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 +1,208 @@
|
|
|
1
|
+
system "ISO:san-Gran:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:san
|
|
7
|
+
source_script Gran
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Sanskrit (Grantha); 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 7.12 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
|
+
}
|
|
24
|
+
}
|
|
25
|
+
|
|
26
|
+
languages opt98 opt99 opt10
|
|
27
|
+
|
|
28
|
+
tests {
|
|
29
|
+
"𑌅" -> "a"
|
|
30
|
+
"𑌕" -> "ka"
|
|
31
|
+
"𑌆" -> "ā"
|
|
32
|
+
"𑌾" -> "ā"
|
|
33
|
+
"𑌖" -> "kha"
|
|
34
|
+
"𑌇" -> "i"
|
|
35
|
+
"𑌿" -> "i"
|
|
36
|
+
"𑌗" -> "ga"
|
|
37
|
+
"𑌈" -> "ī"
|
|
38
|
+
"𑍀" -> "ī"
|
|
39
|
+
"𑌘" -> "gha"
|
|
40
|
+
"𑌉" -> "u"
|
|
41
|
+
"𑍁" -> "u"
|
|
42
|
+
"𑌙" -> "ṅa"
|
|
43
|
+
"𑌊" -> "ū"
|
|
44
|
+
"𑍂" -> "ū"
|
|
45
|
+
"𑌚" -> "ca"
|
|
46
|
+
"𑌋" -> "r̥"
|
|
47
|
+
"𑍃" -> "r̥"
|
|
48
|
+
"𑌛" -> "cha"
|
|
49
|
+
"𑍠" -> "r̥̄"
|
|
50
|
+
"𑍄" -> "r̥̄"
|
|
51
|
+
"𑌜" -> "ja"
|
|
52
|
+
"𑌌" -> "l̥"
|
|
53
|
+
"𑍢" -> "l̥"
|
|
54
|
+
"𑌝" -> "jha"
|
|
55
|
+
"𑍡" -> "l̥̄"
|
|
56
|
+
"𑍣" -> "l̥̄"
|
|
57
|
+
"𑌞" -> "ña"
|
|
58
|
+
"𑌏" -> "ē"
|
|
59
|
+
"𑍇" -> "ē"
|
|
60
|
+
"𑌟" -> "ṭa"
|
|
61
|
+
"𑌐" -> "ai"
|
|
62
|
+
"𑍈" -> "ai"
|
|
63
|
+
"𑌠" -> "ṭha"
|
|
64
|
+
"𑌓" -> "ō"
|
|
65
|
+
"𑍋" -> "ō"
|
|
66
|
+
"𑌡" -> "ḍa"
|
|
67
|
+
"𑌔" -> "au"
|
|
68
|
+
"𑍌" -> "au"
|
|
69
|
+
"𑌢" -> "ḍha"
|
|
70
|
+
"𑌤" -> "ta"
|
|
71
|
+
"𑌯" -> "ya"
|
|
72
|
+
"𑌥" -> "tha"
|
|
73
|
+
"𑌰" -> "ra"
|
|
74
|
+
"𑌦" -> "da"
|
|
75
|
+
"𑌲" -> "la"
|
|
76
|
+
"𑌧" -> "dha"
|
|
77
|
+
"𑌵" -> "va"
|
|
78
|
+
"𑌨" -> "na"
|
|
79
|
+
"𑌶" -> "śa"
|
|
80
|
+
"𑌪" -> "pa"
|
|
81
|
+
"𑌷" -> "ṣa"
|
|
82
|
+
"𑌫" -> "pha"
|
|
83
|
+
"𑌸" -> "sa"
|
|
84
|
+
"𑌬" -> "ba"
|
|
85
|
+
"𑌹" -> "ha"
|
|
86
|
+
"𑌭" -> "bha"
|
|
87
|
+
"𑌳" -> "ḷa"
|
|
88
|
+
"𑌮" -> "ma"
|
|
89
|
+
"௦" -> "0"
|
|
90
|
+
"௧" -> "1"
|
|
91
|
+
"௨" -> "2"
|
|
92
|
+
"௩" -> "3"
|
|
93
|
+
"௪" -> "4"
|
|
94
|
+
"௫" -> "5"
|
|
95
|
+
"௬" -> "6"
|
|
96
|
+
"௭" -> "7"
|
|
97
|
+
"௮" -> "8"
|
|
98
|
+
"௯" -> "9"
|
|
99
|
+
"𑌣" -> "ṇa"
|
|
100
|
+
"𑌀" -> "ṁ"
|
|
101
|
+
"𑌁" -> "m̐"
|
|
102
|
+
"𑌃" -> "ḥ"
|
|
103
|
+
"𑌽" -> "'"
|
|
104
|
+
}
|
|
105
|
+
|
|
106
|
+
stage main {
|
|
107
|
+
|
|
108
|
+
# Table 7.12 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
109
|
+
parallel {
|
|
110
|
+
|
|
111
|
+
sub "𑌅" "a"
|
|
112
|
+
sub "𑌅" "A" when opt98
|
|
113
|
+
sub "𑌕" "ka"
|
|
114
|
+
sub "𑌆" "ā"
|
|
115
|
+
sub "𑌾" "ā"
|
|
116
|
+
sub "𑌆" "Ā" when opt98
|
|
117
|
+
sub "𑌖" "kha"
|
|
118
|
+
sub "𑌇" "i"
|
|
119
|
+
sub "𑌿" "i"
|
|
120
|
+
sub "𑌇" "I" when opt98
|
|
121
|
+
sub "𑌗" "ga"
|
|
122
|
+
sub "𑌈" "ī"
|
|
123
|
+
sub "𑍀" "ī"
|
|
124
|
+
sub "𑌈" "Ī" when opt98
|
|
125
|
+
sub "𑌘" "gha"
|
|
126
|
+
sub "𑌉" "u"
|
|
127
|
+
sub "𑍁" "u"
|
|
128
|
+
sub "𑌉" "U" when opt98
|
|
129
|
+
sub "𑌙" "ṅa"
|
|
130
|
+
sub "𑌊" "ū"
|
|
131
|
+
sub "𑍂" "ū"
|
|
132
|
+
sub "𑌊" "Ū" when opt98
|
|
133
|
+
sub "𑌚" "ca"
|
|
134
|
+
sub "𑌋" "r̥"
|
|
135
|
+
sub "𑍃" "r̥"
|
|
136
|
+
sub "𑌋" "R̥" when opt98
|
|
137
|
+
sub "𑌛" "cha"
|
|
138
|
+
sub "𑍠" "r̥̄"
|
|
139
|
+
sub "𑍄" "r̥̄"
|
|
140
|
+
sub "𑍠" "R̥̄" when opt98
|
|
141
|
+
sub "𑌜" "ja"
|
|
142
|
+
sub "𑌌" "l̥"
|
|
143
|
+
sub "𑍢" "l̥"
|
|
144
|
+
sub "𑌌" "L̥" when opt98
|
|
145
|
+
sub "𑌝" "jha"
|
|
146
|
+
sub "𑍡" "l̥̄"
|
|
147
|
+
sub "𑍣" "l̥̄"
|
|
148
|
+
sub "𑍡" "L̥̄" when opt98
|
|
149
|
+
sub "𑌞" "ña"
|
|
150
|
+
sub "𑌏" "ē"
|
|
151
|
+
sub "𑍇" "ē"
|
|
152
|
+
sub "𑌏" "Ē" when opt98
|
|
153
|
+
sub "𑌟" "ṭa"
|
|
154
|
+
sub "𑌐" "ai"
|
|
155
|
+
sub "𑍈" "ai"
|
|
156
|
+
sub "𑌐" "Ai" when opt98
|
|
157
|
+
sub "𑌠" "ṭha"
|
|
158
|
+
sub "𑌓" "ō"
|
|
159
|
+
sub "𑍋" "ō"
|
|
160
|
+
sub "𑌓" "Ō" when opt98
|
|
161
|
+
sub "𑌡" "ḍa"
|
|
162
|
+
sub "𑌔" "au"
|
|
163
|
+
sub "𑍌" "au"
|
|
164
|
+
sub "𑌔" "Au" when opt98
|
|
165
|
+
sub "𑌢" "ḍha"
|
|
166
|
+
sub "𑌣" "ṇa"
|
|
167
|
+
sub "𑌤" "ta"
|
|
168
|
+
sub "𑌯" "ya"
|
|
169
|
+
sub "𑌥" "tha"
|
|
170
|
+
sub "𑌰" "ra"
|
|
171
|
+
sub "𑌦" "da"
|
|
172
|
+
sub "𑌲" "la"
|
|
173
|
+
sub "𑌧" "dha"
|
|
174
|
+
sub "𑌵" "va"
|
|
175
|
+
sub "𑌨" "na"
|
|
176
|
+
sub "𑌶" "śa"
|
|
177
|
+
sub "𑌪" "pa"
|
|
178
|
+
sub "𑌷" "ṣa"
|
|
179
|
+
sub "𑌫" "pha"
|
|
180
|
+
sub "𑌸" "sa"
|
|
181
|
+
sub "𑌬" "ba"
|
|
182
|
+
sub "𑌹" "ha"
|
|
183
|
+
sub "𑌭" "bha"
|
|
184
|
+
sub "𑌳" "ḷa"
|
|
185
|
+
sub "𑌮" "ma"
|
|
186
|
+
sub "𑌀" "ṁ"
|
|
187
|
+
sub "𑌁" "m̐"
|
|
188
|
+
sub "𑌃" "ḥ"
|
|
189
|
+
sub "𑌽" "'" # avagraha
|
|
190
|
+
sub "𑍍" ""
|
|
191
|
+
sub "𑍍" "·" when opt10
|
|
192
|
+
sub "" ""
|
|
193
|
+
sub "" "=" when opt99
|
|
194
|
+
sub "௦" "0"
|
|
195
|
+
sub "௧" "1"
|
|
196
|
+
sub "௨" "2"
|
|
197
|
+
sub "௩" "3"
|
|
198
|
+
sub "௪" "4"
|
|
199
|
+
sub "௫" "5"
|
|
200
|
+
sub "௬" "6"
|
|
201
|
+
sub "௭" "7"
|
|
202
|
+
sub "௮" "8"
|
|
203
|
+
sub "௯" "9"
|
|
204
|
+
}
|
|
205
|
+
|
|
206
|
+
compose
|
|
207
|
+
}
|
|
208
|
+
}
|
|
@@ -0,0 +1,174 @@
|
|
|
1
|
+
system "ISO:sin-Sinh:Latn:15919-2001" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2001
|
|
6
|
+
language iso-639-2:sin
|
|
7
|
+
source_script Sinh
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Sinhala)"
|
|
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 (Sinhala is covered by the first edition; the 2001 Sinhala nukta characters and Pali-language rules are not printed in the transcription source and are therefore not encoded)."
|
|
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 Sinhala cell is encoded and embedded as a test row."
|
|
20
|
+
note "Verification: every encoded value agrees with ISO/DIS 15919 (2026) Table 7.10 shared content (N125; also N108 CD 2025, N88 WD 2024)."
|
|
21
|
+
note "Cross-check (audit axis) vs corpus map iso-pli-Sinh-Latn-15919-2001: 51/60 printed rows agree; divergent families recorded as findings, not fixes: vocalic rows (corpus ṛ/ṝ/ḻ/ḹ vs ISO r̥/r̥̄/l̥/l̥̄ per the blessed source and DIS Table 7.10), prenasalized consonants (corpus bare clusters vs ISO n̆-marked forms), and the corpus candrabindu rows built on Gujarati U+0A81."
|
|
22
|
+
note "Vowel-sign (mātrā) rows are structural: each sign carries the value of its printed independent vowel row; no invented Latin values."
|
|
23
|
+
note "Adjudicated against the published ISO 15919:2001 edition: Table 10 refs 141-144 print the vocalic vowels with ring below (r, r + macron, l, l + macron), confirming the encoded values; refs 159/166/172/179/185 print the prenasalized letters with n/m breve forms, matching the encoded values. The official table's Pali-usage alternative readings (refs 159a, 166a, 172a, 179a, 185a: nga, nja, nda-nasal, nda, mba as full sequences) are context-dependent renderings of the same letters and are not separately encodable; the official table's three Tamil-used letters (refs 197a, 187a, 177a) have no Unicode characters and cannot be encoded as inputs."
|
|
24
|
+
}
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
tests {
|
|
28
|
+
"අ" -> "a"
|
|
29
|
+
"ආ" -> "ā"
|
|
30
|
+
"ඇ" -> "æ"
|
|
31
|
+
"ඈ" -> "ǣ"
|
|
32
|
+
"ඉ" -> "i"
|
|
33
|
+
"ඊ" -> "ī"
|
|
34
|
+
"උ" -> "u"
|
|
35
|
+
"ඌ" -> "ū"
|
|
36
|
+
"ඍ" -> "r̥"
|
|
37
|
+
"ඎ" -> "r̥̄"
|
|
38
|
+
"ඏ" -> "l̥"
|
|
39
|
+
"ඐ" -> "l̥̄"
|
|
40
|
+
"එ" -> "e"
|
|
41
|
+
"ඒ" -> "ē"
|
|
42
|
+
"ඓ" -> "ai"
|
|
43
|
+
"ඔ" -> "o"
|
|
44
|
+
"ඕ" -> "ō"
|
|
45
|
+
"ඖ" -> "au"
|
|
46
|
+
"ං" -> "ṁ"
|
|
47
|
+
"ඃ" -> "ḥ"
|
|
48
|
+
"ක" -> "ka"
|
|
49
|
+
"ඛ" -> "kha"
|
|
50
|
+
"ග" -> "ga"
|
|
51
|
+
"ඝ" -> "gha"
|
|
52
|
+
"ඞ" -> "ṅa"
|
|
53
|
+
"ඟ" -> "n̆ga"
|
|
54
|
+
"ච" -> "ca"
|
|
55
|
+
"ඡ" -> "cha"
|
|
56
|
+
"ජ" -> "ja"
|
|
57
|
+
"ඣ" -> "jha"
|
|
58
|
+
"ඤ" -> "ña"
|
|
59
|
+
"ඦ" -> "n̆ja"
|
|
60
|
+
"ට" -> "ṭa"
|
|
61
|
+
"ඨ" -> "ṭha"
|
|
62
|
+
"ඩ" -> "ḍa"
|
|
63
|
+
"ඪ" -> "ḍha"
|
|
64
|
+
"ණ" -> "ṇa"
|
|
65
|
+
"ඬ" -> "n̆ḍa"
|
|
66
|
+
"ත" -> "ta"
|
|
67
|
+
"ථ" -> "tha"
|
|
68
|
+
"ද" -> "da"
|
|
69
|
+
"ධ" -> "dha"
|
|
70
|
+
"න" -> "na"
|
|
71
|
+
"ඳ" -> "n̆da"
|
|
72
|
+
"ප" -> "pa"
|
|
73
|
+
"ඵ" -> "pha"
|
|
74
|
+
"බ" -> "ba"
|
|
75
|
+
"භ" -> "bha"
|
|
76
|
+
"ම" -> "ma"
|
|
77
|
+
"ඹ" -> "m̆ba"
|
|
78
|
+
"ය" -> "ya"
|
|
79
|
+
"ර" -> "ra"
|
|
80
|
+
"ල" -> "la"
|
|
81
|
+
"ළ" -> "ḷa"
|
|
82
|
+
"ව" -> "va"
|
|
83
|
+
"ශ" -> "śa"
|
|
84
|
+
"ෂ" -> "ṣa"
|
|
85
|
+
"ස" -> "sa"
|
|
86
|
+
"හ" -> "ha"
|
|
87
|
+
"ෆ" -> "fa"
|
|
88
|
+
}
|
|
89
|
+
|
|
90
|
+
stage main {
|
|
91
|
+
|
|
92
|
+
parallel {
|
|
93
|
+
sub "අ" "a"
|
|
94
|
+
sub "ආ" "ā"
|
|
95
|
+
sub "ඇ" "æ"
|
|
96
|
+
sub "ඈ" "ǣ"
|
|
97
|
+
sub "ඉ" "i"
|
|
98
|
+
sub "ඊ" "ī"
|
|
99
|
+
sub "උ" "u"
|
|
100
|
+
sub "ඌ" "ū"
|
|
101
|
+
sub "ඍ" "r̥"
|
|
102
|
+
sub "ඎ" "r̥̄"
|
|
103
|
+
sub "ඏ" "l̥"
|
|
104
|
+
sub "ඐ" "l̥̄"
|
|
105
|
+
sub "එ" "e"
|
|
106
|
+
sub "ඒ" "ē"
|
|
107
|
+
sub "ඓ" "ai"
|
|
108
|
+
sub "ඔ" "o"
|
|
109
|
+
sub "ඕ" "ō"
|
|
110
|
+
sub "ඖ" "au"
|
|
111
|
+
sub "ං" "ṁ"
|
|
112
|
+
sub "ඃ" "ḥ"
|
|
113
|
+
sub "ක" "ka"
|
|
114
|
+
sub "ඛ" "kha"
|
|
115
|
+
sub "ග" "ga"
|
|
116
|
+
sub "ඝ" "gha"
|
|
117
|
+
sub "ඞ" "ṅa"
|
|
118
|
+
sub "ඟ" "n̆ga"
|
|
119
|
+
sub "ච" "ca"
|
|
120
|
+
sub "ඡ" "cha"
|
|
121
|
+
sub "ජ" "ja"
|
|
122
|
+
sub "ඣ" "jha"
|
|
123
|
+
sub "ඤ" "ña"
|
|
124
|
+
sub "ඦ" "n̆ja"
|
|
125
|
+
sub "ට" "ṭa"
|
|
126
|
+
sub "ඨ" "ṭha"
|
|
127
|
+
sub "ඩ" "ḍa"
|
|
128
|
+
sub "ඪ" "ḍha"
|
|
129
|
+
sub "ණ" "ṇa"
|
|
130
|
+
sub "ඬ" "n̆ḍa"
|
|
131
|
+
sub "ත" "ta"
|
|
132
|
+
sub "ථ" "tha"
|
|
133
|
+
sub "ද" "da"
|
|
134
|
+
sub "ධ" "dha"
|
|
135
|
+
sub "න" "na"
|
|
136
|
+
sub "ඳ" "n̆da"
|
|
137
|
+
sub "ප" "pa"
|
|
138
|
+
sub "ඵ" "pha"
|
|
139
|
+
sub "බ" "ba"
|
|
140
|
+
sub "භ" "bha"
|
|
141
|
+
sub "ම" "ma"
|
|
142
|
+
sub "ඹ" "m̆ba"
|
|
143
|
+
sub "ය" "ya"
|
|
144
|
+
sub "ර" "ra"
|
|
145
|
+
sub "ල" "la"
|
|
146
|
+
sub "ළ" "ḷa"
|
|
147
|
+
sub "ව" "va"
|
|
148
|
+
sub "ශ" "śa"
|
|
149
|
+
sub "ෂ" "ṣa"
|
|
150
|
+
sub "ස" "sa"
|
|
151
|
+
sub "හ" "ha"
|
|
152
|
+
sub "ෆ" "fa"
|
|
153
|
+
sub "ා" "ā"
|
|
154
|
+
sub "ැ" "æ"
|
|
155
|
+
sub "ෑ" "ǣ"
|
|
156
|
+
sub "ි" "i"
|
|
157
|
+
sub "ී" "ī"
|
|
158
|
+
sub "ු" "u"
|
|
159
|
+
sub "ූ" "ū"
|
|
160
|
+
sub "ෘ" "r̥"
|
|
161
|
+
sub "ෲ" "r̥̄"
|
|
162
|
+
sub "ෟ" "l̥"
|
|
163
|
+
sub "ෳ" "l̥̄"
|
|
164
|
+
sub "ෙ" "e"
|
|
165
|
+
sub "ේ" "ē"
|
|
166
|
+
sub "ෛ" "ai"
|
|
167
|
+
sub "ො" "o"
|
|
168
|
+
sub "ෝ" "ō"
|
|
169
|
+
sub "ෞ" "au"
|
|
170
|
+
}
|
|
171
|
+
|
|
172
|
+
compose
|
|
173
|
+
}
|
|
174
|
+
}
|
|
@@ -0,0 +1,238 @@
|
|
|
1
|
+
system "ISO:sin-Sinh:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:sin
|
|
7
|
+
source_script Sinh
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Sinhala; 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 7.10 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 "Cross-check: all Table 7.10 cells agree with the owner-blessed Wikipedia ISO 15919 table; agreement with the corpus Pali-scoped map iso-pli-Sinh-Latn-15919-2001: 51/60 of printed rows, divergent families recorded as findings (vocalics ṛ-family vs r̥-family; prenasalized bare vs n̆-marked)."
|
|
24
|
+
note "Row-level source errata encoded per printed text: Table 7.10 row ['ඦ']: latin/hex mismatch: text='n̆ja' hex=006E 0306 0067"
|
|
25
|
+
}
|
|
26
|
+
}
|
|
27
|
+
|
|
28
|
+
languages opt98 opt99 opt10
|
|
29
|
+
|
|
30
|
+
tests {
|
|
31
|
+
"අ" -> "a"
|
|
32
|
+
"ක" -> "ka"
|
|
33
|
+
"ආ" -> "ā"
|
|
34
|
+
"ා" -> "ā"
|
|
35
|
+
"ඛ" -> "kha"
|
|
36
|
+
"ඇ" -> "æ"
|
|
37
|
+
"ැ" -> "æ"
|
|
38
|
+
"ග" -> "ga"
|
|
39
|
+
"ඈ" -> "ǣ"
|
|
40
|
+
"ෑ" -> "ǣ"
|
|
41
|
+
"ඝ" -> "gha"
|
|
42
|
+
"ඉ" -> "i"
|
|
43
|
+
"ි" -> "i"
|
|
44
|
+
"ඞ" -> "ṅa"
|
|
45
|
+
"ඊ" -> "ī"
|
|
46
|
+
"ී" -> "ī"
|
|
47
|
+
"ඟ" -> "n̆ga"
|
|
48
|
+
"උ" -> "u"
|
|
49
|
+
"ු" -> "u"
|
|
50
|
+
"ච" -> "ca"
|
|
51
|
+
"ඌ" -> "ū"
|
|
52
|
+
"ූ" -> "ū"
|
|
53
|
+
"ඡ" -> "cha"
|
|
54
|
+
"ඍ" -> "r̥"
|
|
55
|
+
"ෘ" -> "r̥"
|
|
56
|
+
"ජ" -> "ja"
|
|
57
|
+
"ඎ" -> "r̥̄"
|
|
58
|
+
"ෲ" -> "r̥̄"
|
|
59
|
+
"ඣ" -> "jha"
|
|
60
|
+
"ඏ" -> "l̥"
|
|
61
|
+
"ෟ" -> "l̥"
|
|
62
|
+
"ඤ" -> "ña"
|
|
63
|
+
"ඐ" -> "l̥̄"
|
|
64
|
+
"ෳ" -> "l̥̄"
|
|
65
|
+
"ඦ" -> "n̆ja"
|
|
66
|
+
"එ" -> "e"
|
|
67
|
+
"ෙ" -> "e"
|
|
68
|
+
"ට" -> "ṭa"
|
|
69
|
+
"ඒ" -> "ē"
|
|
70
|
+
"ේ" -> "ē"
|
|
71
|
+
"ඨ" -> "ṭha"
|
|
72
|
+
"ඓ" -> "ai"
|
|
73
|
+
"ෛ" -> "ai"
|
|
74
|
+
"ඩ" -> "ḍa"
|
|
75
|
+
"ඔ" -> "o"
|
|
76
|
+
"ො" -> "o"
|
|
77
|
+
"ඪ" -> "ḍha"
|
|
78
|
+
"ඕ" -> "ō"
|
|
79
|
+
"ෝ" -> "ō"
|
|
80
|
+
"ණ" -> "ṇa"
|
|
81
|
+
"ඖ" -> "au"
|
|
82
|
+
"ෞ" -> "au"
|
|
83
|
+
"ඬ" -> "n̆ḍa"
|
|
84
|
+
"ත" -> "ta"
|
|
85
|
+
"ශ" -> "śa"
|
|
86
|
+
"ථ" -> "tha"
|
|
87
|
+
"ෂ" -> "ṣa"
|
|
88
|
+
"ද" -> "da"
|
|
89
|
+
"ස" -> "sa"
|
|
90
|
+
"ධ" -> "dha"
|
|
91
|
+
"හ" -> "ha"
|
|
92
|
+
"න" -> "na"
|
|
93
|
+
"ළ" -> "ḷa"
|
|
94
|
+
"ඳ" -> "n̆da"
|
|
95
|
+
"ෆ" -> "fa"
|
|
96
|
+
"ප" -> "pa"
|
|
97
|
+
"ං" -> "ṁ"
|
|
98
|
+
"ඵ" -> "pha"
|
|
99
|
+
"ඃ" -> "ḥ"
|
|
100
|
+
"බ" -> "ba"
|
|
101
|
+
"භ" -> "bha"
|
|
102
|
+
"ම" -> "ma"
|
|
103
|
+
"ඹ" -> "m̆ba"
|
|
104
|
+
"ය" -> "ya"
|
|
105
|
+
"ර" -> "ra"
|
|
106
|
+
"ල" -> "la"
|
|
107
|
+
"ව" -> "va"
|
|
108
|
+
"෦" -> "0"
|
|
109
|
+
"෧" -> "1"
|
|
110
|
+
"෨" -> "2"
|
|
111
|
+
"෩" -> "3"
|
|
112
|
+
"෪" -> "4"
|
|
113
|
+
"෫" -> "5"
|
|
114
|
+
"෬" -> "6"
|
|
115
|
+
"෭" -> "7"
|
|
116
|
+
"෮" -> "8"
|
|
117
|
+
"෯" -> "9"
|
|
118
|
+
}
|
|
119
|
+
|
|
120
|
+
stage main {
|
|
121
|
+
|
|
122
|
+
# Table 7.10 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
123
|
+
parallel {
|
|
124
|
+
|
|
125
|
+
sub "අ" "a"
|
|
126
|
+
sub "අ" "A" when opt98
|
|
127
|
+
sub "ක" "ka"
|
|
128
|
+
sub "ආ" "ā"
|
|
129
|
+
sub "ා" "ā"
|
|
130
|
+
sub "ආ" "Ā" when opt98
|
|
131
|
+
sub "ඛ" "kha"
|
|
132
|
+
sub "ඇ" "æ"
|
|
133
|
+
sub "ැ" "æ"
|
|
134
|
+
sub "ඇ" "Æ" when opt98
|
|
135
|
+
sub "ග" "ga"
|
|
136
|
+
sub "ඈ" "ǣ"
|
|
137
|
+
sub "ෑ" "ǣ"
|
|
138
|
+
sub "ඈ" "Ǣ" when opt98
|
|
139
|
+
sub "ඝ" "gha"
|
|
140
|
+
sub "ඉ" "i"
|
|
141
|
+
sub "ි" "i"
|
|
142
|
+
sub "ඉ" "I" when opt98
|
|
143
|
+
sub "ඞ" "ṅa"
|
|
144
|
+
sub "ඊ" "ī"
|
|
145
|
+
sub "ී" "ī"
|
|
146
|
+
sub "ඊ" "Ī" when opt98
|
|
147
|
+
sub "ඟ" "n̆ga"
|
|
148
|
+
sub "උ" "u"
|
|
149
|
+
sub "ු" "u"
|
|
150
|
+
sub "උ" "U" when opt98
|
|
151
|
+
sub "ච" "ca"
|
|
152
|
+
sub "ඌ" "ū"
|
|
153
|
+
sub "ූ" "ū"
|
|
154
|
+
sub "ඌ" "Ū" when opt98
|
|
155
|
+
sub "ඡ" "cha"
|
|
156
|
+
sub "ඍ" "r̥"
|
|
157
|
+
sub "ෘ" "r̥"
|
|
158
|
+
sub "ඍ" "R̥" when opt98
|
|
159
|
+
sub "ජ" "ja"
|
|
160
|
+
sub "ඎ" "r̥̄"
|
|
161
|
+
sub "ෲ" "r̥̄"
|
|
162
|
+
sub "ඎ" "R̥̄" when opt98
|
|
163
|
+
sub "ඣ" "jha"
|
|
164
|
+
sub "ඏ" "l̥"
|
|
165
|
+
sub "ෟ" "l̥"
|
|
166
|
+
sub "ඏ" "L̥" when opt98
|
|
167
|
+
sub "ඤ" "ña"
|
|
168
|
+
sub "ඐ" "l̥̄"
|
|
169
|
+
sub "ෳ" "l̥̄"
|
|
170
|
+
sub "ඐ" "L̥̄" when opt98
|
|
171
|
+
sub "ඦ" "n̆ja"
|
|
172
|
+
sub "එ" "e"
|
|
173
|
+
sub "ෙ" "e"
|
|
174
|
+
sub "එ" "E" when opt98
|
|
175
|
+
sub "ට" "ṭa"
|
|
176
|
+
sub "ඒ" "ē"
|
|
177
|
+
sub "ේ" "ē"
|
|
178
|
+
sub "ඒ" "Ē" when opt98
|
|
179
|
+
sub "ඨ" "ṭha"
|
|
180
|
+
sub "ඓ" "ai"
|
|
181
|
+
sub "ෛ" "ai"
|
|
182
|
+
sub "ඓ" "Ai" when opt98
|
|
183
|
+
sub "ඩ" "ḍa"
|
|
184
|
+
sub "ඔ" "o"
|
|
185
|
+
sub "ො" "o"
|
|
186
|
+
sub "ඔ" "O" when opt98
|
|
187
|
+
sub "ඪ" "ḍha"
|
|
188
|
+
sub "ඕ" "ō"
|
|
189
|
+
sub "ෝ" "ō"
|
|
190
|
+
sub "ඕ" "Ō" when opt98
|
|
191
|
+
sub "ණ" "ṇa"
|
|
192
|
+
sub "ඖ" "au"
|
|
193
|
+
sub "ෞ" "au"
|
|
194
|
+
sub "ඖ" "Au" when opt98
|
|
195
|
+
sub "ඬ" "n̆ḍa"
|
|
196
|
+
sub "ත" "ta"
|
|
197
|
+
sub "ශ" "śa"
|
|
198
|
+
sub "ථ" "tha"
|
|
199
|
+
sub "ෂ" "ṣa"
|
|
200
|
+
sub "ද" "da"
|
|
201
|
+
sub "ස" "sa"
|
|
202
|
+
sub "ධ" "dha"
|
|
203
|
+
sub "හ" "ha"
|
|
204
|
+
sub "න" "na"
|
|
205
|
+
sub "ළ" "ḷa"
|
|
206
|
+
sub "ඳ" "n̆da"
|
|
207
|
+
sub "ෆ" "fa"
|
|
208
|
+
sub "ප" "pa"
|
|
209
|
+
sub "ං" "ṁ"
|
|
210
|
+
sub "ඵ" "pha"
|
|
211
|
+
sub "ඃ" "ḥ"
|
|
212
|
+
sub "බ" "ba"
|
|
213
|
+
sub "භ" "bha"
|
|
214
|
+
sub "ම" "ma"
|
|
215
|
+
sub "ඹ" "m̆ba"
|
|
216
|
+
sub "ය" "ya"
|
|
217
|
+
sub "ර" "ra"
|
|
218
|
+
sub "ල" "la"
|
|
219
|
+
sub "ව" "va"
|
|
220
|
+
sub "්" ""
|
|
221
|
+
sub "්" "·" when opt10
|
|
222
|
+
sub "" ""
|
|
223
|
+
sub "" "=" when opt99
|
|
224
|
+
sub "෦" "0"
|
|
225
|
+
sub "෧" "1"
|
|
226
|
+
sub "෨" "2"
|
|
227
|
+
sub "෩" "3"
|
|
228
|
+
sub "෪" "4"
|
|
229
|
+
sub "෫" "5"
|
|
230
|
+
sub "෬" "6"
|
|
231
|
+
sub "෭" "7"
|
|
232
|
+
sub "෮" "8"
|
|
233
|
+
sub "෯" "9"
|
|
234
|
+
}
|
|
235
|
+
|
|
236
|
+
compose
|
|
237
|
+
}
|
|
238
|
+
}
|
|
@@ -33,6 +33,7 @@ metadata {
|
|
|
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 "Numerals in Tamil scripts shall be converted into decimal notation on transliteration, where\n necessary."
|
|
35
35
|
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."
|
|
36
|
+
note "Adjudicated against the published ISO 15919:2001 edition: Table 6 prints no Tamil anusvara (U+0B82) row and neither does the second edition's Table 7.6; the anusvara row seen in modern secondary transcriptions is out of scope and is not encoded. The official Tamil special rows (refs 177, 169, 180, 131) are all encoded."
|
|
36
37
|
}
|
|
37
38
|
}
|
|
38
39
|
|