interscript-maps 3.2.4 โ†’ 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.
Files changed (45) hide show
  1. checksums.yaml +4 -4
  2. data/interscript-maps.gemspec +1 -1
  3. data/maps/alalc-aze-Cyrl-Latn-1997.isc +48 -11
  4. data/maps/alalc-ben-Beng-Latn-2017.isc +68 -17
  5. data/maps/alalc-sat-Olck-Latn-2017.isc +7 -3
  6. data/maps/bsi-rus-Cyrl-Latn-2979-1958.isc +233 -0
  7. data/maps/din-ab-Cyrl-Latn-1460-2-2011.isc +8 -4
  8. data/maps/din-atv-Cyrl-Latn-1460-2-2011.isc +8 -4
  9. data/maps/din-az-Cyrl-Latn-1460-2-2011.isc +10 -6
  10. data/maps/din-ba-Cyrl-Latn-1460-2-2011.isc +10 -6
  11. data/maps/din-urd-Arab-Latn-31635-2011.isc +7 -1
  12. data/maps/iso-ben-Beng-Latn-15919-2001.isc +5 -0
  13. data/maps/iso-ben-Beng-Latn-15919-2026.isc +228 -0
  14. data/maps/iso-doi-Takr-Latn-15919-2026.isc +182 -0
  15. data/maps/iso-guj-Gujr-Latn-15919-2026.isc +231 -0
  16. data/maps/iso-heb-Hebr-Latn-259-1984.isc +426 -0
  17. data/maps/iso-heb-Hebr-Latn-259-2-1994.isc +469 -0
  18. data/maps/iso-inc-Kthi-Latn-15919-2001.isc +121 -0
  19. data/maps/iso-inc-Kthi-Latn-15919-2026.isc +197 -0
  20. data/maps/iso-jpn-Hrkt-Latn-3602-1989.isc +53 -0
  21. data/maps/iso-kan-Kana-Latn-15919-2001.isc +8 -4
  22. data/maps/iso-kan-Kana-Latn-15919-2026.isc +229 -0
  23. data/maps/iso-kas-Shrd-Latn-15919-2026.isc +208 -0
  24. data/maps/iso-mal-Mlym-Latn-15919-2001.isc +1 -0
  25. data/maps/iso-mal-Mlym-Latn-15919-2026.isc +223 -0
  26. data/maps/iso-mar-Deva-Latn-15919-2001.isc +1 -1
  27. data/maps/iso-mar-Modi-Latn-15919-2026.isc +204 -0
  28. data/maps/iso-new-Newa-Latn-15919-2026.isc +221 -0
  29. data/maps/iso-ori-Orya-Latn-15919-2026.isc +222 -0
  30. data/maps/iso-pan-Guru-Latn-15919-2026.isc +222 -0
  31. data/maps/iso-pra-Brah-Latn-15919-2026.isc +231 -0
  32. data/maps/iso-san-Deva-Latn-15919-2001.isc +5 -2
  33. data/maps/iso-san-Deva-Latn-15919-2026.isc +278 -0
  34. data/maps/iso-san-Gran-Latn-15919-2026.isc +208 -0
  35. data/maps/iso-sin-Sinh-Latn-15919-2001.isc +174 -0
  36. data/maps/iso-sin-Sinh-Latn-15919-2026.isc +238 -0
  37. data/maps/iso-tam-Taml-Latn-15919-2001.isc +1 -0
  38. data/maps/iso-tam-Taml-Latn-15919-2026.isc +178 -0
  39. data/maps/iso-tel-Telu-Latn-15919-2001.isc +7 -0
  40. data/maps/iso-tel-Telu-Latn-15919-2026.isc +229 -0
  41. data/maps/odni-che-Cyrl-Latn-2015.isc +19 -19
  42. data/maps/odni-mkd-Cyrl-Latn-2015.isc +11 -16
  43. data/maps/var-jpn-Hrkt-Latn-komaba-2009.isc +417 -0
  44. metadata +24 -2
  45. data/maps/bsi-rus-Cyrl-Latn-1958.isc +0 -199
@@ -0,0 +1,208 @@
1
+ system "ISO:kas-Shrd:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:kas
7
+ source_script Shrd
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Kashmiri (Sharada); 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 7.15 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
+ "๐‘†ƒ" -> "a"
30
+ "๐‘†‘" -> "ka"
31
+ "๐‘†„" -> "ฤ"
32
+ "๐‘†ณ" -> "ฤ"
33
+ "๐‘†’" -> "kha"
34
+ "๐‘†…" -> "i"
35
+ "๐‘†ด" -> "i"
36
+ "๐‘†“" -> "ga"
37
+ "๐‘††" -> "ฤซ"
38
+ "๐‘†ต" -> "ฤซ"
39
+ "๐‘†”" -> "gha"
40
+ "๐‘†‡" -> "u"
41
+ "๐‘†ถ" -> "u"
42
+ "๐‘†•" -> "แน…a"
43
+ "๐‘†ˆ" -> "ลซ"
44
+ "๐‘†ท" -> "ลซ"
45
+ "๐‘†–" -> "ca"
46
+ "๐‘†‰" -> "rฬฅ"
47
+ "๐‘†ธ" -> "rฬฅ"
48
+ "๐‘†—" -> "cha"
49
+ "๐‘†Š" -> "rฬฅฬ„"
50
+ "๐‘†น" -> "rฬฅฬ„"
51
+ "๐‘†˜" -> "ja"
52
+ "๐‘†‹" -> "lฬฅ"
53
+ "๐‘†บ" -> "lฬฅ"
54
+ "๐‘†™" -> "jha"
55
+ "๐‘†Œ" -> "lฬฅฬ„"
56
+ "๐‘†ป" -> "lฬฅฬ„"
57
+ "๐‘†š" -> "รฑa"
58
+ "๐‘†" -> "ฤ“"
59
+ "๐‘†ผ" -> "ฤ“"
60
+ "๐‘†›" -> "แนญa"
61
+ "๐‘†Ž" -> "ai"
62
+ "๐‘†ฝ" -> "ai"
63
+ "๐‘†œ" -> "แนญha"
64
+ "๐‘†" -> "ล"
65
+ "๐‘†พ" -> "ล"
66
+ "๐‘†" -> "แธa"
67
+ "๐‘†" -> "au"
68
+ "๐‘†ฟ" -> "au"
69
+ "๐‘†ž" -> "แธha"
70
+ "๐‘† " -> "ta"
71
+ "๐‘†ช" -> "ya"
72
+ "๐‘†ก" -> "tha"
73
+ "๐‘†ซ" -> "ra"
74
+ "๐‘†ข" -> "da"
75
+ "๐‘†ฌ" -> "la"
76
+ "๐‘†ฃ" -> "dha"
77
+ "๐‘†ญ" -> "แธทa"
78
+ "๐‘†ค" -> "na"
79
+ "๐‘†ฎ" -> "va"
80
+ "๐‘†ฅ" -> "pa"
81
+ "๐‘†ฏ" -> "ล›a"
82
+ "๐‘†ฆ" -> "pha"
83
+ "๐‘†ฐ" -> "แนฃa"
84
+ "๐‘†ง" -> "ba"
85
+ "๐‘†ฑ" -> "sa"
86
+ "๐‘†จ" -> "bha"
87
+ "๐‘†ฒ" -> "ha"
88
+ "๐‘†ฉ" -> "ma"
89
+ "๐‘‡" -> "0"
90
+ "๐‘‡‘" -> "1"
91
+ "๐‘‡’" -> "2"
92
+ "๐‘‡“" -> "3"
93
+ "๐‘‡”" -> "4"
94
+ "๐‘‡•" -> "5"
95
+ "๐‘‡–" -> "6"
96
+ "๐‘‡—" -> "7"
97
+ "๐‘‡˜" -> "8"
98
+ "๐‘‡™" -> "9"
99
+ "๐‘†Ÿ" -> "แน‡a"
100
+ "๐‘†€" -> "mฬ"
101
+ "๐‘†" -> "แน"
102
+ "๐‘†‚" -> "แธฅ"
103
+ "๐‘‡" -> "'"
104
+ }
105
+
106
+ stage main {
107
+
108
+ # Table 7.15 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
109
+ parallel {
110
+
111
+ sub "๐‘†ƒ" "a"
112
+ sub "๐‘†ƒ" "A" when opt98
113
+ sub "๐‘†‘" "ka"
114
+ sub "๐‘†„" "ฤ"
115
+ sub "๐‘†ณ" "ฤ"
116
+ sub "๐‘†„" "ฤ€" when opt98
117
+ sub "๐‘†’" "kha"
118
+ sub "๐‘†…" "i"
119
+ sub "๐‘†ด" "i"
120
+ sub "๐‘†…" "I" when opt98
121
+ sub "๐‘†“" "ga"
122
+ sub "๐‘††" "ฤซ"
123
+ sub "๐‘†ต" "ฤซ"
124
+ sub "๐‘††" "ฤช" when opt98
125
+ sub "๐‘†”" "gha"
126
+ sub "๐‘†‡" "u"
127
+ sub "๐‘†ถ" "u"
128
+ sub "๐‘†‡" "U" when opt98
129
+ sub "๐‘†•" "แน…a"
130
+ sub "๐‘†ˆ" "ลซ"
131
+ sub "๐‘†ท" "ลซ"
132
+ sub "๐‘†ˆ" "ลช" when opt98
133
+ sub "๐‘†–" "ca"
134
+ sub "๐‘†‰" "rฬฅ"
135
+ sub "๐‘†ธ" "rฬฅ"
136
+ sub "๐‘†‰" "Rฬฅ" when opt98
137
+ sub "๐‘†—" "cha"
138
+ sub "๐‘†Š" "rฬฅฬ„"
139
+ sub "๐‘†น" "rฬฅฬ„"
140
+ sub "๐‘†Š" "Rฬฅฬ„" when opt98
141
+ sub "๐‘†˜" "ja"
142
+ sub "๐‘†‹" "lฬฅ"
143
+ sub "๐‘†บ" "lฬฅ"
144
+ sub "๐‘†‹" "Lฬฅ" when opt98
145
+ sub "๐‘†™" "jha"
146
+ sub "๐‘†Œ" "lฬฅฬ„"
147
+ sub "๐‘†ป" "lฬฅฬ„"
148
+ sub "๐‘†Œ" "Lฬฅฬ„" when opt98
149
+ sub "๐‘†š" "รฑa"
150
+ sub "๐‘†" "ฤ“"
151
+ sub "๐‘†ผ" "ฤ“"
152
+ sub "๐‘†" "ฤ’" when opt98
153
+ sub "๐‘†›" "แนญa"
154
+ sub "๐‘†Ž" "ai"
155
+ sub "๐‘†ฝ" "ai"
156
+ sub "๐‘†Ž" "Ai" when opt98
157
+ sub "๐‘†œ" "แนญha"
158
+ sub "๐‘†" "ล"
159
+ sub "๐‘†พ" "ล"
160
+ sub "๐‘†" "ลŒ" when opt98
161
+ sub "๐‘†" "แธa"
162
+ sub "๐‘†" "au"
163
+ sub "๐‘†ฟ" "au"
164
+ sub "๐‘†" "Au" when opt98
165
+ sub "๐‘†ž" "แธha"
166
+ sub "๐‘†Ÿ" "แน‡a"
167
+ sub "๐‘† " "ta"
168
+ sub "๐‘†ช" "ya"
169
+ sub "๐‘†ก" "tha"
170
+ sub "๐‘†ซ" "ra"
171
+ sub "๐‘†ข" "da"
172
+ sub "๐‘†ฌ" "la"
173
+ sub "๐‘†ฃ" "dha"
174
+ sub "๐‘†ญ" "แธทa"
175
+ sub "๐‘†ค" "na"
176
+ sub "๐‘†ฎ" "va"
177
+ sub "๐‘†ฅ" "pa"
178
+ sub "๐‘†ฏ" "ล›a"
179
+ sub "๐‘†ฆ" "pha"
180
+ sub "๐‘†ฐ" "แนฃa"
181
+ sub "๐‘†ง" "ba"
182
+ sub "๐‘†ฑ" "sa"
183
+ sub "๐‘†จ" "bha"
184
+ sub "๐‘†ฒ" "ha"
185
+ sub "๐‘†ฉ" "ma"
186
+ sub "๐‘†€" "mฬ"
187
+ sub "๐‘†" "แน"
188
+ sub "๐‘†‚" "แธฅ"
189
+ sub "๐‘‡" "'" # avagraha
190
+ sub "๐‘‡€" ""
191
+ sub "๐‘‡€" "ยท" when opt10
192
+ sub "โ€" ""
193
+ sub "โ€" "=" when opt99
194
+ sub "๐‘‡" "0"
195
+ sub "๐‘‡‘" "1"
196
+ sub "๐‘‡’" "2"
197
+ sub "๐‘‡“" "3"
198
+ sub "๐‘‡”" "4"
199
+ sub "๐‘‡•" "5"
200
+ sub "๐‘‡–" "6"
201
+ sub "๐‘‡—" "7"
202
+ sub "๐‘‡˜" "8"
203
+ sub "๐‘‡™" "9"
204
+ }
205
+
206
+ compose
207
+ }
208
+ }
@@ -35,6 +35,7 @@ metadata {
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
36
  note "In Malayalam text, เต acts as the mฤtrฤ for ลญ when final in a word, except when it removes the inherent vowel of a single\n consonant."
37
37
  note "The ambiguous pure consonant r/แนŸ (เตผ) in Malayalam script shall be transliterated into r when combined\n with another consonant; when it is final in a word it shall be transliterated as แนŸ in Malayalam language."
38
+ note "Official-edition finding (published ISO 15919:2001, owner-provided PDF): Table 9 does NOT print the letter U+0D3A (ttta) or any t-line-below row; the U+0D3A row seen in modern secondary transcriptions is a post-2001 extension and is not encoded. The official alveolar rows are ref 041a (n with line below, the letter today at U+0D29, encoded) and ref 049 (ra with line below, U+0D31, encoded); ref 052 prints la with line below (U+0D34, encoded). Table 9 also omits the second edition's chillu rows."
38
39
  }
39
40
  }
40
41
 
@@ -0,0 +1,223 @@
1
+ system "ISO:mal-Mlym:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:mal
7
+ source_script Mlym
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Malayalam; 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 7.9 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 "Table 7.9 prints malayalam virama U+0D4D as ลญ when final in a word (row note b); this is word-context-dependent and cannot be expressed by the substitution IR, so U+0D4D carries the clause 6 virama behavior (deleted, or ยท under opt10). The ลญ row remains documented here."
24
+ note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 51/58 printed rows; systematic divergences recorded as findings, not fixes: vocalic r/l rows (corpus แน›-family vs ISO rฬฅ-family), long e/o rows (corpus e/o vs ISO ฤ“/ล), avagraha (corpus :โ€™ vs ISO ')."
25
+ }
26
+ }
27
+
28
+ languages opt98 opt99 opt10
29
+
30
+ tests {
31
+ "เด…" -> "a"
32
+ "เด•" -> "ka"
33
+ "เด†" -> "ฤ"
34
+ "เดพ" -> "ฤ"
35
+ "เด–" -> "kha"
36
+ "เด‡" -> "i"
37
+ "เดฟ" -> "i"
38
+ "เด—" -> "ga"
39
+ "เดˆ" -> "ฤซ"
40
+ "เต€" -> "ฤซ"
41
+ "เด˜" -> "gha"
42
+ "เด‰" -> "u"
43
+ "เต" -> "u"
44
+ "เด™" -> "แน…a"
45
+ "เดŠ" -> "ลซ"
46
+ "เต‚" -> "ลซ"
47
+ "เดš" -> "ca"
48
+ "เด‹" -> "rฬฅ"
49
+ "เตƒ" -> "rฬฅ"
50
+ "เดœ" -> "ja"
51
+ "เต " -> "rฬฅฬ„"
52
+ "เต„" -> "rฬฅฬ„"
53
+ "เด" -> "jha"
54
+ "เดŒ" -> "lฬฅ"
55
+ "เตข" -> "lฬฅ"
56
+ "เดž" -> "รฑa"
57
+ "เตก" -> "lฬฅฬ„"
58
+ "เตฃ" -> "lฬฅฬ„"
59
+ "เดŸ" -> "แนญa"
60
+ "เดŽ" -> "e"
61
+ "เต†" -> "e"
62
+ "เด " -> "แนญha"
63
+ "เด" -> "ฤ“"
64
+ "เต‡" -> "ฤ“"
65
+ "เดก" -> "แธa"
66
+ "เด" -> "ai"
67
+ "เตˆ" -> "ai"
68
+ "เดข" -> "แธha"
69
+ "เด’" -> "o"
70
+ "เตŠ" -> "o"
71
+ "เดฃ" -> "แน‡a"
72
+ "เด“" -> "ล"
73
+ "เต‹" -> "ล"
74
+ "เด”" -> "au"
75
+ "เตŒ" -> "au"
76
+ "เดค" -> "ta"
77
+ "เดถ" -> "ล›a"
78
+ "เดฅ" -> "tha"
79
+ "เดท" -> "แนฃa"
80
+ "เดฆ" -> "da"
81
+ "เดธ" -> "sa"
82
+ "เดง" -> "dha"
83
+ "เดน" -> "ha"
84
+ "เดจ" -> "na"
85
+ "เดณ" -> "แธทa"
86
+ "เดช" -> "pa"
87
+ "เดด" -> "แธปa"
88
+ "เดซ" -> "pha"
89
+ "เดฑ" -> "แนŸa"
90
+ "เดฌ" -> "ba"
91
+ "เดฉ" -> "แน‰a"
92
+ "เดญ" -> "bha"
93
+ "เด‚" -> "แน"
94
+ "เดฎ" -> "ma"
95
+ "เดƒ" -> "แธฅ"
96
+ "เดฏ" -> "ya"
97
+ "เดฝ" -> "'"
98
+ "เดฐ" -> "ra"
99
+ "เดฒ" -> "la"
100
+ "เดต" -> "va"
101
+ "เตฆ" -> "0"
102
+ "เตง" -> "1"
103
+ "เตจ" -> "2"
104
+ "เตฉ" -> "3"
105
+ "เตช" -> "4"
106
+ "เตซ" -> "5"
107
+ "เตฌ" -> "6"
108
+ "เตญ" -> "7"
109
+ "เตฎ" -> "8"
110
+ "เตฏ" -> "9"
111
+ "เด›" -> "cha"
112
+ }
113
+
114
+ stage main {
115
+
116
+ # Table 7.9 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
117
+ parallel {
118
+
119
+ sub "เด…" "a"
120
+ sub "เด•" "ka"
121
+ sub "เด†" "ฤ"
122
+ sub "เดพ" "ฤ"
123
+ sub "เด†" "ฤ€" when opt98
124
+ sub "เด–" "kha"
125
+ sub "เด‡" "i"
126
+ sub "เดฟ" "i"
127
+ sub "เด‡" "I" when opt98
128
+ sub "เด—" "ga"
129
+ sub "เดˆ" "ฤซ"
130
+ sub "เต€" "ฤซ"
131
+ sub "เดˆ" "ฤช" when opt98
132
+ sub "เด˜" "gha"
133
+ sub "เด‰" "u"
134
+ sub "เต" "u"
135
+ sub "เด‰" "U" when opt98
136
+ sub "เด™" "แน…a"
137
+ sub "เดŠ" "ลซ"
138
+ sub "เต‚" "ลซ"
139
+ sub "เดŠ" "ลช" when opt98
140
+ sub "เดš" "ca"
141
+ sub "เด›" "cha"
142
+ sub "เด‹" "rฬฅ"
143
+ sub "เตƒ" "rฬฅ"
144
+ sub "เด‹" "Rฬฅ" when opt98
145
+ sub "เดœ" "ja"
146
+ sub "เต " "rฬฅฬ„"
147
+ sub "เต„" "rฬฅฬ„"
148
+ sub "เต " "Rฬฅฬ„" when opt98
149
+ sub "เด" "jha"
150
+ sub "เดŒ" "lฬฅ"
151
+ sub "เตข" "lฬฅ"
152
+ sub "เดŒ" "Lฬฅ" when opt98
153
+ sub "เดž" "รฑa"
154
+ sub "เตก" "lฬฅฬ„"
155
+ sub "เตฃ" "lฬฅฬ„"
156
+ sub "เตก" "Lฬฅฬ„" when opt98
157
+ sub "เดŸ" "แนญa"
158
+ sub "เดŽ" "e"
159
+ sub "เต†" "e"
160
+ sub "เดŽ" "E" when opt98
161
+ sub "เด " "แนญha"
162
+ sub "เด" "ฤ“"
163
+ sub "เต‡" "ฤ“"
164
+ sub "เด" "ฤ’" when opt98
165
+ sub "เดก" "แธa"
166
+ sub "เด" "ai"
167
+ sub "เตˆ" "ai"
168
+ sub "เด" "Ai" when opt98
169
+ sub "เดข" "แธha"
170
+ sub "เด’" "o"
171
+ sub "เตŠ" "o"
172
+ sub "เด’" "O" when opt98
173
+ sub "เดฃ" "แน‡a"
174
+ sub "เด“" "ล"
175
+ sub "เต‹" "ล"
176
+ sub "เด“" "ลŒ" when opt98
177
+ sub "เด”" "au"
178
+ sub "เตŒ" "au"
179
+ sub "เด”" "Au" when opt98
180
+ sub "เดค" "ta"
181
+ sub "เดถ" "ล›a"
182
+ sub "เดฅ" "tha"
183
+ sub "เดท" "แนฃa"
184
+ sub "เดฆ" "da"
185
+ sub "เดธ" "sa"
186
+ sub "เดง" "dha"
187
+ sub "เดน" "ha"
188
+ sub "เดจ" "na"
189
+ sub "เดณ" "แธทa"
190
+ sub "เดช" "pa"
191
+ sub "เดด" "แธปa"
192
+ sub "เดซ" "pha"
193
+ sub "เดฑ" "แนŸa"
194
+ sub "เดฌ" "ba"
195
+ sub "เดฉ" "แน‰a"
196
+ sub "เดญ" "bha"
197
+ sub "เด‚" "แน"
198
+ sub "เดฎ" "ma"
199
+ sub "เดƒ" "แธฅ"
200
+ sub "เดฏ" "ya"
201
+ sub "เดฝ" "'"
202
+ sub "เดฐ" "ra"
203
+ sub "เดฒ" "la"
204
+ sub "เดต" "va"
205
+ sub "เต" ""
206
+ sub "เต" "ยท" when opt10
207
+ sub "โ€" ""
208
+ sub "โ€" "=" when opt99
209
+ sub "เตฆ" "0"
210
+ sub "เตง" "1"
211
+ sub "เตจ" "2"
212
+ sub "เตฉ" "3"
213
+ sub "เตช" "4"
214
+ sub "เตซ" "5"
215
+ sub "เตฌ" "6"
216
+ sub "เตญ" "7"
217
+ sub "เตฎ" "8"
218
+ sub "เตฏ" "9"
219
+ }
220
+
221
+ compose
222
+ }
223
+ }
@@ -39,7 +39,7 @@ metadata {
39
39
  tests {
40
40
  "เค เคพเคฃเฅ‡ - เคœเคฟเคฒเฅเคนเฅเคฏเคพเคค เคฌเฅเคงเคตเคพเคฐเฅ€ เคเค• เคนเคœเคพเคฐ เคฐเฅเค—เฅเคฃเคพเค‚เคšเฅ€ เคตเคพเคข, เคคเคฐ เคœเคฃเคพเค‚เคšเฅเคฏเคพ เคฎเฅƒเคคเฅเคฏเฅ‚เคšเฅ€ เคจเฅ‹เค‚เคฆ" -> "แนญhaฤแน‡ae - jailahayaฤta baudhavaฤraฤซ eka hajaฤra raugaแน‡aฤแนcaฤซ vaฤแธha, tara jaแน‡aฤแนcayaฤ maแน›tayaลซcaฤซ naoแนda"
41
41
  "เคเค•เคคเคพ เค•เคชเฅ‚เคฐ เคชเฅเคจเฅเคนเคพ เค…เคกเค•เคฒเฅ€ เคตเคพเคฆเคพเคค, เคตเฅ‡เคฌเคธเฅ€เคฐเคฟเคœเคฎเคงเคฒเฅเคฏเคพ 'เคคเฅเคฏเคพ' เคธเฅ€เคจเคฎเฅเคณเฅ‡ เคœเคฎเคพเคตเคพเคšเฅ€ เค˜เคฐเคพเคตเคฐ เคฆเค—เคกเคซเฅ‡เค•" -> "ekataฤ kapaลซra paunahaฤ aแธakalaฤซ vaฤdaฤta, vaebasaฤซraijamadhalayaฤ 'tayaฤ' saฤซnamauแธทae jamaฤvaฤcaฤซ gharaฤvara dagaแธaphaeka"
42
- "เคœเคพเคฃเฅ‚เคจ เค˜เฅเคฏเคพ, เคฌเฅ€เคเคฎเคธเฅ€เคšเฅเคฏเคพ เค…เคงเคฟเค•เคพเคฑเฅเคฏเคพเค‚เคจเฅ€ เค•เค‚เค—เคจเคพ เคฐเคพเคฃเฅŒเคคเคšเฅเคฏเคพ เค‘เคซเคฟเคธเคฎเคงเคฒเฅ‡ เคจเค•เฅเค•เฅ€ เค•เคพเคฏ- เค•เคพเคฏ เคคเฅ‹เคกเคฒเค‚" -> "jaฤแน‡aลซna ghayaฤ, baฤซemasaฤซcayaฤ adhaikaฤเคฑyaฤแนnaฤซ kaแนganaฤ raฤแน‡aautacayaฤ รดphaisamadhalae nakakaฤซ kaฤya- kaฤya taoแธalaแน"
42
+ "เคœเคพเคฃเฅ‚เคจ เค˜เฅเคฏเคพ, เคฌเฅ€เคเคฎเคธเฅ€เคšเฅเคฏเคพ เค…เคงเคฟเค•เคพเคฑเฅเคฏเคพเค‚เคจเฅ€ เค•เค‚เค—เคจเคพ เคฐเคพเคฃเฅŒเคคเคšเฅเคฏเคพ เค‘เคซเคฟเคธเคฎเคงเคฒเฅ‡ เคจเค•เฅเค•เฅ€ เค•เคพเคฏ- เค•เคพเคฏ เคคเฅ‹เคกเคฒเค‚" -> "jaฤแน‡aลซna ghayaฤ, baฤซemasaฤซcayaฤ adhaikaฤrฬ†yaฤแนnaฤซ kaแนganaฤ raฤแน‡aautacayaฤ รดphaisamadhalae nakakaฤซ kaฤya- kaฤya taoแธalaแน"
43
43
  "เค•เค‚เค—เคจเคพ เคฎเฅเค‚เคฌเคˆเคค เคฆเคพเค–เคฒ เคนเฅ‹เคฃเฅเคฏเคพเคชเฅ‚เคฐเฅเคตเฅ€ 'เคฎเคพเคคเฅ‹เคถเฅเคฐเฅ€'เคตเคฐเฅ‚เคจ เคซเคฐเฅเคฎเคพเคจ เคธเฅเคŸเคฒเฅ‡; เคชเฅเคฐเคตเค•เฅเคคเฅเคฏเคพเค‚เคจเคพ เคธเค•เฅเคค เค†เคฆเฅ‡เคถ" -> "kaแนganaฤ mauแนbaฤซta daฤkhala haoแน‡ayaฤpaลซravaฤซ 'maฤtaoล›araฤซ'varaลซna pharamaฤna sauแนญalae; paravakatayaฤแนnaฤ sakata ฤdaeล›a"
44
44
  "เคฎเคฐเคพเค เคพ เค†เคฐเค•เฅเคทเคฃเคพเคธ เคคเคพเคคเฅเคชเฅเคฐเคคเฅ€ เคธเฅเคฅเค—เคฟเคคเฅ€; เคธเคฐเฅเคตเฅ‹เคšเฅเคš เคจเฅเคฏเคพเคฏเคพเคฒเคฏเคพเคšเคพ เคจเคฟเคฐเฅเคฃเคฏ" -> "maraฤแนญhaฤ ฤrakaแนฃaแน‡aฤsa taฤtapaurataฤซ sathagaitaฤซ; saravaocaca nayaฤyaฤlayaฤcaฤ nairaแน‡aya"
45
45
  "เคญเคพเคฐเคคเคพเคšเฅเคฏเคพ เคคเคฟเคจเฅเคนเฅ€ เคฒเคถเฅ€เค‚เคšเคพ เคชเคนเคฟเคฒเคพ เคŸเคชเฅเคชเคพ เคฏเคถเคธเฅเคตเฅ€, เคตเคพเคšเคพ เค•เคงเฅ€ เคฏเฅ‡เคฃเคพเคฐ เคฌเคพเคœเคพเคฐเคพเคค" -> "bhaฤrataฤcayaฤ tainahaฤซ laล›aฤซแนcaฤ pahailaฤ แนญapapaฤ yaล›asavaฤซ, vaฤcaฤ kadhaฤซ yaeแน‡aฤra baฤjaฤraฤta"
@@ -0,0 +1,204 @@
1
+ system "ISO:mar-Modi:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:mar
7
+ source_script Modi
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Marathi (Modi); 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 7.14 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
+ "๐‘˜€" -> "a"
30
+ "๐‘˜Ž" -> "ka"
31
+ "๐‘˜" -> "ฤ"
32
+ "๐‘˜ฐ" -> "ฤ"
33
+ "๐‘˜" -> "kha"
34
+ "๐‘˜‚" -> "i"
35
+ "๐‘˜ฑ" -> "i"
36
+ "๐‘˜" -> "ga"
37
+ "๐‘˜ƒ" -> "ฤซ"
38
+ "๐‘˜ฒ" -> "ฤซ"
39
+ "๐‘˜‘" -> "gha"
40
+ "๐‘˜„" -> "u"
41
+ "๐‘˜ณ" -> "u"
42
+ "๐‘˜’" -> "แน…a"
43
+ "๐‘˜…" -> "ลซ"
44
+ "๐‘˜ด" -> "ลซ"
45
+ "๐‘˜“" -> "ca"
46
+ "๐‘˜†" -> "rฬฅ"
47
+ "๐‘˜ต" -> "rฬฅ"
48
+ "๐‘˜”" -> "cha"
49
+ "๐‘˜‡" -> "rฬฅฬ„"
50
+ "๐‘˜ถ" -> "rฬฅฬ„"
51
+ "๐‘˜•" -> "ja"
52
+ "๐‘˜ˆ" -> "lฬฅ"
53
+ "๐‘˜ท" -> "lฬฅ"
54
+ "๐‘˜–" -> "jha"
55
+ "๐‘˜‰" -> "lฬฅฬ„"
56
+ "๐‘˜ธ" -> "lฬฅฬ„"
57
+ "๐‘˜—" -> "รฑa"
58
+ "๐‘˜Š" -> "ฤ“"
59
+ "๐‘˜น" -> "ฤ“"
60
+ "๐‘˜˜" -> "แนญa"
61
+ "๐‘˜‹" -> "ai"
62
+ "๐‘˜บ" -> "ai"
63
+ "๐‘˜™" -> "แนญha"
64
+ "๐‘˜Œ" -> "ล"
65
+ "๐‘˜ป" -> "ล"
66
+ "๐‘˜š" -> "แธa"
67
+ "๐‘˜" -> "au"
68
+ "๐‘˜ผ" -> "au"
69
+ "๐‘˜›" -> "แธha"
70
+ "๐‘˜" -> "ta"
71
+ "๐‘˜ง" -> "ya"
72
+ "๐‘˜ž" -> "tha"
73
+ "๐‘˜จ" -> "ra"
74
+ "๐‘˜Ÿ" -> "da"
75
+ "๐‘˜ฉ" -> "la"
76
+ "๐‘˜ " -> "dha"
77
+ "๐‘˜ช" -> "va"
78
+ "๐‘˜ก" -> "na"
79
+ "๐‘˜ซ" -> "ล›a"
80
+ "๐‘˜ข" -> "pa"
81
+ "๐‘˜ฌ" -> "แนฃa"
82
+ "๐‘˜ฃ" -> "pha"
83
+ "๐‘˜ญ" -> "sa"
84
+ "๐‘˜ค" -> "ba"
85
+ "๐‘˜ฎ" -> "ha"
86
+ "๐‘˜ฅ" -> "bha"
87
+ "๐‘˜ฏ" -> "แธทa"
88
+ "๐‘˜ฆ" -> "ma"
89
+ "๐‘™" -> "0"
90
+ "๐‘™‘" -> "1"
91
+ "๐‘™’" -> "2"
92
+ "๐‘™“" -> "3"
93
+ "๐‘™”" -> "4"
94
+ "๐‘™•" -> "5"
95
+ "๐‘™–" -> "6"
96
+ "๐‘™—" -> "7"
97
+ "๐‘™˜" -> "8"
98
+ "๐‘™™" -> "9"
99
+ "๐‘˜œ" -> "แน‡a"
100
+ "๐‘˜ฝ" -> "แน"
101
+ "๐‘˜พ" -> "แธฅ"
102
+ }
103
+
104
+ stage main {
105
+
106
+ # Table 7.14 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
107
+ parallel {
108
+
109
+ sub "๐‘˜€" "a"
110
+ sub "๐‘˜€" "A" when opt98
111
+ sub "๐‘˜Ž" "ka"
112
+ sub "๐‘˜" "ฤ"
113
+ sub "๐‘˜ฐ" "ฤ"
114
+ sub "๐‘˜" "ฤ€" when opt98
115
+ sub "๐‘˜" "kha"
116
+ sub "๐‘˜‚" "i"
117
+ sub "๐‘˜ฑ" "i"
118
+ sub "๐‘˜‚" "I" when opt98
119
+ sub "๐‘˜" "ga"
120
+ sub "๐‘˜ƒ" "ฤซ"
121
+ sub "๐‘˜ฒ" "ฤซ"
122
+ sub "๐‘˜ƒ" "ฤช" when opt98
123
+ sub "๐‘˜‘" "gha"
124
+ sub "๐‘˜„" "u"
125
+ sub "๐‘˜ณ" "u"
126
+ sub "๐‘˜„" "U" when opt98
127
+ sub "๐‘˜’" "แน…a"
128
+ sub "๐‘˜…" "ลซ"
129
+ sub "๐‘˜ด" "ลซ"
130
+ sub "๐‘˜…" "ลช" when opt98
131
+ sub "๐‘˜“" "ca"
132
+ sub "๐‘˜†" "rฬฅ"
133
+ sub "๐‘˜ต" "rฬฅ"
134
+ sub "๐‘˜†" "Rฬฅ" when opt98
135
+ sub "๐‘˜”" "cha"
136
+ sub "๐‘˜‡" "rฬฅฬ„"
137
+ sub "๐‘˜ถ" "rฬฅฬ„"
138
+ sub "๐‘˜‡" "Rฬฅฬ„" when opt98
139
+ sub "๐‘˜•" "ja"
140
+ sub "๐‘˜ˆ" "lฬฅ"
141
+ sub "๐‘˜ท" "lฬฅ"
142
+ sub "๐‘˜ˆ" "Lฬฅ" when opt98
143
+ sub "๐‘˜–" "jha"
144
+ sub "๐‘˜‰" "lฬฅฬ„"
145
+ sub "๐‘˜ธ" "lฬฅฬ„"
146
+ sub "๐‘˜‰" "Lฬฅฬ„" when opt98
147
+ sub "๐‘˜—" "รฑa"
148
+ sub "๐‘˜Š" "ฤ“"
149
+ sub "๐‘˜น" "ฤ“"
150
+ sub "๐‘˜Š" "ฤ’" when opt98
151
+ sub "๐‘˜˜" "แนญa"
152
+ sub "๐‘˜‹" "ai"
153
+ sub "๐‘˜บ" "ai"
154
+ sub "๐‘˜‹" "Ai" when opt98
155
+ sub "๐‘˜™" "แนญha"
156
+ sub "๐‘˜Œ" "ล"
157
+ sub "๐‘˜ป" "ล"
158
+ sub "๐‘˜Œ" "ลŒ" when opt98
159
+ sub "๐‘˜š" "แธa"
160
+ sub "๐‘˜" "au"
161
+ sub "๐‘˜ผ" "au"
162
+ sub "๐‘˜" "Au" when opt98
163
+ sub "๐‘˜›" "แธha"
164
+ sub "๐‘˜œ" "แน‡a"
165
+ sub "๐‘˜" "ta"
166
+ sub "๐‘˜ง" "ya"
167
+ sub "๐‘˜ž" "tha"
168
+ sub "๐‘˜จ" "ra"
169
+ sub "๐‘˜Ÿ" "da"
170
+ sub "๐‘˜ฉ" "la"
171
+ sub "๐‘˜ " "dha"
172
+ sub "๐‘˜ช" "va"
173
+ sub "๐‘˜ก" "na"
174
+ sub "๐‘˜ซ" "ล›a"
175
+ sub "๐‘˜ข" "pa"
176
+ sub "๐‘˜ฌ" "แนฃa"
177
+ sub "๐‘˜ฃ" "pha"
178
+ sub "๐‘˜ญ" "sa"
179
+ sub "๐‘˜ค" "ba"
180
+ sub "๐‘˜ฎ" "ha"
181
+ sub "๐‘˜ฅ" "bha"
182
+ sub "๐‘˜ฏ" "แธทa"
183
+ sub "๐‘˜ฆ" "ma"
184
+ sub "๐‘˜ฝ" "แน"
185
+ sub "๐‘˜พ" "แธฅ"
186
+ sub "๐‘˜ฟ" ""
187
+ sub "๐‘˜ฟ" "ยท" when opt10
188
+ sub "โ€" ""
189
+ sub "โ€" "=" when opt99
190
+ sub "๐‘™" "0"
191
+ sub "๐‘™‘" "1"
192
+ sub "๐‘™’" "2"
193
+ sub "๐‘™“" "3"
194
+ sub "๐‘™”" "4"
195
+ sub "๐‘™•" "5"
196
+ sub "๐‘™–" "6"
197
+ sub "๐‘™—" "7"
198
+ sub "๐‘™˜" "8"
199
+ sub "๐‘™™" "9"
200
+ }
201
+
202
+ compose
203
+ }
204
+ }