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 +1,221 @@
|
|
|
1
|
+
system "ISO:new-Newa:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:new
|
|
7
|
+
source_script Newa
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Newar (Newa); 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 7.17 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 "DIS errata recorded: Table 7.17 row NGHA 11413 prints Hex '1445 0324 0067' (leading typo) and row NYHA 11419 prints Hex '00F1 0324 0067' while both Latin text cells read n̤a (n + U+0324 + a); the Latin text is encoded. NGHA, NYHA and NHA 11424 all print n̤a (colliding outputs, as printed)."
|
|
24
|
+
note "Row-level source errata encoded per printed text: Table 7.17 row ['𑐓']: latin/hex mismatch: text='n̤a' hex=1445 0324 0067 | Table 7.17 row ['𑐙']: latin/hex mismatch: text='n̤a' hex=00F1 0324 0067 | Table 7.17 row ['𑐯']: latin/hex mismatch: text='l̤a' hex=006C 0324"
|
|
25
|
+
note "Row LLA 1142F is encoded l̤a (006C 0324 0061), matching the printed Latin cell's mark order like the other under-diaeresis rows."
|
|
26
|
+
}
|
|
27
|
+
}
|
|
28
|
+
|
|
29
|
+
languages opt98 opt99 opt10
|
|
30
|
+
|
|
31
|
+
tests {
|
|
32
|
+
"𑐀" -> "a"
|
|
33
|
+
"𑐎" -> "ka"
|
|
34
|
+
"𑐁" -> "ā"
|
|
35
|
+
"𑐵" -> "ā"
|
|
36
|
+
"𑐏" -> "kha"
|
|
37
|
+
"𑐂" -> "i"
|
|
38
|
+
"𑐶" -> "i"
|
|
39
|
+
"𑐐" -> "ga"
|
|
40
|
+
"𑐃" -> "ī"
|
|
41
|
+
"𑐷" -> "ī"
|
|
42
|
+
"𑐑" -> "gha"
|
|
43
|
+
"𑐄" -> "u"
|
|
44
|
+
"𑐸" -> "u"
|
|
45
|
+
"𑐒" -> "ṅa"
|
|
46
|
+
"𑐅" -> "ū"
|
|
47
|
+
"𑐹" -> "ū"
|
|
48
|
+
"𑐓" -> "n̤a"
|
|
49
|
+
"𑐆" -> "r̥"
|
|
50
|
+
"𑐺" -> "r̥"
|
|
51
|
+
"𑐔" -> "ca"
|
|
52
|
+
"𑐇" -> "r̥̄"
|
|
53
|
+
"𑐻" -> "r̥̄"
|
|
54
|
+
"𑐕" -> "cha"
|
|
55
|
+
"𑐈" -> "l̥"
|
|
56
|
+
"𑐼" -> "l̥"
|
|
57
|
+
"𑐖" -> "ja"
|
|
58
|
+
"𑐉" -> "l̥̄"
|
|
59
|
+
"𑐽" -> "l̥̄"
|
|
60
|
+
"𑐗" -> "jha"
|
|
61
|
+
"𑐊" -> "ē"
|
|
62
|
+
"𑐾" -> "ē"
|
|
63
|
+
"𑐘" -> "ña"
|
|
64
|
+
"𑐋" -> "ai"
|
|
65
|
+
"𑐿" -> "ai"
|
|
66
|
+
"𑐙" -> "n̤a"
|
|
67
|
+
"𑐌" -> "ō"
|
|
68
|
+
"𑑀" -> "ō"
|
|
69
|
+
"𑐚" -> "ṭa"
|
|
70
|
+
"𑐍" -> "au"
|
|
71
|
+
"𑑁" -> "au"
|
|
72
|
+
"𑐛" -> "ṭha"
|
|
73
|
+
"𑐟" -> "ta"
|
|
74
|
+
"𑐬" -> "ra"
|
|
75
|
+
"𑐠" -> "tha"
|
|
76
|
+
"𑐭" -> "r̤a"
|
|
77
|
+
"𑐡" -> "da"
|
|
78
|
+
"𑐮" -> "la"
|
|
79
|
+
"𑐢" -> "dha"
|
|
80
|
+
"𑐯" -> "l̤a"
|
|
81
|
+
"𑐣" -> "na"
|
|
82
|
+
"𑐰" -> "va"
|
|
83
|
+
"𑐤" -> "n̤a"
|
|
84
|
+
"𑐱" -> "śa"
|
|
85
|
+
"𑐥" -> "pa"
|
|
86
|
+
"𑐲" -> "ṣa"
|
|
87
|
+
"𑐦" -> "pha"
|
|
88
|
+
"𑐳" -> "sa"
|
|
89
|
+
"𑐧" -> "ba"
|
|
90
|
+
"𑐴" -> "ha"
|
|
91
|
+
"𑐨" -> "bha"
|
|
92
|
+
"𑑄" -> "ṁ"
|
|
93
|
+
"𑐩" -> "ma"
|
|
94
|
+
"𑑃" -> "m̐"
|
|
95
|
+
"𑐪" -> "m̤a"
|
|
96
|
+
"𑑅" -> "ḥ"
|
|
97
|
+
"𑐫" -> "ya"
|
|
98
|
+
"𑑇" -> "'"
|
|
99
|
+
"𑑐" -> "0"
|
|
100
|
+
"𑑑" -> "1"
|
|
101
|
+
"𑑒" -> "2"
|
|
102
|
+
"𑑓" -> "3"
|
|
103
|
+
"𑑔" -> "4"
|
|
104
|
+
"𑑕" -> "5"
|
|
105
|
+
"𑑖" -> "6"
|
|
106
|
+
"𑑗" -> "7"
|
|
107
|
+
"𑑘" -> "8"
|
|
108
|
+
"𑑙" -> "9"
|
|
109
|
+
"𑐜" -> "ḍa"
|
|
110
|
+
"𑐝" -> "ḍha"
|
|
111
|
+
"𑐞" -> "ṇa"
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
stage main {
|
|
115
|
+
|
|
116
|
+
# Table 7.17 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
117
|
+
parallel {
|
|
118
|
+
|
|
119
|
+
sub "𑐀" "a"
|
|
120
|
+
sub "𑐀" "A" when opt98
|
|
121
|
+
sub "𑐎" "ka"
|
|
122
|
+
sub "𑐁" "ā"
|
|
123
|
+
sub "𑐵" "ā"
|
|
124
|
+
sub "𑐁" "Ā" when opt98
|
|
125
|
+
sub "𑐏" "kha"
|
|
126
|
+
sub "𑐂" "i"
|
|
127
|
+
sub "𑐶" "i"
|
|
128
|
+
sub "𑐂" "I" when opt98
|
|
129
|
+
sub "𑐐" "ga"
|
|
130
|
+
sub "𑐃" "ī"
|
|
131
|
+
sub "𑐷" "ī"
|
|
132
|
+
sub "𑐃" "Ī" when opt98
|
|
133
|
+
sub "𑐑" "gha"
|
|
134
|
+
sub "𑐄" "u"
|
|
135
|
+
sub "𑐸" "u"
|
|
136
|
+
sub "𑐄" "U" when opt98
|
|
137
|
+
sub "𑐒" "ṅa"
|
|
138
|
+
sub "𑐅" "ū"
|
|
139
|
+
sub "𑐹" "ū"
|
|
140
|
+
sub "𑐅" "Ū" when opt98
|
|
141
|
+
sub "𑐓" "n̤a"
|
|
142
|
+
sub "𑐆" "r̥"
|
|
143
|
+
sub "𑐺" "r̥"
|
|
144
|
+
sub "𑐆" "R̥" when opt98
|
|
145
|
+
sub "𑐔" "ca"
|
|
146
|
+
sub "𑐇" "r̥̄"
|
|
147
|
+
sub "𑐻" "r̥̄"
|
|
148
|
+
sub "𑐇" "R̥̄" when opt98
|
|
149
|
+
sub "𑐕" "cha"
|
|
150
|
+
sub "𑐈" "l̥"
|
|
151
|
+
sub "𑐼" "l̥"
|
|
152
|
+
sub "𑐈" "L̥" when opt98
|
|
153
|
+
sub "𑐖" "ja"
|
|
154
|
+
sub "𑐉" "l̥̄"
|
|
155
|
+
sub "𑐽" "l̥̄"
|
|
156
|
+
sub "𑐉" "L̥̄" when opt98
|
|
157
|
+
sub "𑐗" "jha"
|
|
158
|
+
sub "𑐊" "ē"
|
|
159
|
+
sub "𑐾" "ē"
|
|
160
|
+
sub "𑐊" "Ē" when opt98
|
|
161
|
+
sub "𑐘" "ña"
|
|
162
|
+
sub "𑐋" "ai"
|
|
163
|
+
sub "𑐿" "ai"
|
|
164
|
+
sub "𑐋" "Ai" when opt98
|
|
165
|
+
sub "𑐙" "n̤a"
|
|
166
|
+
sub "𑐌" "ō"
|
|
167
|
+
sub "𑑀" "ō"
|
|
168
|
+
sub "𑐌" "Ō" when opt98
|
|
169
|
+
sub "𑐚" "ṭa"
|
|
170
|
+
sub "𑐍" "au"
|
|
171
|
+
sub "𑑁" "au"
|
|
172
|
+
sub "𑐍" "Au" when opt98
|
|
173
|
+
sub "𑐛" "ṭha"
|
|
174
|
+
sub "𑐟" "ta"
|
|
175
|
+
sub "𑐬" "ra"
|
|
176
|
+
sub "𑐠" "tha"
|
|
177
|
+
sub "𑐭" "r̤a"
|
|
178
|
+
sub "𑐡" "da"
|
|
179
|
+
sub "𑐮" "la"
|
|
180
|
+
sub "𑐢" "dha"
|
|
181
|
+
sub "𑐯" "l̤a"
|
|
182
|
+
sub "𑐣" "na"
|
|
183
|
+
sub "𑐜" "ḍa"
|
|
184
|
+
sub "𑐰" "va"
|
|
185
|
+
sub "𑐤" "n̤a"
|
|
186
|
+
sub "𑐱" "śa"
|
|
187
|
+
sub "𑐥" "pa"
|
|
188
|
+
sub "𑐲" "ṣa"
|
|
189
|
+
sub "𑐦" "pha"
|
|
190
|
+
sub "𑐳" "sa"
|
|
191
|
+
sub "𑐧" "ba"
|
|
192
|
+
sub "𑐴" "ha"
|
|
193
|
+
sub "𑐨" "bha"
|
|
194
|
+
sub "𑑄" "ṁ"
|
|
195
|
+
sub "𑐩" "ma"
|
|
196
|
+
sub "𑑃" "m̐"
|
|
197
|
+
sub "𑐪" "m̤a"
|
|
198
|
+
sub "𑑅" "ḥ"
|
|
199
|
+
sub "𑐫" "ya"
|
|
200
|
+
sub "𑑇" "'"
|
|
201
|
+
sub "𑐝" "ḍha"
|
|
202
|
+
sub "𑐞" "ṇa"
|
|
203
|
+
sub "𑑂" ""
|
|
204
|
+
sub "𑑂" "·" when opt10
|
|
205
|
+
sub "" ""
|
|
206
|
+
sub "" "=" when opt99
|
|
207
|
+
sub "𑑐" "0"
|
|
208
|
+
sub "𑑑" "1"
|
|
209
|
+
sub "𑑒" "2"
|
|
210
|
+
sub "𑑓" "3"
|
|
211
|
+
sub "𑑔" "4"
|
|
212
|
+
sub "𑑕" "5"
|
|
213
|
+
sub "𑑖" "6"
|
|
214
|
+
sub "𑑗" "7"
|
|
215
|
+
sub "𑑘" "8"
|
|
216
|
+
sub "𑑙" "9"
|
|
217
|
+
}
|
|
218
|
+
|
|
219
|
+
compose
|
|
220
|
+
}
|
|
221
|
+
}
|
|
@@ -0,0 +1,222 @@
|
|
|
1
|
+
system "ISO:ori-Orya:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:ori
|
|
7
|
+
source_script Orya
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Odia; 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 7.5 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 "DIS clause 6 erratum recorded: printed Ori. 084D (Samarak); corrected to Odia virama 0B4D."
|
|
24
|
+
note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 49/56 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
|
+
"ଅ" -> "a"
|
|
32
|
+
"କ" -> "ka"
|
|
33
|
+
"ଆ" -> "ā"
|
|
34
|
+
"ା" -> "ā"
|
|
35
|
+
"ଖ" -> "kha"
|
|
36
|
+
"ଇ" -> "i"
|
|
37
|
+
"ି" -> "i"
|
|
38
|
+
"ଗ" -> "ga"
|
|
39
|
+
"ଈ" -> "ī"
|
|
40
|
+
"ୀ" -> "ī"
|
|
41
|
+
"ଘ" -> "gha"
|
|
42
|
+
"ଉ" -> "u"
|
|
43
|
+
"ୁ" -> "u"
|
|
44
|
+
"ଙ" -> "ṅa"
|
|
45
|
+
"ଊ" -> "ū"
|
|
46
|
+
"ୂ" -> "ū"
|
|
47
|
+
"ଚ" -> "ca"
|
|
48
|
+
"ଋ" -> "r̥"
|
|
49
|
+
"ୃ" -> "r̥"
|
|
50
|
+
"ଛ" -> "cha"
|
|
51
|
+
"ୠ" -> "r̥̄"
|
|
52
|
+
"ୄ" -> "r̥̄"
|
|
53
|
+
"ଜ" -> "ja"
|
|
54
|
+
"ଌ" -> "l̥"
|
|
55
|
+
"ୢ" -> "l̥"
|
|
56
|
+
"ଝ" -> "jha"
|
|
57
|
+
"ୡ" -> "l̥̄"
|
|
58
|
+
"ୣ" -> "l̥̄"
|
|
59
|
+
"ଞ" -> "ña"
|
|
60
|
+
"ଏ" -> "ē"
|
|
61
|
+
"େ" -> "ē"
|
|
62
|
+
"ଟ" -> "ṭa"
|
|
63
|
+
"ଐ" -> "ai"
|
|
64
|
+
"ୈ" -> "ai"
|
|
65
|
+
"ଠ" -> "ṭha"
|
|
66
|
+
"ଓ" -> "ō"
|
|
67
|
+
"ୋ" -> "ō"
|
|
68
|
+
"ଡ" -> "ḍa"
|
|
69
|
+
"ଔ" -> "au"
|
|
70
|
+
"ୌ" -> "au"
|
|
71
|
+
"ଢ" -> "ḍha"
|
|
72
|
+
"ତ" -> "ta"
|
|
73
|
+
"ଶ" -> "śa"
|
|
74
|
+
"ଥ" -> "tha"
|
|
75
|
+
"ଷ" -> "ṣa"
|
|
76
|
+
"ଦ" -> "da"
|
|
77
|
+
"ସ" -> "sa"
|
|
78
|
+
"ଧ" -> "dha"
|
|
79
|
+
"ହ" -> "ha"
|
|
80
|
+
"ନ" -> "na"
|
|
81
|
+
"ଡ଼" -> "ṛa"
|
|
82
|
+
"ପ" -> "pa"
|
|
83
|
+
"ଢ଼" -> "ṛha"
|
|
84
|
+
"ଫ" -> "pha"
|
|
85
|
+
"ଳ" -> "ḷa"
|
|
86
|
+
"ବ" -> "ba"
|
|
87
|
+
"ଵ" -> "va"
|
|
88
|
+
"ଭ" -> "bha"
|
|
89
|
+
"ୱ" -> "wa"
|
|
90
|
+
"ମ" -> "ma"
|
|
91
|
+
"ଂ" -> "ṁ"
|
|
92
|
+
"ଯ" -> "ya"
|
|
93
|
+
"ଁ" -> "m̐"
|
|
94
|
+
"ୟ" -> "ẏa"
|
|
95
|
+
"ଃ" -> "ḥ"
|
|
96
|
+
"ର" -> "ra"
|
|
97
|
+
"ଽ" -> "'"
|
|
98
|
+
"ଲ" -> "la"
|
|
99
|
+
"୦" -> "0"
|
|
100
|
+
"୧" -> "1"
|
|
101
|
+
"୨" -> "2"
|
|
102
|
+
"୩" -> "3"
|
|
103
|
+
"୪" -> "4"
|
|
104
|
+
"୫" -> "5"
|
|
105
|
+
"୬" -> "6"
|
|
106
|
+
"୭" -> "7"
|
|
107
|
+
"୮" -> "8"
|
|
108
|
+
"୯" -> "9"
|
|
109
|
+
"ଣ" -> "ṇa"
|
|
110
|
+
"ଡ଼" -> "ṛa"
|
|
111
|
+
"ଢ଼" -> "ṛha"
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
stage main {
|
|
115
|
+
|
|
116
|
+
# Table 7.5 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
117
|
+
parallel {
|
|
118
|
+
|
|
119
|
+
sub "ଅ" "a"
|
|
120
|
+
sub "ଅ" "A" when opt98
|
|
121
|
+
sub "କ" "ka"
|
|
122
|
+
sub "ଆ" "ā"
|
|
123
|
+
sub "ା" "ā"
|
|
124
|
+
sub "ଆ" "Ā" when opt98
|
|
125
|
+
sub "ଖ" "kha"
|
|
126
|
+
sub "ଇ" "i"
|
|
127
|
+
sub "ି" "i"
|
|
128
|
+
sub "ଇ" "I" when opt98
|
|
129
|
+
sub "ଗ" "ga"
|
|
130
|
+
sub "ଈ" "ī"
|
|
131
|
+
sub "ୀ" "ī"
|
|
132
|
+
sub "ଈ" "Ī" when opt98
|
|
133
|
+
sub "ଘ" "gha"
|
|
134
|
+
sub "ଉ" "u"
|
|
135
|
+
sub "ୁ" "u"
|
|
136
|
+
sub "ଉ" "U" when opt98
|
|
137
|
+
sub "ଙ" "ṅa"
|
|
138
|
+
sub "ଊ" "ū"
|
|
139
|
+
sub "ୂ" "ū"
|
|
140
|
+
sub "ଊ" "Ū" when opt98
|
|
141
|
+
sub "ଚ" "ca"
|
|
142
|
+
sub "ଋ" "r̥"
|
|
143
|
+
sub "ୃ" "r̥"
|
|
144
|
+
sub "ଋ" "R̥" when opt98
|
|
145
|
+
sub "ଛ" "cha"
|
|
146
|
+
sub "ୠ" "r̥̄"
|
|
147
|
+
sub "ୄ" "r̥̄"
|
|
148
|
+
sub "ୠ" "R̥̄" when opt98
|
|
149
|
+
sub "ଜ" "ja"
|
|
150
|
+
sub "ଌ" "l̥"
|
|
151
|
+
sub "ୢ" "l̥"
|
|
152
|
+
sub "ଌ" "L̥" when opt98
|
|
153
|
+
sub "ଝ" "jha"
|
|
154
|
+
sub "ୡ" "l̥̄"
|
|
155
|
+
sub "ୣ" "l̥̄"
|
|
156
|
+
sub "ୡ" "L̥̄" when opt98
|
|
157
|
+
sub "ଞ" "ña"
|
|
158
|
+
sub "ଏ" "ē"
|
|
159
|
+
sub "େ" "ē"
|
|
160
|
+
sub "ଏ" "Ē" when opt98
|
|
161
|
+
sub "ଟ" "ṭa"
|
|
162
|
+
sub "ଐ" "ai"
|
|
163
|
+
sub "ୈ" "ai"
|
|
164
|
+
sub "ଐ" "Ai" when opt98
|
|
165
|
+
sub "ଠ" "ṭha"
|
|
166
|
+
sub "ଓ" "ō"
|
|
167
|
+
sub "ୋ" "ō"
|
|
168
|
+
sub "ଓ" "Ō" when opt98
|
|
169
|
+
sub "ଡ" "ḍa"
|
|
170
|
+
sub "ଔ" "au"
|
|
171
|
+
sub "ୌ" "au"
|
|
172
|
+
sub "ଔ" "Au" when opt98
|
|
173
|
+
sub "ଢ" "ḍha"
|
|
174
|
+
sub "ଣ" "ṇa"
|
|
175
|
+
sub "ତ" "ta"
|
|
176
|
+
sub "ଶ" "śa"
|
|
177
|
+
sub "ଥ" "tha"
|
|
178
|
+
sub "ଷ" "ṣa"
|
|
179
|
+
sub "ଦ" "da"
|
|
180
|
+
sub "ସ" "sa"
|
|
181
|
+
sub "ଧ" "dha"
|
|
182
|
+
sub "ହ" "ha"
|
|
183
|
+
sub "ନ" "na"
|
|
184
|
+
sub "ଡ଼" "ṛa"
|
|
185
|
+
sub "ପ" "pa"
|
|
186
|
+
sub "ଢ଼" "ṛha"
|
|
187
|
+
sub "ଫ" "pha"
|
|
188
|
+
sub "ଳ" "ḷa"
|
|
189
|
+
sub "ବ" "ba"
|
|
190
|
+
sub "ଵ" "va"
|
|
191
|
+
sub "ଭ" "bha"
|
|
192
|
+
sub "ୱ" "wa"
|
|
193
|
+
sub "ମ" "ma"
|
|
194
|
+
sub "ଂ" "ṁ"
|
|
195
|
+
sub "ଯ" "ya"
|
|
196
|
+
sub "ଁ" "m̐"
|
|
197
|
+
sub "ୟ" "ẏa"
|
|
198
|
+
sub "ଃ" "ḥ"
|
|
199
|
+
sub "ର" "ra"
|
|
200
|
+
sub "ଽ" "'"
|
|
201
|
+
sub "ଲ" "la"
|
|
202
|
+
sub "ଡ଼" "ṛa"
|
|
203
|
+
sub "ଢ଼" "ṛha"
|
|
204
|
+
sub "୍" ""
|
|
205
|
+
sub "୍" "·" when opt10
|
|
206
|
+
sub "" ""
|
|
207
|
+
sub "" "=" when opt99
|
|
208
|
+
sub "୦" "0"
|
|
209
|
+
sub "୧" "1"
|
|
210
|
+
sub "୨" "2"
|
|
211
|
+
sub "୩" "3"
|
|
212
|
+
sub "୪" "4"
|
|
213
|
+
sub "୫" "5"
|
|
214
|
+
sub "୬" "6"
|
|
215
|
+
sub "୭" "7"
|
|
216
|
+
sub "୮" "8"
|
|
217
|
+
sub "୯" "9"
|
|
218
|
+
}
|
|
219
|
+
|
|
220
|
+
compose
|
|
221
|
+
}
|
|
222
|
+
}
|
|
@@ -0,0 +1,222 @@
|
|
|
1
|
+
system "ISO:pan-Guru:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:pan
|
|
7
|
+
source_script Guru
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Punjabi (Gurmukhi); 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 7.3 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 "Adhak U+0A71 (clause 6 note): before an aspirated stop it indicates insertion of the unaspirated stop; elsewhere it doubles the following consonant. This is context-dependent and outside the substitution IR; no Latin value is printed for it in Table 7.3."
|
|
24
|
+
note "DIS erratum recorded: Table 7.3 row ja+nukta (0A5B) prints Latin 'za' with Hex 1E63 (contradiction); the Latin text 'za' is encoded."
|
|
25
|
+
note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 48/54 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 ')."
|
|
26
|
+
note "Row-level source errata encoded per printed text: Table 7.3 row ['ਜ਼']: latin/hex mismatch: text='za' hex=1E63"
|
|
27
|
+
note "The precomposed nukta letters 0A33 0A36 0A59 0A5A 0A5B 0A5E are encoded alongside their decomposed combinations (clause 7.3: precomposed and decomposed characters are treated equally on input); the printed qa row is the combination 0A15 0A3C."
|
|
28
|
+
}
|
|
29
|
+
}
|
|
30
|
+
|
|
31
|
+
languages opt98 opt99 opt10
|
|
32
|
+
|
|
33
|
+
tests {
|
|
34
|
+
"ਅ" -> "a"
|
|
35
|
+
"ਚ" -> "ca"
|
|
36
|
+
"ਆ" -> "ā"
|
|
37
|
+
"ਾ" -> "ā"
|
|
38
|
+
"ਛ" -> "cha"
|
|
39
|
+
"ਇ" -> "i"
|
|
40
|
+
"ਿ" -> "i"
|
|
41
|
+
"ਜ" -> "ja"
|
|
42
|
+
"ਈ" -> "ī"
|
|
43
|
+
"ੀ" -> "ī"
|
|
44
|
+
"ਝ" -> "jha"
|
|
45
|
+
"ਉ" -> "u"
|
|
46
|
+
"ੁ" -> "u"
|
|
47
|
+
"ਞ" -> "ña"
|
|
48
|
+
"ਊ" -> "ū"
|
|
49
|
+
"ੂ" -> "ū"
|
|
50
|
+
"ਟ" -> "ṭa"
|
|
51
|
+
"ਏ" -> "ē"
|
|
52
|
+
"ੇ" -> "ē"
|
|
53
|
+
"ਠ" -> "ṭha"
|
|
54
|
+
"ਐ" -> "ai"
|
|
55
|
+
"ੈ" -> "ai"
|
|
56
|
+
"ਡ" -> "ḍa"
|
|
57
|
+
"ਓ" -> "ō"
|
|
58
|
+
"ੋ" -> "ō"
|
|
59
|
+
"ਢ" -> "ḍha"
|
|
60
|
+
"ਔ" -> "au"
|
|
61
|
+
"ੌ" -> "au"
|
|
62
|
+
"ਣ" -> "ṇa"
|
|
63
|
+
"ਸ" -> "sa"
|
|
64
|
+
"ਤ" -> "ta"
|
|
65
|
+
"ਹ" -> "ha"
|
|
66
|
+
"ਥ" -> "tha"
|
|
67
|
+
"ਕ" -> "ka"
|
|
68
|
+
"ਦ" -> "da"
|
|
69
|
+
"ਖ" -> "kha"
|
|
70
|
+
"ਧ" -> "dha"
|
|
71
|
+
"ਗ" -> "ga"
|
|
72
|
+
"ਨ" -> "na"
|
|
73
|
+
"ਘ" -> "gha"
|
|
74
|
+
"ਙ" -> "ṅa"
|
|
75
|
+
"ਪ" -> "pa"
|
|
76
|
+
"ਸ਼" -> "śa"
|
|
77
|
+
"ਫ" -> "pha"
|
|
78
|
+
"ਖ਼" -> "k͟ha"
|
|
79
|
+
"ਬ" -> "ba"
|
|
80
|
+
"ਗ਼" -> "ġa"
|
|
81
|
+
"ਭ" -> "bha"
|
|
82
|
+
"ਜ਼" -> "za"
|
|
83
|
+
"ਮ" -> "ma"
|
|
84
|
+
"ਫ਼" -> "fa"
|
|
85
|
+
"ਯ" -> "ya"
|
|
86
|
+
"ਰ" -> "ra"
|
|
87
|
+
"ਂ" -> "ṁ"
|
|
88
|
+
"ਲ" -> "la"
|
|
89
|
+
"ੰ" -> "ṃ"
|
|
90
|
+
"ਲ਼" -> "ḷa"
|
|
91
|
+
"ਁ" -> "m̐"
|
|
92
|
+
"ਵ" -> "va"
|
|
93
|
+
"ਃ" -> "ḥ"
|
|
94
|
+
"ੜ" -> "ṛa"
|
|
95
|
+
"੦" -> "0"
|
|
96
|
+
"੧" -> "1"
|
|
97
|
+
"੨" -> "2"
|
|
98
|
+
"੩" -> "3"
|
|
99
|
+
"੪" -> "4"
|
|
100
|
+
"੫" -> "5"
|
|
101
|
+
"੬" -> "6"
|
|
102
|
+
"੭" -> "7"
|
|
103
|
+
"੮" -> "8"
|
|
104
|
+
"੯" -> "9"
|
|
105
|
+
"ਲ਼" -> "ḷa"
|
|
106
|
+
"ਸ਼" -> "śa"
|
|
107
|
+
"ਖ਼" -> "k͟ha"
|
|
108
|
+
"ਗ਼" -> "ġa"
|
|
109
|
+
"ਜ਼" -> "za"
|
|
110
|
+
"ਫ਼" -> "fa"
|
|
111
|
+
"ਕ਼" -> "qa"
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
stage main {
|
|
115
|
+
|
|
116
|
+
# Table 7.3 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
117
|
+
parallel {
|
|
118
|
+
|
|
119
|
+
sub "ਅ" "a"
|
|
120
|
+
sub "ਅ" "A" when opt98
|
|
121
|
+
sub "ਚ" "ca"
|
|
122
|
+
sub "ਆ" "ā"
|
|
123
|
+
sub "ਾ" "ā"
|
|
124
|
+
sub "ਆ" "Ā" when opt98
|
|
125
|
+
sub "ਛ" "cha"
|
|
126
|
+
sub "ਇ" "i"
|
|
127
|
+
sub "ਿ" "i"
|
|
128
|
+
sub "ਇ" "I" when opt98
|
|
129
|
+
sub "ਜ" "ja"
|
|
130
|
+
sub "ਈ" "ī"
|
|
131
|
+
sub "ੀ" "ī"
|
|
132
|
+
sub "ਈ" "Ī" when opt98
|
|
133
|
+
sub "ਝ" "jha"
|
|
134
|
+
sub "ਉ" "u"
|
|
135
|
+
sub "ੁ" "u"
|
|
136
|
+
sub "ਉ" "U" when opt98
|
|
137
|
+
sub "ਞ" "ña"
|
|
138
|
+
sub "ਊ" "ū"
|
|
139
|
+
sub "ੂ" "ū"
|
|
140
|
+
sub "ਊ" "Ū" when opt98
|
|
141
|
+
sub "ਟ" "ṭa"
|
|
142
|
+
sub "ਏ" "ē"
|
|
143
|
+
sub "ੇ" "ē"
|
|
144
|
+
sub "ਏ" "Ē" when opt98
|
|
145
|
+
sub "ਠ" "ṭha"
|
|
146
|
+
sub "ਐ" "ai"
|
|
147
|
+
sub "ੈ" "ai"
|
|
148
|
+
sub "ਐ" "Ai" when opt98
|
|
149
|
+
sub "ਡ" "ḍa"
|
|
150
|
+
sub "ਓ" "ō"
|
|
151
|
+
sub "ੋ" "ō"
|
|
152
|
+
sub "ਓ" "Ō" when opt98
|
|
153
|
+
sub "ਢ" "ḍha"
|
|
154
|
+
sub "ਔ" "au"
|
|
155
|
+
sub "ੌ" "au"
|
|
156
|
+
sub "ਔ" "Au" when opt98
|
|
157
|
+
sub "ਣ" "ṇa"
|
|
158
|
+
sub "ਸ" "sa"
|
|
159
|
+
sub "ਸ" "Sa" when opt98
|
|
160
|
+
sub "ਤ" "ta"
|
|
161
|
+
sub "ਹ" "ha"
|
|
162
|
+
sub "ਹ" "Ha" when opt98
|
|
163
|
+
sub "ਥ" "tha"
|
|
164
|
+
sub "ਕ" "ka"
|
|
165
|
+
sub "ਕ਼" "qa"
|
|
166
|
+
sub "ਕ" "Ka" when opt98
|
|
167
|
+
sub "ਦ" "da"
|
|
168
|
+
sub "ਖ" "kha"
|
|
169
|
+
sub "ਖ" "Kha" when opt98
|
|
170
|
+
sub "ਧ" "dha"
|
|
171
|
+
sub "ਗ" "ga"
|
|
172
|
+
sub "ਗ" "Ga" when opt98
|
|
173
|
+
sub "ਨ" "na"
|
|
174
|
+
sub "ਘ" "gha"
|
|
175
|
+
sub "ਘ" "Gha" when opt98
|
|
176
|
+
sub "ਙ" "ṅa"
|
|
177
|
+
sub "ਙ" "Ṅa" when opt98
|
|
178
|
+
sub "ਪ" "pa"
|
|
179
|
+
sub "ਸ਼" "śa"
|
|
180
|
+
sub "ਸ਼" "śa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
181
|
+
sub "ਫ" "pha"
|
|
182
|
+
sub "ਖ਼" "k͟ha"
|
|
183
|
+
sub "ਖ਼" "k͟ha" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
184
|
+
sub "ਬ" "ba"
|
|
185
|
+
sub "ਗ਼" "ġa"
|
|
186
|
+
sub "ਗ਼" "ġa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
187
|
+
sub "ਭ" "bha"
|
|
188
|
+
sub "ਜ਼" "za"
|
|
189
|
+
sub "ਜ਼" "za" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
190
|
+
sub "ਮ" "ma"
|
|
191
|
+
sub "ਫ਼" "fa"
|
|
192
|
+
sub "ਫ਼" "fa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
193
|
+
sub "ਯ" "ya"
|
|
194
|
+
sub "ਰ" "ra"
|
|
195
|
+
sub "ਂ" "ṁ"
|
|
196
|
+
sub "ਲ" "la"
|
|
197
|
+
sub "ਲ਼" "ḷa"
|
|
198
|
+
sub "ੰ" "ṃ"
|
|
199
|
+
sub "ਲ਼" "ḷa"
|
|
200
|
+
sub "ਁ" "m̐"
|
|
201
|
+
sub "ਵ" "va"
|
|
202
|
+
sub "ਃ" "ḥ"
|
|
203
|
+
sub "ੜ" "ṛa"
|
|
204
|
+
sub "੍" ""
|
|
205
|
+
sub "੍" "·" when opt10
|
|
206
|
+
sub "" ""
|
|
207
|
+
sub "" "=" when opt99
|
|
208
|
+
sub "੦" "0"
|
|
209
|
+
sub "੧" "1"
|
|
210
|
+
sub "੨" "2"
|
|
211
|
+
sub "੩" "3"
|
|
212
|
+
sub "੪" "4"
|
|
213
|
+
sub "੫" "5"
|
|
214
|
+
sub "੬" "6"
|
|
215
|
+
sub "੭" "7"
|
|
216
|
+
sub "੮" "8"
|
|
217
|
+
sub "੯" "9"
|
|
218
|
+
}
|
|
219
|
+
|
|
220
|
+
compose
|
|
221
|
+
}
|
|
222
|
+
}
|