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
|
@@ -50,9 +50,12 @@ tests {
|
|
|
50
50
|
# visually identified (PR #242) as j-acute; transcribed as "j́"; the row
|
|
51
51
|
# passes end-to-end. | к̢ (position 37) — printed cell "(ķ)" (value 'ķ');
|
|
52
52
|
# runtime gives ''. Failing row, finding below — never forced green.
|
|
53
|
-
# Findings (map-vs-source
|
|
54
|
-
#
|
|
55
|
-
#
|
|
53
|
+
# Findings (map-vs-source) resolved in the E3 corpus-fixes round (2026-11-17): the
|
|
54
|
+
# map values now carry the printed cedilla (ķ/ņ, the DIN uvular/nasal
|
|
55
|
+
# series letters); the atv/az pos-37 stray-paren empty-target sub rule is
|
|
56
|
+
# replaced by the printed (ķ) value. The rows are part of the generated
|
|
57
|
+
# set; the per-cell notes above record the printed readings.
|
|
58
|
+
# Provenance artifact: scripts/row-sources/din-atv-Cyrl-Latn-1460-2-2011.json (37 rows).
|
|
56
59
|
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
|
|
57
60
|
"a" -> "a"
|
|
58
61
|
"б" -> "b"
|
|
@@ -68,6 +71,7 @@ tests {
|
|
|
68
71
|
"i" -> "í"
|
|
69
72
|
"j" -> "j́"
|
|
70
73
|
"к" -> "k"
|
|
74
|
+
"к̢" -> "ķ"
|
|
71
75
|
"л" -> "l"
|
|
72
76
|
"м" -> "m"
|
|
73
77
|
"н" -> "n"
|
|
@@ -108,7 +112,7 @@ stage main {
|
|
|
108
112
|
sub "i" "í"
|
|
109
113
|
sub "j" "j́"
|
|
110
114
|
sub "к" "k"
|
|
111
|
-
sub "к̢" ""
|
|
115
|
+
sub "к̢" "ķ"
|
|
112
116
|
sub "л" "l"
|
|
113
117
|
sub "м" "m"
|
|
114
118
|
sub "н" "n"
|
|
@@ -57,10 +57,12 @@ tests {
|
|
|
57
57
|
# the row passes end-to-end. | э (position 90) — the printed cell carries
|
|
58
58
|
# the value parenthesized ("(ė)"), DIN's optional-value notation;
|
|
59
59
|
# transcribed without the typographic parentheses; the row passes
|
|
60
|
-
# end-to-end. Findings (map-vs-source
|
|
61
|
-
#
|
|
62
|
-
#
|
|
63
|
-
#
|
|
60
|
+
# end-to-end. Findings (map-vs-source) resolved in the E3 corpus-fixes round (2026-11-17): the
|
|
61
|
+
# map values now carry the printed cedilla (ķ/ņ, the DIN uvular/nasal
|
|
62
|
+
# series letters); the atv/az pos-37 stray-paren empty-target sub rule is
|
|
63
|
+
# replaced by the printed (ķ) value. The rows are part of the generated
|
|
64
|
+
# set; the per-cell notes above record the printed readings.
|
|
65
|
+
# Provenance artifact: scripts/row-sources/din-az-Cyrl-Latn-1460-2-2011.json (37 rows).
|
|
64
66
|
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
|
|
65
67
|
"a" -> "a"
|
|
66
68
|
"б" -> "b"
|
|
@@ -76,6 +78,8 @@ tests {
|
|
|
76
78
|
"й" -> "j"
|
|
77
79
|
"j" -> "j"
|
|
78
80
|
"к" -> "k"
|
|
81
|
+
"к̢" -> "ķ"
|
|
82
|
+
"ҝ" -> "ķ"
|
|
79
83
|
"л" -> "l"
|
|
80
84
|
"м" -> "m"
|
|
81
85
|
"н" -> "n"
|
|
@@ -115,8 +119,8 @@ stage main {
|
|
|
115
119
|
sub "й" "j"
|
|
116
120
|
sub "j" "j"
|
|
117
121
|
sub "к" "k"
|
|
118
|
-
sub "к̢" ""
|
|
119
|
-
sub "ҝ" "k"
|
|
122
|
+
sub "к̢" "ķ"
|
|
123
|
+
sub "ҝ" "ķ"
|
|
120
124
|
sub "л" "l"
|
|
121
125
|
sub "м" "m"
|
|
122
126
|
sub "н" "n"
|
|
@@ -46,10 +46,12 @@ tests {
|
|
|
46
46
|
# numbers. Cell notes: ҡ (position 39) — printed cell "ķ" (value 'ķ');
|
|
47
47
|
# runtime gives 'k'. Failing row, finding below — never forced green. | ң
|
|
48
48
|
# (position 47) — printed cell "ņ" (value 'ņ'); runtime gives 'n'. Failing
|
|
49
|
-
# row, finding below — never forced green. Findings (map-vs-source
|
|
50
|
-
#
|
|
51
|
-
#
|
|
52
|
-
#
|
|
49
|
+
# row, finding below — never forced green. Findings (map-vs-source) resolved in the E3 corpus-fixes round (2026-11-17): the
|
|
50
|
+
# map values now carry the printed cedilla (ķ/ņ, the DIN uvular/nasal
|
|
51
|
+
# series letters); the atv/az pos-37 stray-paren empty-target sub rule is
|
|
52
|
+
# replaced by the printed (ķ) value. The rows are part of the generated
|
|
53
|
+
# set; the per-cell notes above record the printed readings.
|
|
54
|
+
# Provenance artifact: scripts/row-sources/din-ba-Cyrl-Latn-1460-2-2011.json (39 rows).
|
|
53
55
|
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
|
|
54
56
|
"a" -> "a"
|
|
55
57
|
"б" -> "b"
|
|
@@ -66,9 +68,11 @@ tests {
|
|
|
66
68
|
"и" -> "i"
|
|
67
69
|
"й" -> "j"
|
|
68
70
|
"к" -> "k"
|
|
71
|
+
"ҡ" -> "ķ"
|
|
69
72
|
"л" -> "l"
|
|
70
73
|
"м" -> "m"
|
|
71
74
|
"н" -> "n"
|
|
75
|
+
"ң" -> "ņ"
|
|
72
76
|
"о" -> "o"
|
|
73
77
|
"ө" -> "ö"
|
|
74
78
|
"п" -> "p"
|
|
@@ -107,11 +111,11 @@ stage main {
|
|
|
107
111
|
sub "и" "i"
|
|
108
112
|
sub "й" "j"
|
|
109
113
|
sub "к" "k"
|
|
110
|
-
sub "ҡ" "k"
|
|
114
|
+
sub "ҡ" "ķ"
|
|
111
115
|
sub "л" "l"
|
|
112
116
|
sub "м" "m"
|
|
113
117
|
sub "н" "n"
|
|
114
|
-
sub "ң" "n"
|
|
118
|
+
sub "ң" "ņ"
|
|
115
119
|
sub "о" "o"
|
|
116
120
|
sub "ө" "ö"
|
|
117
121
|
sub "п" "p"
|
|
@@ -26,7 +26,10 @@ metadata {
|
|
|
26
26
|
recorded here. Yeh (row 36, given as 064A/0649) renders y by
|
|
27
27
|
default and i-macron over vocalized input; Urdu texts commonly
|
|
28
28
|
write the yeh with the Persian codepoint (06CC), which this map
|
|
29
|
-
accepts as the same letter.
|
|
29
|
+
accepts as the same letter. Urdu texts likewise write heh
|
|
30
|
+
(row 35, 06BE/0647) overwhelmingly in the gol form (06C1), which this
|
|
31
|
+
map accepts as the same letter (cf. ALA-LC rule 9: heh "usually
|
|
32
|
+
written in the form" ہ). The badi ye (row 37) renders e.
|
|
30
33
|
Remark d: aspiration is written as in the original script (bh and
|
|
31
34
|
the like), which follows mechanically from the heh's constant h —
|
|
32
35
|
the aspirate digraphs need no separate rules. Remark b: the
|
|
@@ -76,6 +79,7 @@ tests {
|
|
|
76
79
|
"و" -> "v"
|
|
77
80
|
"ه" -> "h"
|
|
78
81
|
"ھ" -> "h"
|
|
82
|
+
"ہ" -> "h"
|
|
79
83
|
"ی" -> "y"
|
|
80
84
|
"ي" -> "y"
|
|
81
85
|
"ى" -> "y"
|
|
@@ -227,6 +231,7 @@ stage main {
|
|
|
227
231
|
sub "وّ" "vv"
|
|
228
232
|
sub "هّ" "hh"
|
|
229
233
|
sub "ھّ" "hh"
|
|
234
|
+
sub "ہّ" "hh"
|
|
230
235
|
sub "يّ" "yy"
|
|
231
236
|
sub "یّ" "yy"
|
|
232
237
|
sub "وُ" "ū"
|
|
@@ -282,6 +287,7 @@ stage main {
|
|
|
282
287
|
sub "و" "v"
|
|
283
288
|
sub "ه" "h"
|
|
284
289
|
sub "ھ" "h"
|
|
290
|
+
sub "ہ" "h"
|
|
285
291
|
sub "ي" "y"
|
|
286
292
|
sub "ی" "y"
|
|
287
293
|
sub "ى" "y"
|
|
@@ -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 Bengali ba:i (not bai), “book”.\n - Unexpected use of secondary ya/ẏa , as in Bengali r:yāpāra , English “wrapper” (using full r); a:yā (not ayā )."
|
|
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: Table 2 ref 156a prints ja + nukta -> za and ref 172a prints ba + nukta -> wa (footnote c: used for transliteration of Persian and Arabic words into Bengali script); both combinations are now encoded. The Assamese letters (refs 240/241, footnote b) belong to the Assamese map; the q/kha-line/ga-line/f letters of modern secondary transcriptions are not printed by the official table."
|
|
35
36
|
}
|
|
36
37
|
}
|
|
37
38
|
|
|
@@ -46,6 +47,8 @@ tests {
|
|
|
46
47
|
"সুয়ারেজকে ‘বের করে দেওয়া’য় বার্সাকে ধুয়ে দিলেন মেসি" -> "sauẏaāraejakae ‘baera karae daeoẏaā’ẏa baārasaākae dhauẏae dailaena maesai"
|
|
47
48
|
"আমি না থাকলে আর্জেন্টিনা দলে মেসিরও থাকার যোগ্যতা নেই" -> "āmai naā thaākalae ārajaenaṭainaā dalae maesairao thaākaāra yaogayataā naei"
|
|
48
49
|
"তবে, নিয়মিত মুখগুলোর মধ্যে দলে নেই মেসির দুই ‘প্রিয় বন্ধু’ পিএসজির মিডফিল্ডার আনহেল দি মারিয়া ও ম্যানচেস্টার সিটির সার্জিও আগুয়েরো" -> "tabae, naiẏamaita maukhagaulaora madhayae dalae naei maesaira daui ‘paraiẏa banadhau’ paiesajaira maiḍaphailaḍaāra ānahaela dai maāraiẏaā o mayaānacaesaṭaāra saiṭaira saārajaio āgauẏaerao"
|
|
50
|
+
"জ়" -> "za"
|
|
51
|
+
"ব়" -> "wa"
|
|
49
52
|
}
|
|
50
53
|
|
|
51
54
|
stage main {
|
|
@@ -137,6 +140,8 @@ stage main {
|
|
|
137
140
|
sub "বঁ" "m̐va"
|
|
138
141
|
|
|
139
142
|
sub "ৎ" "t"
|
|
143
|
+
sub "জ়" "za"
|
|
144
|
+
sub "ব়" "wa"
|
|
140
145
|
sub "্" ""
|
|
141
146
|
|
|
142
147
|
|
|
@@ -0,0 +1,228 @@
|
|
|
1
|
+
system "ISO:ben-Beng:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:ben
|
|
7
|
+
source_script Beng
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Bengali (and Assamese); 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 7.2 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 erratum recorded: Table 7.2 row ba+nukta (09AC 09BC) prints Latin 'wa' with Hex 0066 (contradiction); the Latin text 'wa' is encoded."
|
|
24
|
+
note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 44/66 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
|
+
note "Row-level source errata encoded per printed text: Table 7.2 row ['ব়']: latin/hex mismatch: text='wa' hex=0066"
|
|
26
|
+
note "The precomposed nukta letters 09DC 09DD 09DF are encoded alongside their decomposed combinations (clause 7.3: precomposed and decomposed characters are treated equally on input)."
|
|
27
|
+
}
|
|
28
|
+
}
|
|
29
|
+
|
|
30
|
+
languages opt98 opt99 opt10
|
|
31
|
+
|
|
32
|
+
tests {
|
|
33
|
+
"অ" -> "a"
|
|
34
|
+
"ক" -> "ka"
|
|
35
|
+
"আ" -> "ā"
|
|
36
|
+
"া" -> "ā"
|
|
37
|
+
"খ" -> "kha"
|
|
38
|
+
"ই" -> "i"
|
|
39
|
+
"ি" -> "i"
|
|
40
|
+
"গ" -> "ga"
|
|
41
|
+
"ঈ" -> "ī"
|
|
42
|
+
"ী" -> "ī"
|
|
43
|
+
"ঘ" -> "gha"
|
|
44
|
+
"উ" -> "u"
|
|
45
|
+
"ু" -> "u"
|
|
46
|
+
"ঙ" -> "ṅa"
|
|
47
|
+
"ঊ" -> "ū"
|
|
48
|
+
"ূ" -> "ū"
|
|
49
|
+
"চ" -> "ca"
|
|
50
|
+
"ঋ" -> "r̥"
|
|
51
|
+
"ৃ" -> "r̥"
|
|
52
|
+
"ছ" -> "cha"
|
|
53
|
+
"ৠ" -> "r̥̄"
|
|
54
|
+
"ৄ" -> "r̥̄"
|
|
55
|
+
"জ" -> "ja"
|
|
56
|
+
"ঌ" -> "l̥"
|
|
57
|
+
"ৢ" -> "l̥"
|
|
58
|
+
"ঝ" -> "jha"
|
|
59
|
+
"ৡ" -> "l̥̄"
|
|
60
|
+
"ৣ" -> "l̥̄"
|
|
61
|
+
"ঞ" -> "ña"
|
|
62
|
+
"এ" -> "ē"
|
|
63
|
+
"ে" -> "ē"
|
|
64
|
+
"ট" -> "ṭa"
|
|
65
|
+
"ঐ" -> "ai"
|
|
66
|
+
"ৈ" -> "ai"
|
|
67
|
+
"ঠ" -> "ṭha"
|
|
68
|
+
"ও" -> "ō"
|
|
69
|
+
"ো" -> "ō"
|
|
70
|
+
"ড" -> "ḍa"
|
|
71
|
+
"ঔ" -> "au"
|
|
72
|
+
"ৌ" -> "au"
|
|
73
|
+
"ঢ" -> "ḍha"
|
|
74
|
+
"ত" -> "ta"
|
|
75
|
+
"ল" -> "la"
|
|
76
|
+
"থ" -> "tha"
|
|
77
|
+
"ৱ" -> "va"
|
|
78
|
+
"দ" -> "da"
|
|
79
|
+
"শ" -> "śa"
|
|
80
|
+
"ধ" -> "dha"
|
|
81
|
+
"ষ" -> "ṣa"
|
|
82
|
+
"ন" -> "na"
|
|
83
|
+
"স" -> "sa"
|
|
84
|
+
"প" -> "pa"
|
|
85
|
+
"হ" -> "ha"
|
|
86
|
+
"ফ" -> "pha"
|
|
87
|
+
"ড়" -> "ṛa"
|
|
88
|
+
"ব" -> "ba"
|
|
89
|
+
"ঢ়" -> "ṛha"
|
|
90
|
+
"ভ" -> "bha"
|
|
91
|
+
"জ়" -> "za"
|
|
92
|
+
"ম" -> "ma"
|
|
93
|
+
"ব়" -> "wa"
|
|
94
|
+
"য" -> "ya"
|
|
95
|
+
"ং" -> "ṁ"
|
|
96
|
+
"য়" -> "ẏa"
|
|
97
|
+
"ঁ" -> "m̐"
|
|
98
|
+
"র" -> "ra"
|
|
99
|
+
"ঃ" -> "ḥ"
|
|
100
|
+
"ৰ" -> "ṟa"
|
|
101
|
+
"ঽ" -> "'"
|
|
102
|
+
"০" -> "0"
|
|
103
|
+
"১" -> "1"
|
|
104
|
+
"২" -> "2"
|
|
105
|
+
"৩" -> "3"
|
|
106
|
+
"৪" -> "4"
|
|
107
|
+
"৫" -> "5"
|
|
108
|
+
"৬" -> "6"
|
|
109
|
+
"৭" -> "7"
|
|
110
|
+
"৮" -> "8"
|
|
111
|
+
"৯" -> "9"
|
|
112
|
+
"ণ" -> "ṇa"
|
|
113
|
+
"ড়" -> "ṛa"
|
|
114
|
+
"ঢ়" -> "ṛha"
|
|
115
|
+
"য়" -> "ẏa"
|
|
116
|
+
}
|
|
117
|
+
|
|
118
|
+
stage main {
|
|
119
|
+
|
|
120
|
+
# Table 7.2 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
121
|
+
parallel {
|
|
122
|
+
|
|
123
|
+
sub "অ" "a"
|
|
124
|
+
sub "অ" "A" when opt98
|
|
125
|
+
sub "ক" "ka"
|
|
126
|
+
sub "আ" "ā"
|
|
127
|
+
sub "া" "ā"
|
|
128
|
+
sub "আ" "Ā" when opt98
|
|
129
|
+
sub "খ" "kha"
|
|
130
|
+
sub "ই" "i"
|
|
131
|
+
sub "ি" "i"
|
|
132
|
+
sub "ই" "I" when opt98
|
|
133
|
+
sub "গ" "ga"
|
|
134
|
+
sub "ঈ" "ī"
|
|
135
|
+
sub "ী" "ī"
|
|
136
|
+
sub "ঈ" "Ī" when opt98
|
|
137
|
+
sub "ঘ" "gha"
|
|
138
|
+
sub "উ" "u"
|
|
139
|
+
sub "ু" "u"
|
|
140
|
+
sub "উ" "U" when opt98
|
|
141
|
+
sub "ঙ" "ṅa"
|
|
142
|
+
sub "ঊ" "ū"
|
|
143
|
+
sub "ূ" "ū"
|
|
144
|
+
sub "ঊ" "Ū" when opt98
|
|
145
|
+
sub "চ" "ca"
|
|
146
|
+
sub "ঋ" "r̥"
|
|
147
|
+
sub "ৃ" "r̥"
|
|
148
|
+
sub "ঋ" "R̥" when opt98
|
|
149
|
+
sub "ছ" "cha"
|
|
150
|
+
sub "ৠ" "r̥̄"
|
|
151
|
+
sub "ৄ" "r̥̄"
|
|
152
|
+
sub "ৠ" "R̥̄" when opt98
|
|
153
|
+
sub "জ" "ja"
|
|
154
|
+
sub "ঌ" "l̥"
|
|
155
|
+
sub "ৢ" "l̥"
|
|
156
|
+
sub "ঌ" "L̥" when opt98
|
|
157
|
+
sub "ঝ" "jha"
|
|
158
|
+
sub "ৡ" "l̥̄"
|
|
159
|
+
sub "ৣ" "l̥̄"
|
|
160
|
+
sub "ৡ" "L̥̄" when opt98
|
|
161
|
+
sub "ঞ" "ña"
|
|
162
|
+
sub "এ" "ē"
|
|
163
|
+
sub "ে" "ē"
|
|
164
|
+
sub "এ" "Ē" when opt98
|
|
165
|
+
sub "ট" "ṭa"
|
|
166
|
+
sub "ঐ" "ai"
|
|
167
|
+
sub "ৈ" "ai"
|
|
168
|
+
sub "ঐ" "Ai" when opt98
|
|
169
|
+
sub "ঠ" "ṭha"
|
|
170
|
+
sub "ও" "ō"
|
|
171
|
+
sub "ো" "ō"
|
|
172
|
+
sub "ও" "Ō" when opt98
|
|
173
|
+
sub "ড" "ḍa"
|
|
174
|
+
sub "ঔ" "au"
|
|
175
|
+
sub "ৌ" "au"
|
|
176
|
+
sub "ঔ" "Au" when opt98
|
|
177
|
+
sub "ঢ" "ḍha"
|
|
178
|
+
sub "ণ" "ṇa"
|
|
179
|
+
sub "ত" "ta"
|
|
180
|
+
sub "ল" "la"
|
|
181
|
+
sub "থ" "tha"
|
|
182
|
+
sub "ৱ" "va"
|
|
183
|
+
sub "দ" "da"
|
|
184
|
+
sub "শ" "śa"
|
|
185
|
+
sub "ধ" "dha"
|
|
186
|
+
sub "ষ" "ṣa"
|
|
187
|
+
sub "ন" "na"
|
|
188
|
+
sub "স" "sa"
|
|
189
|
+
sub "প" "pa"
|
|
190
|
+
sub "হ" "ha"
|
|
191
|
+
sub "ফ" "pha"
|
|
192
|
+
sub "ড়" "ṛa"
|
|
193
|
+
sub "ড়" "ṛa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
194
|
+
sub "ব" "ba"
|
|
195
|
+
sub "ঢ়" "ṛha"
|
|
196
|
+
sub "ঢ়" "ṛha" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
197
|
+
sub "ভ" "bha"
|
|
198
|
+
sub "জ়" "za"
|
|
199
|
+
sub "ম" "ma"
|
|
200
|
+
sub "ব়" "wa"
|
|
201
|
+
sub "য" "ya"
|
|
202
|
+
sub "ং" "ṁ"
|
|
203
|
+
sub "য়" "ẏa"
|
|
204
|
+
sub "য়" "ẏa" # precomposed (clause 7.3: precomposed and decomposed equal on input)
|
|
205
|
+
sub "ঁ" "m̐"
|
|
206
|
+
sub "র" "ra"
|
|
207
|
+
sub "ঃ" "ḥ"
|
|
208
|
+
sub "ৰ" "ṟa"
|
|
209
|
+
sub "ঽ" "'"
|
|
210
|
+
sub "্" ""
|
|
211
|
+
sub "্" "·" when opt10
|
|
212
|
+
sub "" ""
|
|
213
|
+
sub "" "=" when opt99
|
|
214
|
+
sub "০" "0"
|
|
215
|
+
sub "১" "1"
|
|
216
|
+
sub "২" "2"
|
|
217
|
+
sub "৩" "3"
|
|
218
|
+
sub "৪" "4"
|
|
219
|
+
sub "৫" "5"
|
|
220
|
+
sub "৬" "6"
|
|
221
|
+
sub "৭" "7"
|
|
222
|
+
sub "৮" "8"
|
|
223
|
+
sub "৯" "9"
|
|
224
|
+
}
|
|
225
|
+
|
|
226
|
+
compose
|
|
227
|
+
}
|
|
228
|
+
}
|
|
@@ -0,0 +1,182 @@
|
|
|
1
|
+
system "ISO:doi-Takr:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:doi
|
|
7
|
+
source_script Takr
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Dogri (Takri); 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 7.16 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
|
+
"𑚀" -> "a"
|
|
30
|
+
"𑚊" -> "ka"
|
|
31
|
+
"𑚁" -> "ā"
|
|
32
|
+
"𑚭" -> "ā"
|
|
33
|
+
"𑚋" -> "kha"
|
|
34
|
+
"𑚂" -> "i"
|
|
35
|
+
"𑚮" -> "i"
|
|
36
|
+
"𑚌" -> "ga"
|
|
37
|
+
"𑚃" -> "ī"
|
|
38
|
+
"𑚯" -> "ī"
|
|
39
|
+
"𑚍" -> "gha"
|
|
40
|
+
"𑚄" -> "u"
|
|
41
|
+
"𑚰" -> "u"
|
|
42
|
+
"𑚎" -> "ṅa"
|
|
43
|
+
"𑚅" -> "ū"
|
|
44
|
+
"𑚱" -> "ū"
|
|
45
|
+
"𑚏" -> "ca"
|
|
46
|
+
"𑚆" -> "ē"
|
|
47
|
+
"𑚲" -> "ē"
|
|
48
|
+
"𑚐" -> "cha"
|
|
49
|
+
"𑚇" -> "ai"
|
|
50
|
+
"𑚳" -> "ai"
|
|
51
|
+
"𑚑" -> "ja"
|
|
52
|
+
"𑚈" -> "ō"
|
|
53
|
+
"𑚴" -> "ō"
|
|
54
|
+
"𑚒" -> "jha"
|
|
55
|
+
"𑚉" -> "au"
|
|
56
|
+
"𑚵" -> "au"
|
|
57
|
+
"𑚓" -> "ña"
|
|
58
|
+
"𑚙" -> "ta"
|
|
59
|
+
"𑚣" -> "ya"
|
|
60
|
+
"𑚚" -> "tha"
|
|
61
|
+
"𑚤" -> "ra"
|
|
62
|
+
"𑚛" -> "da"
|
|
63
|
+
"𑚥" -> "la"
|
|
64
|
+
"𑚜" -> "dha"
|
|
65
|
+
"𑚦" -> "va"
|
|
66
|
+
"𑚝" -> "na"
|
|
67
|
+
"𑚧" -> "śa"
|
|
68
|
+
"𑚞" -> "pa"
|
|
69
|
+
"𑚨" -> "sa"
|
|
70
|
+
"𑚟" -> "pha"
|
|
71
|
+
"𑚩" -> "ha"
|
|
72
|
+
"𑚠" -> "ba"
|
|
73
|
+
"𑚪" -> "ṛa"
|
|
74
|
+
"𑚡" -> "bha"
|
|
75
|
+
"𑚢" -> "ma"
|
|
76
|
+
"𑛀" -> "0"
|
|
77
|
+
"𑛁" -> "1"
|
|
78
|
+
"𑛂" -> "2"
|
|
79
|
+
"𑛃" -> "3"
|
|
80
|
+
"𑛄" -> "4"
|
|
81
|
+
"𑛅" -> "5"
|
|
82
|
+
"𑛆" -> "6"
|
|
83
|
+
"𑛇" -> "7"
|
|
84
|
+
"𑛈" -> "8"
|
|
85
|
+
"𑛉" -> "9"
|
|
86
|
+
"𑚔" -> "ṭa"
|
|
87
|
+
"𑚕" -> "ṭha"
|
|
88
|
+
"𑚖" -> "ḍa"
|
|
89
|
+
"𑚗" -> "ḍha"
|
|
90
|
+
"𑚘" -> "ṇa"
|
|
91
|
+
"𑚫" -> "ṁ"
|
|
92
|
+
"𑚬" -> "ḥ"
|
|
93
|
+
}
|
|
94
|
+
|
|
95
|
+
stage main {
|
|
96
|
+
|
|
97
|
+
# Table 7.16 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
98
|
+
parallel {
|
|
99
|
+
|
|
100
|
+
sub "𑚀" "a"
|
|
101
|
+
sub "𑚀" "A" when opt98
|
|
102
|
+
sub "𑚊" "ka"
|
|
103
|
+
sub "𑚁" "ā"
|
|
104
|
+
sub "𑚭" "ā"
|
|
105
|
+
sub "𑚁" "Ā" when opt98
|
|
106
|
+
sub "𑚋" "kha"
|
|
107
|
+
sub "𑚂" "i"
|
|
108
|
+
sub "𑚮" "i"
|
|
109
|
+
sub "𑚂" "I" when opt98
|
|
110
|
+
sub "𑚌" "ga"
|
|
111
|
+
sub "𑚃" "ī"
|
|
112
|
+
sub "𑚯" "ī"
|
|
113
|
+
sub "𑚃" "Ī" when opt98
|
|
114
|
+
sub "𑚍" "gha"
|
|
115
|
+
sub "𑚄" "u"
|
|
116
|
+
sub "𑚰" "u"
|
|
117
|
+
sub "𑚄" "U" when opt98
|
|
118
|
+
sub "𑚎" "ṅa"
|
|
119
|
+
sub "𑚅" "ū"
|
|
120
|
+
sub "𑚱" "ū"
|
|
121
|
+
sub "𑚅" "Ū" when opt98
|
|
122
|
+
sub "𑚏" "ca"
|
|
123
|
+
sub "𑚆" "ē"
|
|
124
|
+
sub "𑚲" "ē"
|
|
125
|
+
sub "𑚆" "Ē" when opt98
|
|
126
|
+
sub "𑚐" "cha"
|
|
127
|
+
sub "𑚇" "ai"
|
|
128
|
+
sub "𑚳" "ai"
|
|
129
|
+
sub "𑚇" "Ai" when opt98
|
|
130
|
+
sub "𑚑" "ja"
|
|
131
|
+
sub "𑚈" "ō"
|
|
132
|
+
sub "𑚴" "ō"
|
|
133
|
+
sub "𑚈" "Ō" when opt98
|
|
134
|
+
sub "𑚒" "jha"
|
|
135
|
+
sub "𑚉" "au"
|
|
136
|
+
sub "𑚵" "au"
|
|
137
|
+
sub "𑚉" "Au" when opt98
|
|
138
|
+
sub "𑚓" "ña"
|
|
139
|
+
sub "𑚙" "ta"
|
|
140
|
+
sub "𑚣" "ya"
|
|
141
|
+
sub "𑚚" "tha"
|
|
142
|
+
sub "𑚤" "ra"
|
|
143
|
+
sub "𑚛" "da"
|
|
144
|
+
sub "𑚥" "la"
|
|
145
|
+
sub "𑚜" "dha"
|
|
146
|
+
sub "𑚦" "va"
|
|
147
|
+
sub "𑚝" "na"
|
|
148
|
+
sub "𑚔" "ṭa"
|
|
149
|
+
sub "𑚧" "śa"
|
|
150
|
+
sub "𑚞" "pa"
|
|
151
|
+
sub "𑚨" "sa"
|
|
152
|
+
sub "𑚟" "pha"
|
|
153
|
+
sub "𑚩" "ha"
|
|
154
|
+
sub "𑚠" "ba"
|
|
155
|
+
sub "𑚪" "ṛa"
|
|
156
|
+
sub "𑚡" "bha"
|
|
157
|
+
sub "𑚢" "ma"
|
|
158
|
+
sub "𑚕" "ṭha"
|
|
159
|
+
sub "𑚖" "ḍa"
|
|
160
|
+
sub "𑚗" "ḍha"
|
|
161
|
+
sub "𑚘" "ṇa"
|
|
162
|
+
sub "𑚫" "ṁ"
|
|
163
|
+
sub "𑚬" "ḥ"
|
|
164
|
+
sub "𑚶" ""
|
|
165
|
+
sub "𑚶" "·" when opt10
|
|
166
|
+
sub "" ""
|
|
167
|
+
sub "" "=" when opt99
|
|
168
|
+
sub "𑛀" "0"
|
|
169
|
+
sub "𑛁" "1"
|
|
170
|
+
sub "𑛂" "2"
|
|
171
|
+
sub "𑛃" "3"
|
|
172
|
+
sub "𑛄" "4"
|
|
173
|
+
sub "𑛅" "5"
|
|
174
|
+
sub "𑛆" "6"
|
|
175
|
+
sub "𑛇" "7"
|
|
176
|
+
sub "𑛈" "8"
|
|
177
|
+
sub "𑛉" "9"
|
|
178
|
+
}
|
|
179
|
+
|
|
180
|
+
compose
|
|
181
|
+
}
|
|
182
|
+
}
|