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 +1,231 @@
|
|
|
1
|
+
system "ISO:pra-Brah:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:pra
|
|
7
|
+
source_script Brah
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Prakrit (Brahmi); DIS stage)"
|
|
10
|
+
url https://www.iso.org/committee/48820.html
|
|
11
|
+
creation_date 2026
|
|
12
|
+
adoption_date 2026
|
|
13
|
+
description { Second edition (DIS stage) of ISO 15919, Transliteration of Indic scripts into Latin characters.
|
|
14
|
+
Encoded from the committee ballot ISO/TC 46/WG 3 N125; per-script tables of clause 7,
|
|
15
|
+
numerals of normative Annex A, Rule 17 Vedic accents, and options 9.8/9.9/9.10 as
|
|
16
|
+
selectable variants (languages opt98 opt99 opt10). See notes for provenance and errata. }
|
|
17
|
+
|
|
18
|
+
notes {
|
|
19
|
+
note "Encoded from ISO/DIS 15919 (2026), ISO/TC 46/WG 3 N125 (DIS stage draft, 2026-01-26), Table 7.11 plus the numerals of normative Annex A Table A.2; shared-table content verified against ISO/CD 15919 (2025, N108) and ISO 15919 WD (2024, N88). The DIS is not yet a published International Standard."
|
|
20
|
+
note "Rule 2 convention: inherent a with a consonant is always transliterated (consonant rows carry the inherent a)."
|
|
21
|
+
note "virama is deleted in the default behavior (clause 6 printed virama hex list); option 9.10 (language selector opt10) instead renders virama as middle dot U+00B7."
|
|
22
|
+
note "Option selectors (W3 languages, single-select): opt98 = clause 9.8 upper-case for all initial vowels (first letter capitalised for digraph outputs); opt99 = clause 9.9 unusual conjuncts marked with equals sign U+003D via the script's zero-width joiner; opt10 = clause 9.10 explicit virama middle dot. Option 9.1 (non-uniform e/o) is available by character substitution on outputs and is not separately staged."
|
|
23
|
+
note "Brahmi variants (clause 9.7): default variant encoded (virama 11046); Tamil variant virama 11070 and letter ḷa 11075 are also encoded as printed; Bhattiprolu variant (no virama) is not mechanically separable and is documented only."
|
|
24
|
+
}
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
languages opt98 opt99 opt10
|
|
28
|
+
|
|
29
|
+
tests {
|
|
30
|
+
"𑀅" -> "a"
|
|
31
|
+
"𑀓" -> "ka"
|
|
32
|
+
"𑀆" -> "ā"
|
|
33
|
+
"𑀸" -> "ā"
|
|
34
|
+
"𑀔" -> "kha"
|
|
35
|
+
"𑀇" -> "i"
|
|
36
|
+
"𑀺" -> "i"
|
|
37
|
+
"𑀕" -> "ga"
|
|
38
|
+
"𑀈" -> "ī"
|
|
39
|
+
"𑀻" -> "ī"
|
|
40
|
+
"𑀖" -> "gha"
|
|
41
|
+
"𑀉" -> "u"
|
|
42
|
+
"𑀼" -> "u"
|
|
43
|
+
"𑀗" -> "ṅa"
|
|
44
|
+
"𑀊" -> "ū"
|
|
45
|
+
"𑀽" -> "ū"
|
|
46
|
+
"𑀘" -> "ca"
|
|
47
|
+
"𑀋" -> "r̥"
|
|
48
|
+
"𑀾" -> "r̥"
|
|
49
|
+
"𑀙" -> "cha"
|
|
50
|
+
"𑀌" -> "r̥̄"
|
|
51
|
+
"𑀿" -> "r̥̄"
|
|
52
|
+
"𑀚" -> "ja"
|
|
53
|
+
"𑀍" -> "l̥"
|
|
54
|
+
"𑁀" -> "l̥"
|
|
55
|
+
"𑀛" -> "jha"
|
|
56
|
+
"𑀎" -> "l̥̄"
|
|
57
|
+
"𑁁" -> "l̥̄"
|
|
58
|
+
"𑀜" -> "ña"
|
|
59
|
+
"𑁱" -> "e"
|
|
60
|
+
"𑁳" -> "e"
|
|
61
|
+
"𑀝" -> "ṭa"
|
|
62
|
+
"𑀏" -> "ē"
|
|
63
|
+
"𑁂" -> "ē"
|
|
64
|
+
"𑀞" -> "ṭha"
|
|
65
|
+
"𑀐" -> "ai"
|
|
66
|
+
"𑁃" -> "ai"
|
|
67
|
+
"𑀟" -> "ḍa"
|
|
68
|
+
"𑁲" -> "o"
|
|
69
|
+
"𑁴" -> "o"
|
|
70
|
+
"𑀠" -> "ḍha"
|
|
71
|
+
"𑀑" -> "ō"
|
|
72
|
+
"𑁄" -> "ō"
|
|
73
|
+
"𑀡" -> "ṇa"
|
|
74
|
+
"𑀒" -> "au"
|
|
75
|
+
"𑁅" -> "au"
|
|
76
|
+
"𑀢" -> "ta"
|
|
77
|
+
"𑀰" -> "śa"
|
|
78
|
+
"𑀣" -> "tha"
|
|
79
|
+
"𑀱" -> "ṣa"
|
|
80
|
+
"𑀤" -> "da"
|
|
81
|
+
"𑀲" -> "sa"
|
|
82
|
+
"𑀥" -> "dha"
|
|
83
|
+
"𑀳" -> "ha"
|
|
84
|
+
"𑀦" -> "na"
|
|
85
|
+
"𑀴" -> "ḷa"
|
|
86
|
+
"𑀧" -> "pa"
|
|
87
|
+
"𑁵" -> "ḷa"
|
|
88
|
+
"𑀨" -> "pha"
|
|
89
|
+
"𑀵" -> "ḻa"
|
|
90
|
+
"𑀩" -> "ba"
|
|
91
|
+
"𑀶" -> "ṟa"
|
|
92
|
+
"𑀪" -> "bha"
|
|
93
|
+
"𑀷" -> "ṉa"
|
|
94
|
+
"𑀫" -> "ma"
|
|
95
|
+
"𑀬" -> "ya"
|
|
96
|
+
"𑀭" -> "ra"
|
|
97
|
+
"𑀮" -> "la"
|
|
98
|
+
"𑀃" -> "ẖ"
|
|
99
|
+
"𑀯" -> "va"
|
|
100
|
+
"𑀄" -> "ḫ"
|
|
101
|
+
"𑁦" -> "0"
|
|
102
|
+
"𑁧" -> "1"
|
|
103
|
+
"𑁨" -> "2"
|
|
104
|
+
"𑁩" -> "3"
|
|
105
|
+
"𑁪" -> "4"
|
|
106
|
+
"𑁫" -> "5"
|
|
107
|
+
"𑁬" -> "6"
|
|
108
|
+
"𑁭" -> "7"
|
|
109
|
+
"𑁮" -> "8"
|
|
110
|
+
"𑁯" -> "9"
|
|
111
|
+
"𑀀" -> "m̐"
|
|
112
|
+
"𑀁" -> "ṁ"
|
|
113
|
+
"𑀂" -> "ḥ"
|
|
114
|
+
}
|
|
115
|
+
|
|
116
|
+
stage main {
|
|
117
|
+
|
|
118
|
+
# Table 7.11 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
119
|
+
parallel {
|
|
120
|
+
|
|
121
|
+
sub "𑀅" "a"
|
|
122
|
+
sub "𑀅" "A" when opt98
|
|
123
|
+
sub "𑀓" "ka"
|
|
124
|
+
sub "𑀆" "ā"
|
|
125
|
+
sub "𑀸" "ā"
|
|
126
|
+
sub "𑀆" "Ā" when opt98
|
|
127
|
+
sub "𑀔" "kha"
|
|
128
|
+
sub "𑀇" "i"
|
|
129
|
+
sub "𑀺" "i"
|
|
130
|
+
sub "𑀇" "I" when opt98
|
|
131
|
+
sub "𑀕" "ga"
|
|
132
|
+
sub "𑀈" "ī"
|
|
133
|
+
sub "𑀻" "ī"
|
|
134
|
+
sub "𑀈" "Ī" when opt98
|
|
135
|
+
sub "𑀖" "gha"
|
|
136
|
+
sub "𑀉" "u"
|
|
137
|
+
sub "𑀼" "u"
|
|
138
|
+
sub "𑀉" "U" when opt98
|
|
139
|
+
sub "𑀗" "ṅa"
|
|
140
|
+
sub "𑀊" "ū"
|
|
141
|
+
sub "𑀽" "ū"
|
|
142
|
+
sub "𑀊" "Ū" when opt98
|
|
143
|
+
sub "𑀘" "ca"
|
|
144
|
+
sub "𑀋" "r̥"
|
|
145
|
+
sub "𑀾" "r̥"
|
|
146
|
+
sub "𑀋" "R̥" when opt98
|
|
147
|
+
sub "𑀙" "cha"
|
|
148
|
+
sub "𑀌" "r̥̄"
|
|
149
|
+
sub "𑀿" "r̥̄"
|
|
150
|
+
sub "𑀌" "R̥̄" when opt98
|
|
151
|
+
sub "𑀚" "ja"
|
|
152
|
+
sub "𑀍" "l̥"
|
|
153
|
+
sub "𑁀" "l̥"
|
|
154
|
+
sub "𑀍" "L̥" when opt98
|
|
155
|
+
sub "𑀛" "jha"
|
|
156
|
+
sub "𑀎" "l̥̄"
|
|
157
|
+
sub "𑁁" "l̥̄"
|
|
158
|
+
sub "𑀎" "L̥̄" when opt98
|
|
159
|
+
sub "𑀜" "ña"
|
|
160
|
+
sub "𑁱" "e"
|
|
161
|
+
sub "𑁳" "e"
|
|
162
|
+
sub "𑁱" "E" when opt98
|
|
163
|
+
sub "𑀝" "ṭa"
|
|
164
|
+
sub "𑀏" "ē"
|
|
165
|
+
sub "𑁂" "ē"
|
|
166
|
+
sub "𑀏" "Ē" when opt98
|
|
167
|
+
sub "𑀞" "ṭha"
|
|
168
|
+
sub "𑀐" "ai"
|
|
169
|
+
sub "𑁃" "ai"
|
|
170
|
+
sub "𑀐" "Ai" when opt98
|
|
171
|
+
sub "𑀟" "ḍa"
|
|
172
|
+
sub "𑁲" "o"
|
|
173
|
+
sub "𑁴" "o"
|
|
174
|
+
sub "𑁲" "O" when opt98
|
|
175
|
+
sub "𑀠" "ḍha"
|
|
176
|
+
sub "𑀑" "ō"
|
|
177
|
+
sub "𑁄" "ō"
|
|
178
|
+
sub "𑀑" "Ō" when opt98
|
|
179
|
+
sub "𑀡" "ṇa"
|
|
180
|
+
sub "𑀒" "au"
|
|
181
|
+
sub "𑁅" "au"
|
|
182
|
+
sub "𑀒" "Au" when opt98
|
|
183
|
+
sub "𑀢" "ta"
|
|
184
|
+
sub "𑀰" "śa"
|
|
185
|
+
sub "𑀣" "tha"
|
|
186
|
+
sub "𑀱" "ṣa"
|
|
187
|
+
sub "𑀤" "da"
|
|
188
|
+
sub "𑀲" "sa"
|
|
189
|
+
sub "𑀥" "dha"
|
|
190
|
+
sub "𑀳" "ha"
|
|
191
|
+
sub "𑀦" "na"
|
|
192
|
+
sub "𑀴" "ḷa"
|
|
193
|
+
sub "𑀧" "pa"
|
|
194
|
+
sub "𑁵" "ḷa"
|
|
195
|
+
sub "𑀨" "pha"
|
|
196
|
+
sub "𑀵" "ḻa"
|
|
197
|
+
sub "𑀩" "ba"
|
|
198
|
+
sub "𑀶" "ṟa"
|
|
199
|
+
sub "𑀪" "bha"
|
|
200
|
+
sub "𑀷" "ṉa"
|
|
201
|
+
sub "𑀫" "ma"
|
|
202
|
+
sub "𑀬" "ya"
|
|
203
|
+
sub "𑀭" "ra"
|
|
204
|
+
sub "𑀮" "la"
|
|
205
|
+
sub "𑀃" "ẖ"
|
|
206
|
+
sub "𑀯" "va"
|
|
207
|
+
sub "𑀄" "ḫ"
|
|
208
|
+
sub "𑀀" "m̐"
|
|
209
|
+
sub "𑀁" "ṁ"
|
|
210
|
+
sub "𑀂" "ḥ"
|
|
211
|
+
sub "𑁰" ""
|
|
212
|
+
sub "𑁰" "·" when opt10
|
|
213
|
+
sub "𑁆" ""
|
|
214
|
+
sub "𑁆" "·" when opt10
|
|
215
|
+
sub "" ""
|
|
216
|
+
sub "" "=" when opt99
|
|
217
|
+
sub "𑁦" "0"
|
|
218
|
+
sub "𑁧" "1"
|
|
219
|
+
sub "𑁨" "2"
|
|
220
|
+
sub "𑁩" "3"
|
|
221
|
+
sub "𑁪" "4"
|
|
222
|
+
sub "𑁫" "5"
|
|
223
|
+
sub "𑁬" "6"
|
|
224
|
+
sub "𑁭" "7"
|
|
225
|
+
sub "𑁮" "8"
|
|
226
|
+
sub "𑁯" "9"
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
compose
|
|
230
|
+
}
|
|
231
|
+
}
|
|
@@ -32,6 +32,7 @@ metadata {
|
|
|
32
32
|
note " A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n follows.\n - :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.\n - Vowel hiatus, not digraph transliteration of diphthongs; as in Sanskrit pra:uga (not prauga), “yoke”;"
|
|
33
33
|
note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
|
|
34
34
|
note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
|
|
35
|
+
note "Adjudicated against the published ISO 15919:2001 edition (owner-provided official PDF): Table 1 refs 003a and 003b print the Vedic accent letters jihvamuliya and upadhmaniya with the transliterations h with dot below + combining macron below (0068 0331) and h with dot below + combining breve below (0068 032E) - the single-character forms 1E96/1E2B are the second edition's Rule 17 values and are not used here. Table 1 ref 048a (eyelash ra, represented here by 0931 094D) prints r with breve, footnote c: used in Marathi and Nepali."
|
|
35
36
|
}
|
|
36
37
|
}
|
|
37
38
|
|
|
@@ -47,6 +48,7 @@ tests {
|
|
|
47
48
|
"पिता माताग्निरात्मा च गुरुश्च भरतर्षभ" -> "paitaā maātaāganairaātamaā ca gaurauśaca bharataraṣabha"
|
|
48
49
|
"पल्यालँ" -> "palayaām̐la"
|
|
49
50
|
"दुसूलँ" -> "dausaūm̐la"
|
|
51
|
+
"ऱ्" -> "r̆"
|
|
50
52
|
}
|
|
51
53
|
|
|
52
54
|
stage main {
|
|
@@ -124,8 +126,8 @@ stage main {
|
|
|
124
126
|
# Aspirate
|
|
125
127
|
sub "ह" "ha"
|
|
126
128
|
|
|
127
|
-
sub "ᳵ" "
|
|
128
|
-
sub "ᳶ" "
|
|
129
|
+
sub "ᳵ" "ḥ̱"
|
|
130
|
+
sub "ᳶ" "ḥ̮"
|
|
129
131
|
|
|
130
132
|
|
|
131
133
|
# Anusvāra
|
|
@@ -158,6 +160,7 @@ stage main {
|
|
|
158
160
|
sub "ॉ" "ô"
|
|
159
161
|
sub "ॅ" "ê"
|
|
160
162
|
|
|
163
|
+
sub "ऱ्" "r̆"
|
|
161
164
|
sub "्" ""
|
|
162
165
|
sub "" ""
|
|
163
166
|
|
|
@@ -0,0 +1,278 @@
|
|
|
1
|
+
system "ISO:san-Deva:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:san
|
|
7
|
+
source_script Deva
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Sanskrit; DIS stage)"
|
|
10
|
+
url https://www.iso.org/committee/48820.html
|
|
11
|
+
creation_date 2026
|
|
12
|
+
adoption_date 2026
|
|
13
|
+
description { Second edition (DIS stage) of ISO 15919, Transliteration of Indic scripts into Latin characters.
|
|
14
|
+
Encoded from the committee ballot ISO/TC 46/WG 3 N125; per-script tables of clause 7,
|
|
15
|
+
numerals of normative Annex A, Rule 17 Vedic accents, and options 9.8/9.9/9.10 as
|
|
16
|
+
selectable variants (languages opt98 opt99 opt10). See notes for provenance and errata. }
|
|
17
|
+
|
|
18
|
+
notes {
|
|
19
|
+
note "Encoded from ISO/DIS 15919 (2026), ISO/TC 46/WG 3 N125 (DIS stage draft, 2026-01-26), Table 7.1 plus the numerals of normative Annex A Table A.2; shared-table content verified against ISO/CD 15919 (2025, N108) and ISO 15919 WD (2024, N88). The DIS is not yet a published International Standard."
|
|
20
|
+
note "Rule 2 convention: inherent a with a consonant is always transliterated (consonant rows carry the inherent a)."
|
|
21
|
+
note "virama is deleted in the default behavior (clause 6 printed virama hex list); option 9.10 (language selector opt10) instead renders virama as middle dot U+00B7."
|
|
22
|
+
note "Option selectors (W3 languages, single-select): opt98 = clause 9.8 upper-case for all initial vowels (first letter capitalised for digraph outputs); opt99 = clause 9.9 unusual conjuncts marked with equals sign U+003D via the script's zero-width joiner; opt10 = clause 9.10 explicit virama middle dot. Option 9.1 (non-uniform e/o) is available by character substitution on outputs and is not separately staged."
|
|
23
|
+
note "Rule 17: the Vedic accents jihvamuliya (Hex 1CF5, Devanagari ᳵ) and upadhmaniya (Hex 1CF6, Devanagari ᳶ) are transliterated ẖ (Hex 1E96) and ḫ (Hex 1E2B). Table 7.1 itself does not print these rows (its NOTE defers Vedic accents to Rules 13 and 17 of 8.1), so they are encoded here from Rule 17. The r̆ rows cover the printed ṟa+virāma letter (0931 094D) and the ra+virāma+zero-width-joiner sequence of Table 7.1 footnote b (0930 094D 200D)."
|
|
24
|
+
note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 57/75 printed rows; systematic divergences recorded as findings, not fixes: vocalic r/l rows (corpus ṛ-family vs ISO r̥-family), long e/o rows (corpus e/o vs ISO ē/ō), avagraha (corpus :’ vs ISO ')."
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
languages opt98 opt99 opt10
|
|
29
|
+
|
|
30
|
+
tests {
|
|
31
|
+
"अ" -> "a"
|
|
32
|
+
"क" -> "ka"
|
|
33
|
+
"आ" -> "ā"
|
|
34
|
+
"ा" -> "ā"
|
|
35
|
+
"ख" -> "kha"
|
|
36
|
+
"इ" -> "i"
|
|
37
|
+
"ि" -> "i"
|
|
38
|
+
"ग" -> "ga"
|
|
39
|
+
"ई" -> "ī"
|
|
40
|
+
"ी" -> "ī"
|
|
41
|
+
"घ" -> "gha"
|
|
42
|
+
"उ" -> "u"
|
|
43
|
+
"ु" -> "u"
|
|
44
|
+
"ङ" -> "ṅa"
|
|
45
|
+
"ऊ" -> "ū"
|
|
46
|
+
"ू" -> "ū"
|
|
47
|
+
"च" -> "ca"
|
|
48
|
+
"ऋ" -> "r̥"
|
|
49
|
+
"ृ" -> "r̥"
|
|
50
|
+
"छ" -> "cha"
|
|
51
|
+
"ॠ" -> "r̥̄"
|
|
52
|
+
"ॄ" -> "r̥̄"
|
|
53
|
+
"ज" -> "ja"
|
|
54
|
+
"ऌ" -> "l̥"
|
|
55
|
+
"ॢ" -> "l̥"
|
|
56
|
+
"झ" -> "jha"
|
|
57
|
+
"ॡ" -> "l̥̄"
|
|
58
|
+
"ॣ" -> "l̥̄"
|
|
59
|
+
"ञ" -> "ña"
|
|
60
|
+
"ऎ" -> "e"
|
|
61
|
+
"ॆ" -> "e"
|
|
62
|
+
"ट" -> "ṭa"
|
|
63
|
+
"ए" -> "ē"
|
|
64
|
+
"े" -> "ē"
|
|
65
|
+
"ठ" -> "ṭha"
|
|
66
|
+
"ऐ" -> "ai"
|
|
67
|
+
"ै" -> "ai"
|
|
68
|
+
"ड" -> "ḍa"
|
|
69
|
+
"ऒ" -> "o"
|
|
70
|
+
"ॊ" -> "o"
|
|
71
|
+
"ढ" -> "ḍha"
|
|
72
|
+
"ओ" -> "ō"
|
|
73
|
+
"ो" -> "ō"
|
|
74
|
+
"ण" -> "ṇa"
|
|
75
|
+
"औ" -> "au"
|
|
76
|
+
"ौ" -> "au"
|
|
77
|
+
"ऩ" -> "ṉa"
|
|
78
|
+
"ऍ" -> "ê"
|
|
79
|
+
"ॅ" -> "ê"
|
|
80
|
+
"ऑ" -> "ô"
|
|
81
|
+
"ॉ" -> "ô"
|
|
82
|
+
"त" -> "ta"
|
|
83
|
+
"थ" -> "tha"
|
|
84
|
+
"द" -> "da"
|
|
85
|
+
"ध" -> "dha"
|
|
86
|
+
"न" -> "na"
|
|
87
|
+
"प" -> "pa"
|
|
88
|
+
"फ" -> "pha"
|
|
89
|
+
"ब" -> "ba"
|
|
90
|
+
"भ" -> "bha"
|
|
91
|
+
"म" -> "ma"
|
|
92
|
+
"य" -> "ya"
|
|
93
|
+
"य़" -> "ẏ"
|
|
94
|
+
"र" -> "ra"
|
|
95
|
+
"ऱ" -> "ṟa"
|
|
96
|
+
"ल" -> "la"
|
|
97
|
+
"ळ" -> "ḷa"
|
|
98
|
+
"ऴ" -> "ḻa"
|
|
99
|
+
"व" -> "va"
|
|
100
|
+
"श" -> "śa"
|
|
101
|
+
"ष" -> "ṣa"
|
|
102
|
+
"स" -> "sa"
|
|
103
|
+
"ह" -> "ha"
|
|
104
|
+
"क़" -> "qa"
|
|
105
|
+
"ख़" -> "k͟ha"
|
|
106
|
+
"ग़" -> "ġa"
|
|
107
|
+
"ज़" -> "za"
|
|
108
|
+
"ड़" -> "ṛa"
|
|
109
|
+
"ॹ" -> "źa"
|
|
110
|
+
"ढ़" -> "ṛha"
|
|
111
|
+
"फ़" -> "fa"
|
|
112
|
+
"ऱ्" -> "r̆"
|
|
113
|
+
"र्" -> "r̆"
|
|
114
|
+
"ं" -> "ṁ"
|
|
115
|
+
"ँ" -> "m̐"
|
|
116
|
+
"ः" -> "ḥ"
|
|
117
|
+
"ऽ" -> "'"
|
|
118
|
+
"ᳵ" -> "ẖ"
|
|
119
|
+
"ᳶ" -> "ḫ"
|
|
120
|
+
"०" -> "0"
|
|
121
|
+
"१" -> "1"
|
|
122
|
+
"२" -> "2"
|
|
123
|
+
"३" -> "3"
|
|
124
|
+
"४" -> "4"
|
|
125
|
+
"५" -> "5"
|
|
126
|
+
"६" -> "6"
|
|
127
|
+
"७" -> "7"
|
|
128
|
+
"८" -> "8"
|
|
129
|
+
"९" -> "9"
|
|
130
|
+
"य़" -> "ẏa"
|
|
131
|
+
"फ़" -> "fa"
|
|
132
|
+
"ढ़" -> "ṛha"
|
|
133
|
+
"ड़" -> "ṛa"
|
|
134
|
+
"ज़" -> "za"
|
|
135
|
+
"ग़" -> "ġa"
|
|
136
|
+
"ख़" -> "k͟ha"
|
|
137
|
+
"क़" -> "qa"
|
|
138
|
+
}
|
|
139
|
+
|
|
140
|
+
stage main {
|
|
141
|
+
|
|
142
|
+
# Table 7.1 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
143
|
+
parallel {
|
|
144
|
+
|
|
145
|
+
sub "अ" "a"
|
|
146
|
+
sub "अ" "A" when opt98
|
|
147
|
+
sub "क" "ka"
|
|
148
|
+
sub "आ" "ā"
|
|
149
|
+
sub "ा" "ā"
|
|
150
|
+
sub "आ" "Ā" when opt98
|
|
151
|
+
sub "ख" "kha"
|
|
152
|
+
sub "इ" "i"
|
|
153
|
+
sub "ि" "i"
|
|
154
|
+
sub "इ" "I" when opt98
|
|
155
|
+
sub "ग" "ga"
|
|
156
|
+
sub "ई" "ī"
|
|
157
|
+
sub "ी" "ī"
|
|
158
|
+
sub "ई" "Ī" when opt98
|
|
159
|
+
sub "घ" "gha"
|
|
160
|
+
sub "उ" "u"
|
|
161
|
+
sub "ु" "u"
|
|
162
|
+
sub "उ" "U" when opt98
|
|
163
|
+
sub "ङ" "ṅa"
|
|
164
|
+
sub "ऊ" "ū"
|
|
165
|
+
sub "ू" "ū"
|
|
166
|
+
sub "ऊ" "Ū" when opt98
|
|
167
|
+
sub "च" "ca"
|
|
168
|
+
sub "ऋ" "r̥"
|
|
169
|
+
sub "ृ" "r̥"
|
|
170
|
+
sub "ऋ" "R̥" when opt98
|
|
171
|
+
sub "छ" "cha"
|
|
172
|
+
sub "ॠ" "r̥̄"
|
|
173
|
+
sub "ॄ" "r̥̄"
|
|
174
|
+
sub "ॠ" "R̥̄" when opt98
|
|
175
|
+
sub "ज" "ja"
|
|
176
|
+
sub "ऌ" "l̥"
|
|
177
|
+
sub "ॢ" "l̥"
|
|
178
|
+
sub "ऌ" "L̥" when opt98
|
|
179
|
+
sub "झ" "jha"
|
|
180
|
+
sub "ॡ" "l̥̄"
|
|
181
|
+
sub "ॣ" "l̥̄"
|
|
182
|
+
sub "ॡ" "L̥̄" when opt98
|
|
183
|
+
sub "ञ" "ña"
|
|
184
|
+
sub "ऎ" "e"
|
|
185
|
+
sub "ॆ" "e"
|
|
186
|
+
sub "ऎ" "E" when opt98
|
|
187
|
+
sub "ट" "ṭa"
|
|
188
|
+
sub "ए" "ē"
|
|
189
|
+
sub "े" "ē"
|
|
190
|
+
sub "ए" "Ē" when opt98
|
|
191
|
+
sub "ठ" "ṭha"
|
|
192
|
+
sub "ऐ" "ai"
|
|
193
|
+
sub "ै" "ai"
|
|
194
|
+
sub "ऐ" "Ai" when opt98
|
|
195
|
+
sub "ड" "ḍa"
|
|
196
|
+
sub "ऒ" "o"
|
|
197
|
+
sub "ॊ" "o"
|
|
198
|
+
sub "ऒ" "O" when opt98
|
|
199
|
+
sub "ढ" "ḍha"
|
|
200
|
+
sub "ओ" "ō"
|
|
201
|
+
sub "ो" "ō"
|
|
202
|
+
sub "ओ" "Ō" when opt98
|
|
203
|
+
sub "ण" "ṇa"
|
|
204
|
+
sub "औ" "au"
|
|
205
|
+
sub "ौ" "au"
|
|
206
|
+
sub "औ" "Au" when opt98
|
|
207
|
+
sub "ऩ" "ṉa"
|
|
208
|
+
sub "ऍ" "ê"
|
|
209
|
+
sub "ॅ" "ê"
|
|
210
|
+
sub "ऍ" "Ê" when opt98
|
|
211
|
+
sub "ऑ" "ô"
|
|
212
|
+
sub "ॉ" "ô"
|
|
213
|
+
sub "ऑ" "Ô" when opt98
|
|
214
|
+
sub "त" "ta"
|
|
215
|
+
sub "थ" "tha"
|
|
216
|
+
sub "द" "da"
|
|
217
|
+
sub "ध" "dha"
|
|
218
|
+
sub "न" "na"
|
|
219
|
+
sub "प" "pa"
|
|
220
|
+
sub "फ" "pha"
|
|
221
|
+
sub "ब" "ba"
|
|
222
|
+
sub "भ" "bha"
|
|
223
|
+
sub "म" "ma"
|
|
224
|
+
sub "य" "ya"
|
|
225
|
+
sub "य़" "ẏ"
|
|
226
|
+
sub "य़" "ẏa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
227
|
+
sub "र" "ra"
|
|
228
|
+
sub "ऱ" "ṟa"
|
|
229
|
+
sub "ल" "la"
|
|
230
|
+
sub "ळ" "ḷa"
|
|
231
|
+
sub "ऴ" "ḻa"
|
|
232
|
+
sub "व" "va"
|
|
233
|
+
sub "श" "śa"
|
|
234
|
+
sub "ष" "ṣa"
|
|
235
|
+
sub "स" "sa"
|
|
236
|
+
sub "ह" "ha"
|
|
237
|
+
sub "क़" "qa"
|
|
238
|
+
sub "क़" "qa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
239
|
+
sub "ख़" "k͟ha"
|
|
240
|
+
sub "ख़" "k͟ha" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
241
|
+
sub "ग़" "ġa"
|
|
242
|
+
sub "ग़" "ġa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
243
|
+
sub "ज़" "za"
|
|
244
|
+
sub "ज़" "za" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
245
|
+
sub "ड़" "ṛa"
|
|
246
|
+
sub "ड़" "ṛa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
247
|
+
sub "ॹ" "źa"
|
|
248
|
+
sub "ढ़" "ṛha"
|
|
249
|
+
sub "ढ़" "ṛha" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
250
|
+
sub "फ़" "fa"
|
|
251
|
+
sub "फ़" "fa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
252
|
+
sub "ऱ्" "r̆" # Table 7.1 printed row: ṟa + virāma (0931 094D), footnote b
|
|
253
|
+
sub "र्" "r̆" # footnote b: implementations might also encounter ra + virāma + ZWJ (0930 094D 200D)
|
|
254
|
+
sub "ं" "ṁ" # Rules 3, 5, 8
|
|
255
|
+
sub "ँ" "m̐" # Rules 4, 5, 8
|
|
256
|
+
sub "ः" "ḥ"
|
|
257
|
+
sub "ऽ" "'" # Rule 15
|
|
258
|
+
sub "ᳵ" "ẖ" # Rule 17: jihvāmūlīya (Hex 1CF5) → ẖ (Hex 1E96)
|
|
259
|
+
sub "ᳶ" "ḫ" # Rule 17: upadhmānīya (Hex 1CF6) → ḫ (Hex 1E2B)
|
|
260
|
+
sub "्" ""
|
|
261
|
+
sub "्" "·" when opt10
|
|
262
|
+
sub "" ""
|
|
263
|
+
sub "" "=" when opt99
|
|
264
|
+
sub "०" "0"
|
|
265
|
+
sub "१" "1"
|
|
266
|
+
sub "२" "2"
|
|
267
|
+
sub "३" "3"
|
|
268
|
+
sub "४" "4"
|
|
269
|
+
sub "५" "5"
|
|
270
|
+
sub "६" "6"
|
|
271
|
+
sub "७" "7"
|
|
272
|
+
sub "८" "8"
|
|
273
|
+
sub "९" "9"
|
|
274
|
+
}
|
|
275
|
+
|
|
276
|
+
compose
|
|
277
|
+
}
|
|
278
|
+
}
|