ְׁ"
|
|
163
|
+
to "ְׁ"
|
|
164
|
+
}
|
|
165
|
+
sub {
|
|
166
|
+
from "ְׂ"
|
|
167
|
+
to "ְׂ"
|
|
168
|
+
}
|
|
169
|
+
sub {
|
|
170
|
+
from "ֱּ"
|
|
171
|
+
to "ֱּ"
|
|
172
|
+
}
|
|
173
|
+
sub {
|
|
174
|
+
from "ֱׁ"
|
|
175
|
+
to "ֱׁ"
|
|
176
|
+
}
|
|
177
|
+
sub {
|
|
178
|
+
from "ֱׂ"
|
|
179
|
+
to "ֱׂ"
|
|
180
|
+
}
|
|
181
|
+
sub {
|
|
182
|
+
from "ֲּ"
|
|
183
|
+
to "ֲּ"
|
|
184
|
+
}
|
|
185
|
+
sub {
|
|
186
|
+
from "ֲׁ"
|
|
187
|
+
to "ֲׁ"
|
|
188
|
+
}
|
|
189
|
+
sub {
|
|
190
|
+
from "ֲׂ"
|
|
191
|
+
to "ֲׂ"
|
|
192
|
+
}
|
|
193
|
+
sub {
|
|
194
|
+
from "ֳּ"
|
|
195
|
+
to "ֳּ"
|
|
196
|
+
}
|
|
197
|
+
sub {
|
|
198
|
+
from "ֳׁ"
|
|
199
|
+
to "ֳׁ"
|
|
200
|
+
}
|
|
201
|
+
sub {
|
|
202
|
+
from "ֳׂ"
|
|
203
|
+
to "ֳׂ"
|
|
204
|
+
}
|
|
205
|
+
sub {
|
|
206
|
+
from "ִּ"
|
|
207
|
+
to "ִּ"
|
|
208
|
+
}
|
|
209
|
+
sub {
|
|
210
|
+
from "ִׁ"
|
|
211
|
+
to "ִׁ"
|
|
212
|
+
}
|
|
213
|
+
sub {
|
|
214
|
+
from "ִׂ"
|
|
215
|
+
to "ִׂ"
|
|
216
|
+
}
|
|
217
|
+
sub {
|
|
218
|
+
from "ֵּ"
|
|
219
|
+
to "ֵּ"
|
|
220
|
+
}
|
|
221
|
+
sub {
|
|
222
|
+
from "ֵׁ"
|
|
223
|
+
to "ֵׁ"
|
|
224
|
+
}
|
|
225
|
+
sub {
|
|
226
|
+
from "ֵׂ"
|
|
227
|
+
to "ֵׂ"
|
|
228
|
+
}
|
|
229
|
+
sub {
|
|
230
|
+
from "ֶּ"
|
|
231
|
+
to "ֶּ"
|
|
232
|
+
}
|
|
233
|
+
sub {
|
|
234
|
+
from "ֶׁ"
|
|
235
|
+
to "ֶׁ"
|
|
236
|
+
}
|
|
237
|
+
sub {
|
|
238
|
+
from "ֶׂ"
|
|
239
|
+
to "ֶׂ"
|
|
240
|
+
}
|
|
241
|
+
sub {
|
|
242
|
+
from "ַּ"
|
|
243
|
+
to "ַּ"
|
|
244
|
+
}
|
|
245
|
+
sub {
|
|
246
|
+
from "ַׁ"
|
|
247
|
+
to "ַׁ"
|
|
248
|
+
}
|
|
249
|
+
sub {
|
|
250
|
+
from "ַׂ"
|
|
251
|
+
to "ַׂ"
|
|
252
|
+
}
|
|
253
|
+
sub {
|
|
254
|
+
from "ָּ"
|
|
255
|
+
to "ָּ"
|
|
256
|
+
}
|
|
257
|
+
sub {
|
|
258
|
+
from "ָׁ"
|
|
259
|
+
to "ָׁ"
|
|
260
|
+
}
|
|
261
|
+
sub {
|
|
262
|
+
from "ָׂ"
|
|
263
|
+
to "ָׂ"
|
|
264
|
+
}
|
|
265
|
+
sub {
|
|
266
|
+
from "ֹּ"
|
|
267
|
+
to "ֹּ"
|
|
268
|
+
}
|
|
269
|
+
sub {
|
|
270
|
+
from "ֹׁ"
|
|
271
|
+
to "ֹׁ"
|
|
272
|
+
}
|
|
273
|
+
sub {
|
|
274
|
+
from "ֹׂ"
|
|
275
|
+
to "ֹׂ"
|
|
276
|
+
}
|
|
277
|
+
sub {
|
|
278
|
+
from "ֺּ"
|
|
279
|
+
to "ֺּ"
|
|
280
|
+
}
|
|
281
|
+
sub {
|
|
282
|
+
from "ֺׁ"
|
|
283
|
+
to "ֺׁ"
|
|
284
|
+
}
|
|
285
|
+
sub {
|
|
286
|
+
from "ֺׂ"
|
|
287
|
+
to "ֺׂ"
|
|
288
|
+
}
|
|
289
|
+
sub {
|
|
290
|
+
from "ֻּ"
|
|
291
|
+
to "ֻּ"
|
|
292
|
+
}
|
|
293
|
+
sub {
|
|
294
|
+
from "ֻׁ"
|
|
295
|
+
to "ֻׁ"
|
|
296
|
+
}
|
|
297
|
+
sub {
|
|
298
|
+
from "ֻׂ"
|
|
299
|
+
to "ֻׂ"
|
|
300
|
+
}
|
|
301
|
+
sub {
|
|
302
|
+
from "ּׁ"
|
|
303
|
+
to "ּׁ"
|
|
304
|
+
}
|
|
305
|
+
sub {
|
|
306
|
+
from "ּׂ"
|
|
307
|
+
to "ּׂ"
|
|
308
|
+
}
|
|
309
|
+
|
|
310
|
+
# CHARACTERS
|
|
311
|
+
parallel {
|
|
312
|
+
# Table 2, row 51: waw + holam (before bare waw and bare holam)
|
|
313
|
+
sub "וֹ" "ŵ"
|
|
314
|
+
# Table 1, rows 1-43: dagesh rows 3, 9, 20 and 31 carry the dot above
|
|
315
|
+
# (row 11 shuruq renders as Table 2 row 52, U+1E87); the dagesh of rows
|
|
316
|
+
# 5, 7, 13, 16, 18, 22, 24, 26, 28, 33, 35, 39, 41 and 43 renders
|
|
317
|
+
# unmarked and is absorbed
|
|
318
|
+
sub "א" "ʾ̲"
|
|
319
|
+
sub "בּ" "ḃ"
|
|
320
|
+
sub "ב" "b"
|
|
321
|
+
sub "גּ" "g"
|
|
322
|
+
sub "ג" "g"
|
|
323
|
+
sub "דּ" "d"
|
|
324
|
+
sub "ד" "d"
|
|
325
|
+
sub "הּ" "ḣ"
|
|
326
|
+
sub "ה" "h"
|
|
327
|
+
sub "וּ" "ẇ"
|
|
328
|
+
sub "ו" "w"
|
|
329
|
+
sub "זּ" "z"
|
|
330
|
+
sub "ז" "z"
|
|
331
|
+
sub "ח" "ḥ"
|
|
332
|
+
sub "טּ" "ṭ"
|
|
333
|
+
sub "ט" "ṭ"
|
|
334
|
+
sub "יּ" "y"
|
|
335
|
+
sub "י" "y"
|
|
336
|
+
sub "כּ" "k̇"
|
|
337
|
+
sub "כ" "k"
|
|
338
|
+
sub "לּ" "l"
|
|
339
|
+
sub "ל" "l"
|
|
340
|
+
sub "מּ" "m"
|
|
341
|
+
sub "מ" "m"
|
|
342
|
+
sub "נּ" "n"
|
|
343
|
+
sub "נ" "n"
|
|
344
|
+
sub "סּ" "s"
|
|
345
|
+
sub "ס" "s"
|
|
346
|
+
sub "ע" "ʿ̲"
|
|
347
|
+
sub "פּ" "ṗ"
|
|
348
|
+
sub "פ" "p"
|
|
349
|
+
sub "צּ" "ṣ"
|
|
350
|
+
sub "צ" "ṣ"
|
|
351
|
+
sub "קּ" "q"
|
|
352
|
+
sub "ק" "q"
|
|
353
|
+
sub "ר" "r"
|
|
354
|
+
# rows 37-41 (row 38 is the raised-caron typographic variant of row 37);
|
|
355
|
+
# rows 39 and 41 render unmarked
|
|
356
|
+
sub "שּׁ" "š"
|
|
357
|
+
sub "שּׁ" "š"
|
|
358
|
+
sub "שׁ" "š"
|
|
359
|
+
sub "שּׂ" "ś"
|
|
360
|
+
sub "שּׂ" "ś"
|
|
361
|
+
sub "שׂ" "ś"
|
|
362
|
+
# unpointed shin reads as shin with sin dot (row 37)
|
|
363
|
+
sub "ש" "š"
|
|
364
|
+
sub "תּ" "t"
|
|
365
|
+
sub "ת" "t"
|
|
366
|
+
# clause 3.3: final forms take their letter's rows
|
|
367
|
+
sub "ךּ" "k̇"
|
|
368
|
+
sub "ך" "k"
|
|
369
|
+
sub "ם" "m"
|
|
370
|
+
sub "ן" "n"
|
|
371
|
+
sub "ףּ" "ṗ"
|
|
372
|
+
sub "ף" "p"
|
|
373
|
+
sub "ץ" "ṣ"
|
|
374
|
+
# Alphabetic Presentation Forms, decomposition equivalents of the rows
|
|
375
|
+
# (the rafe forms render as the bare letter: no table rafe row)
|
|
376
|
+
sub "שׁ" "š"
|
|
377
|
+
sub "שׂ" "ś"
|
|
378
|
+
sub "שּׁ" "š"
|
|
379
|
+
sub "שּׂ" "ś"
|
|
380
|
+
sub "אּ" "ʾ̲"
|
|
381
|
+
sub "בּ" "ḃ"
|
|
382
|
+
sub "גּ" "g"
|
|
383
|
+
sub "דּ" "d"
|
|
384
|
+
sub "הּ" "ḣ"
|
|
385
|
+
sub "וּ" "ẇ"
|
|
386
|
+
sub "זּ" "z"
|
|
387
|
+
sub "טּ" "ṭ"
|
|
388
|
+
sub "יּ" "y"
|
|
389
|
+
sub "ךּ" "k̇"
|
|
390
|
+
sub "כּ" "k̇"
|
|
391
|
+
sub "לּ" "l"
|
|
392
|
+
sub "מּ" "m"
|
|
393
|
+
sub "נּ" "n"
|
|
394
|
+
sub "סּ" "s"
|
|
395
|
+
sub "ףּ" "ṗ"
|
|
396
|
+
sub "פּ" "ṗ"
|
|
397
|
+
sub "צּ" "ṣ"
|
|
398
|
+
sub "קּ" "q"
|
|
399
|
+
sub "רּ" "r"
|
|
400
|
+
sub "שּ" "š"
|
|
401
|
+
sub "תּ" "t"
|
|
402
|
+
sub "וֹ" "ŵ"
|
|
403
|
+
sub "בֿ" "b"
|
|
404
|
+
sub "כֿ" "k"
|
|
405
|
+
sub "פֿ" "p"
|
|
406
|
+
# Table 3: non-Hebrew phonemes and abbreviation symbols
|
|
407
|
+
sub "׳" "ʹ"
|
|
408
|
+
sub "״" "ʺ"
|
|
409
|
+
# Table 2, vowel signs (rows 44-55; row 51 waw+holam above,
|
|
410
|
+
# row 52 = row 11)
|
|
411
|
+
sub "ֺ" "ŵ"
|
|
412
|
+
sub "ַ" "a"
|
|
413
|
+
sub "ָ" "a"
|
|
414
|
+
sub "ֶ" "e"
|
|
415
|
+
sub "ֵ" "e"
|
|
416
|
+
sub "ִ" "i"
|
|
417
|
+
sub "ֹ" "o"
|
|
418
|
+
sub "ֻ" "u"
|
|
419
|
+
sub "ֲ" "a"
|
|
420
|
+
sub "ֱ" "e"
|
|
421
|
+
sub "ֳ" "o"
|
|
422
|
+
# NOTE to Table 2: the shva is not rendered
|
|
423
|
+
sub "ְ" ""
|
|
424
|
+
# residual marks outside the tables
|
|
425
|
+
sub "ּ" ""
|
|
426
|
+
sub "ֽ" ""
|
|
427
|
+
sub "ֿ" ""
|
|
428
|
+
sub "ׁ" ""
|
|
429
|
+
sub "ׂ" ""
|
|
430
|
+
sub "ׄ" ""
|
|
431
|
+
sub "ׅ" ""
|
|
432
|
+
sub "ׇ" ""
|
|
433
|
+
# teamim (cantillation marks)
|
|
434
|
+
sub "֑" ""
|
|
435
|
+
sub "֒" ""
|
|
436
|
+
sub "֓" ""
|
|
437
|
+
sub "֔" ""
|
|
438
|
+
sub "֕" ""
|
|
439
|
+
sub "֖" ""
|
|
440
|
+
sub "֗" ""
|
|
441
|
+
sub "֘" ""
|
|
442
|
+
sub "֙" ""
|
|
443
|
+
sub "֚" ""
|
|
444
|
+
sub "֛" ""
|
|
445
|
+
sub "֜" ""
|
|
446
|
+
sub "֝" ""
|
|
447
|
+
sub "֞" ""
|
|
448
|
+
sub "֟" ""
|
|
449
|
+
sub "֠" ""
|
|
450
|
+
sub "֡" ""
|
|
451
|
+
sub "֢" ""
|
|
452
|
+
sub "֣" ""
|
|
453
|
+
sub "֤" ""
|
|
454
|
+
sub "֥" ""
|
|
455
|
+
sub "֦" ""
|
|
456
|
+
sub "֧" ""
|
|
457
|
+
sub "֨" ""
|
|
458
|
+
sub "֩" ""
|
|
459
|
+
sub "֪" ""
|
|
460
|
+
sub "֫" ""
|
|
461
|
+
sub "֬" ""
|
|
462
|
+
sub "֭" ""
|
|
463
|
+
sub "֮" ""
|
|
464
|
+
sub "֯" ""
|
|
465
|
+
}
|
|
466
|
+
|
|
467
|
+
}
|
|
468
|
+
|
|
469
|
+
}
|
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
system "ISO:inc-Kthi:Latn:15919-2001" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2001
|
|
6
|
+
language iso-639-2:inc
|
|
7
|
+
source_script Kthi
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Kaithi)"
|
|
10
|
+
url https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
|
|
11
|
+
creation_date 2001
|
|
12
|
+
adoption_date 2001
|
|
13
|
+
description { ISO 15919:2001 first edition, Transliteration of Devanagari and related Indic scripts
|
|
14
|
+
into Latin characters. Every printed row of the transcription-source table is encoded
|
|
15
|
+
and embedded as a test row; see notes for provenance, cross-check rates, and findings. }
|
|
16
|
+
|
|
17
|
+
notes {
|
|
18
|
+
note "Authority: ISO 15919:2001 first edition (Kaithi listed in its scope annex); the first edition printed no per-script Kaithi table, so the rows follow the transcription source below and are verified against the second edition's Table 7.13 where they overlap."
|
|
19
|
+
note "Transcription source (owner blessing 2026-11-17): Wikipedia ISO 15919 article table, CC BY-SA, https://en.wikipedia.org/wiki/ISO_15919 - every printed Kaithi cell is encoded and embedded as a test row."
|
|
20
|
+
note "Verification: all overlapping cells agree with ISO/DIS 15919 (2026) Table 7.13 (N125), which additionally prints vocalic r, candrabindu, anusvara and visarga rows not printed by the transcription source."
|
|
21
|
+
note "Vowel-sign rows are not printed by the transcription source for Kaithi and are not encoded; see the 15919-2026 Kaithi map for the second edition's full sign inventory."
|
|
22
|
+
}
|
|
23
|
+
}
|
|
24
|
+
|
|
25
|
+
tests {
|
|
26
|
+
"𑂃" -> "a"
|
|
27
|
+
"𑂄" -> "ā"
|
|
28
|
+
"𑂅" -> "i"
|
|
29
|
+
"𑂆" -> "ī"
|
|
30
|
+
"𑂇" -> "u"
|
|
31
|
+
"𑂈" -> "ū"
|
|
32
|
+
"𑂉" -> "ē"
|
|
33
|
+
"𑂊" -> "ai"
|
|
34
|
+
"𑂋" -> "ō"
|
|
35
|
+
"𑂌" -> "au"
|
|
36
|
+
"𑂍" -> "ka"
|
|
37
|
+
"𑂎" -> "kha"
|
|
38
|
+
"𑂏" -> "ga"
|
|
39
|
+
"𑂐" -> "gha"
|
|
40
|
+
"𑂑" -> "ṅa"
|
|
41
|
+
"𑂒" -> "ca"
|
|
42
|
+
"𑂓" -> "cha"
|
|
43
|
+
"𑂔" -> "ja"
|
|
44
|
+
"𑂕" -> "jha"
|
|
45
|
+
"𑂖" -> "ña"
|
|
46
|
+
"𑂗" -> "ṭa"
|
|
47
|
+
"𑂘" -> "ṭha"
|
|
48
|
+
"𑂙" -> "ḍa"
|
|
49
|
+
"𑂛" -> "ḍha"
|
|
50
|
+
"𑂝" -> "ṇa"
|
|
51
|
+
"𑂞" -> "ta"
|
|
52
|
+
"𑂟" -> "tha"
|
|
53
|
+
"𑂠" -> "da"
|
|
54
|
+
"𑂡" -> "dha"
|
|
55
|
+
"𑂢" -> "na"
|
|
56
|
+
"𑂣" -> "pa"
|
|
57
|
+
"𑂤" -> "pha"
|
|
58
|
+
"𑂥" -> "ba"
|
|
59
|
+
"𑂦" -> "bha"
|
|
60
|
+
"𑂧" -> "ma"
|
|
61
|
+
"𑂨" -> "ya"
|
|
62
|
+
"𑂩" -> "ra"
|
|
63
|
+
"𑂪" -> "la"
|
|
64
|
+
"𑂫" -> "va"
|
|
65
|
+
"𑂬" -> "śa"
|
|
66
|
+
"𑂭" -> "ṣa"
|
|
67
|
+
"𑂮" -> "sa"
|
|
68
|
+
"𑂯" -> "ha"
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
stage main {
|
|
72
|
+
|
|
73
|
+
parallel {
|
|
74
|
+
sub "𑂃" "a"
|
|
75
|
+
sub "𑂄" "ā"
|
|
76
|
+
sub "𑂅" "i"
|
|
77
|
+
sub "𑂆" "ī"
|
|
78
|
+
sub "𑂇" "u"
|
|
79
|
+
sub "𑂈" "ū"
|
|
80
|
+
sub "𑂉" "ē"
|
|
81
|
+
sub "𑂊" "ai"
|
|
82
|
+
sub "𑂋" "ō"
|
|
83
|
+
sub "𑂌" "au"
|
|
84
|
+
sub "𑂍" "ka"
|
|
85
|
+
sub "𑂎" "kha"
|
|
86
|
+
sub "𑂏" "ga"
|
|
87
|
+
sub "𑂐" "gha"
|
|
88
|
+
sub "𑂑" "ṅa"
|
|
89
|
+
sub "𑂒" "ca"
|
|
90
|
+
sub "𑂓" "cha"
|
|
91
|
+
sub "𑂔" "ja"
|
|
92
|
+
sub "𑂕" "jha"
|
|
93
|
+
sub "𑂖" "ña"
|
|
94
|
+
sub "𑂗" "ṭa"
|
|
95
|
+
sub "𑂘" "ṭha"
|
|
96
|
+
sub "𑂙" "ḍa"
|
|
97
|
+
sub "𑂛" "ḍha"
|
|
98
|
+
sub "𑂝" "ṇa"
|
|
99
|
+
sub "𑂞" "ta"
|
|
100
|
+
sub "𑂟" "tha"
|
|
101
|
+
sub "𑂠" "da"
|
|
102
|
+
sub "𑂡" "dha"
|
|
103
|
+
sub "𑂢" "na"
|
|
104
|
+
sub "𑂣" "pa"
|
|
105
|
+
sub "𑂤" "pha"
|
|
106
|
+
sub "𑂥" "ba"
|
|
107
|
+
sub "𑂦" "bha"
|
|
108
|
+
sub "𑂧" "ma"
|
|
109
|
+
sub "𑂨" "ya"
|
|
110
|
+
sub "𑂩" "ra"
|
|
111
|
+
sub "𑂪" "la"
|
|
112
|
+
sub "𑂫" "va"
|
|
113
|
+
sub "𑂬" "śa"
|
|
114
|
+
sub "𑂭" "ṣa"
|
|
115
|
+
sub "𑂮" "sa"
|
|
116
|
+
sub "𑂯" "ha"
|
|
117
|
+
}
|
|
118
|
+
|
|
119
|
+
compose
|
|
120
|
+
}
|
|
121
|
+
}
|