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.
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 +1,197 @@
1
+ system "ISO:inc-Kthi:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:inc
7
+ source_script Kthi
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Indo-Aryan (Kaithi); 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 7.13 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 Kai. 110B9 (unassigned); corrected to Kaithi sign virama 110C1."
24
+ note "DIS erratum recorded: Table 7.13 vocalic r row prints Initial 110A9 110B2 (RA + II sign) with Sign 110C2 (unassigned codepoint; Kaithi sign virama is 110C1). The row is encoded exactly as printed as one three-character sequence mapping to r̥; flagged in the corpus PR for the ISO committee."
25
+ }
26
+ }
27
+
28
+ languages opt98 opt99 opt10
29
+
30
+ tests {
31
+ "𑂃" -> "a"
32
+ "𑂄" -> "ā"
33
+ "𑂰" -> "ā"
34
+ "𑂅" -> "i"
35
+ "𑂱" -> "i"
36
+ "𑂆" -> "ī"
37
+ "𑂲" -> "ī"
38
+ "𑂇" -> "u"
39
+ "𑂳" -> "u"
40
+ "𑂈" -> "ū"
41
+ "𑂴" -> "ū"
42
+ "𑂩𑂲" -> "r̥"
43
+ "𑃂" -> "r̥"
44
+ "𑂉" -> "ē"
45
+ "𑂵" -> "ē"
46
+ "𑂊" -> "ai"
47
+ "𑂶" -> "ai"
48
+ "𑂋" -> "ō"
49
+ "𑂷" -> "ō"
50
+ "𑂌" -> "au"
51
+ "𑂸" -> "au"
52
+ "𑂍" -> "ka"
53
+ "𑂠" -> "da"
54
+ "𑂎" -> "kha"
55
+ "𑂡" -> "dha"
56
+ "𑂏" -> "ga"
57
+ "𑂢" -> "na"
58
+ "𑂐" -> "gha"
59
+ "𑂣" -> "pa"
60
+ "𑂑" -> "ṅa"
61
+ "𑂤" -> "pha"
62
+ "𑂒" -> "ca"
63
+ "𑂥" -> "ba"
64
+ "𑂓" -> "cha"
65
+ "𑂦" -> "bha"
66
+ "𑂔" -> "ja"
67
+ "𑂧" -> "ma"
68
+ "𑂕" -> "jha"
69
+ "𑂨" -> "ya"
70
+ "𑂖" -> "ña"
71
+ "𑂩" -> "ra"
72
+ "𑂗" -> "ṭa"
73
+ "𑂪" -> "la"
74
+ "𑂘" -> "ṭha"
75
+ "𑂫" -> "va"
76
+ "𑂙" -> "ḍa"
77
+ "𑂬" -> "śa"
78
+ "𑂚" -> "ṛa"
79
+ "𑂭" -> "ṣa"
80
+ "𑂛" -> "ḍha"
81
+ "𑂮" -> "sa"
82
+ "𑂜" -> "ṛha"
83
+ "𑂯" -> "ha"
84
+ "𑂝" -> "ṇa"
85
+ "𑂞" -> "ta"
86
+ "𑂟" -> "tha"
87
+ "ᄊ9ᄋ2ᄌ2" -> "r̥"
88
+ "०" -> "0"
89
+ "१" -> "1"
90
+ "२" -> "2"
91
+ "३" -> "3"
92
+ "४" -> "4"
93
+ "५" -> "5"
94
+ "६" -> "6"
95
+ "७" -> "7"
96
+ "८" -> "8"
97
+ "९" -> "9"
98
+ "𑂀" -> "m̐"
99
+ "𑂁" -> "ṁ"
100
+ "𑂂" -> "ḥ"
101
+ }
102
+
103
+ stage main {
104
+
105
+ # Table 7.13 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
106
+ parallel {
107
+
108
+ sub "𑂃" "a"
109
+ sub "𑂃" "A" when opt98
110
+ sub "𑂄" "ā"
111
+ sub "𑂰" "ā"
112
+ sub "𑂄" "Ā" when opt98
113
+ sub "𑂅" "i"
114
+ sub "𑂱" "i"
115
+ sub "𑂅" "I" when opt98
116
+ sub "𑂆" "ī"
117
+ sub "𑂲" "ī"
118
+ sub "𑂆" "Ī" when opt98
119
+ sub "𑂇" "u"
120
+ sub "𑂳" "u"
121
+ sub "𑂇" "U" when opt98
122
+ sub "𑂈" "ū"
123
+ sub "𑂴" "ū"
124
+ sub "𑂈" "Ū" when opt98
125
+ sub "𑂩𑂲" "r̥"
126
+ sub "𑃂" "r̥"
127
+ sub "𑂩𑂲" "R̥" when opt98
128
+ sub "𑂉" "ē"
129
+ sub "𑂵" "ē"
130
+ sub "𑂉" "Ē" when opt98
131
+ sub "𑂊" "ai"
132
+ sub "𑂶" "ai"
133
+ sub "𑂊" "Ai" when opt98
134
+ sub "𑂋" "ō"
135
+ sub "𑂷" "ō"
136
+ sub "𑂋" "Ō" when opt98
137
+ sub "𑂌" "au"
138
+ sub "𑂸" "au"
139
+ sub "𑂌" "Au" when opt98
140
+ sub "𑂍" "ka"
141
+ sub "𑂠" "da"
142
+ sub "𑂎" "kha"
143
+ sub "𑂡" "dha"
144
+ sub "𑂏" "ga"
145
+ sub "𑂢" "na"
146
+ sub "𑂐" "gha"
147
+ sub "𑂣" "pa"
148
+ sub "𑂑" "ṅa"
149
+ sub "𑂤" "pha"
150
+ sub "𑂒" "ca"
151
+ sub "𑂥" "ba"
152
+ sub "𑂓" "cha"
153
+ sub "𑂦" "bha"
154
+ sub "𑂔" "ja"
155
+ sub "𑂧" "ma"
156
+ sub "𑂕" "jha"
157
+ sub "𑂨" "ya"
158
+ sub "𑂖" "ña"
159
+ sub "𑂩" "ra"
160
+ sub "𑂗" "ṭa"
161
+ sub "𑂪" "la"
162
+ sub "𑂘" "ṭha"
163
+ sub "𑂫" "va"
164
+ sub "𑂙" "ḍa"
165
+ sub "𑂬" "śa"
166
+ sub "𑂚" "ṛa"
167
+ sub "𑂭" "ṣa"
168
+ sub "𑂛" "ḍha"
169
+ sub "𑂮" "sa"
170
+ sub "𑂜" "ṛha"
171
+ sub "𑂯" "ha"
172
+ sub "𑂝" "ṇa"
173
+ sub "𑂞" "ta"
174
+ sub "𑂟" "tha"
175
+ sub "ᄊ9ᄋ2ᄌ2" "r̥"
176
+ sub "𑂀" "m̐"
177
+ sub "𑂁" "ṁ"
178
+ sub "𑂂" "ḥ"
179
+ sub "𑃁" ""
180
+ sub "𑃁" "·" when opt10
181
+ sub "‍" ""
182
+ sub "‍" "=" when opt99
183
+ sub "०" "0"
184
+ sub "१" "1"
185
+ sub "२" "2"
186
+ sub "३" "3"
187
+ sub "४" "4"
188
+ sub "५" "5"
189
+ sub "६" "6"
190
+ sub "७" "7"
191
+ sub "८" "8"
192
+ sub "९" "9"
193
+ }
194
+
195
+ compose
196
+ }
197
+ }
@@ -17,6 +17,11 @@ metadata {
17
17
  }
18
18
 
19
19
  notes {
20
+ note "Verified against the official ISO 3602:1989 document (Table 1: 72 signs, Table 2: 36 digraphs, Table 3a: 83 long-vowel digraphs, Table 3b: 36 trigraphs, clauses 1-6)."
21
+ note "Kunrei-siki tables are supplied by the mext-jpn-Hrkt-Latn-1954 dependency; this map adds ISO 3602 Table 3a rows absent there (the consonant + i long vowels kei -> ke, sei -> se, tei -> te, nei -> ne, hei -> he, mei -> me, rei -> re, gei -> ge, zei -> ze, dei -> de, bei -> be, pei -> pe with circumflex)."
22
+ note "Table 1 footnote particle readings (26 ha/wa, 29 he/e, 45 wo) and the NOTE strict-transliteration variants (wo, du, dya/dyu/dyo, macron for the lengthening bar) are language-dependent or strict-scheme alternatives; this map implements the standard transcription values (ha, he, o, zi, zu, zya/zyu/zyo, circumflex)."
23
+ note "Clause 4: a mid-dot marker separates morphemes to block long-vowel collapse (kou•si vs ko•ushi)."
24
+ note "Clause 6: Japanese punctuation marks are transcribed (ideographic full stop -> full stop, comma, katakana middle dot -> hyphen, corner brackets -> quotation marks, fullwidth parentheses)."
20
25
  }
21
26
  }
22
27
 
@@ -36,6 +41,14 @@ tests {
36
41
  "こう•し" -> "kôsi" #格子
37
42
  "こ•うし" -> "kousi" #子牛
38
43
  "ぎゃあ" -> "gyâ"
44
+ "げいじゅつ" -> "gêzyutu"
45
+ "えいが" -> "eiga"
46
+ "け•いき" -> "keiki"
47
+ "げいき" -> "gêki"
48
+ "とうきょう、にっぽん。" -> "tôkyô,nippon."
49
+ "「がっこう」" -> "“gakkô”"
50
+ "ビール" -> "bîru"
51
+ "ラーメン" -> "râmen"
39
52
  }
40
53
 
41
54
  dependency "mext-jpn-Hrkt-Latn-1954" as hrktlatn
@@ -51,6 +64,37 @@ stage main {
51
64
  }
52
65
 
53
66
 
67
+ # ISO 3602 Table 3a - consonant + i long-vowel digraphs (rows for
68
+ # kei sei tei nei hei mei rei gei zei dei bei pei). Applied before the
69
+ # run so a morpheme-boundary marker inside the sequence still blocks
70
+ # the collapse (ke•i -> kei).
71
+ parallel {
72
+ sub "けい" "kê"
73
+ sub "せい" "sê"
74
+ sub "てい" "tê"
75
+ sub "ねい" "nê"
76
+ sub "へい" "hê"
77
+ sub "めい" "mê"
78
+ sub "れい" "rê"
79
+ sub "げい" "gê"
80
+ sub "ぜい" "zê"
81
+ sub "でい" "dê"
82
+ sub "べい" "bê"
83
+ sub "ぺい" "pê"
84
+ sub "ケイ" "Kê"
85
+ sub "セイ" "Sê"
86
+ sub "テイ" "Tê"
87
+ sub "ネイ" "Nê"
88
+ sub "ヘイ" "Hê"
89
+ sub "メイ" "Mê"
90
+ sub "レイ" "Rê"
91
+ sub "ゲイ" "Gê"
92
+ sub "ゼイ" "Zê"
93
+ sub "デイ" "Dê"
94
+ sub "ベイ" "Bê"
95
+ sub "ペイ" "Pê"
96
+ }
97
+
54
98
  run map.hrktlatn.stage.main
55
99
 
56
100
 
@@ -61,6 +105,15 @@ stage main {
61
105
  # Use ’ instead of '
62
106
  sub "'" "’"
63
107
 
108
+ # Clause 6 - punctuation
109
+ sub "。" "."
110
+ sub "、" ","
111
+ sub "・" "-"
112
+ sub "「" "“"
113
+ sub "」" "”"
114
+ sub "(" "("
115
+ sub ")" ")"
116
+
64
117
 
65
118
  }
66
119
  }
@@ -32,6 +32,8 @@ 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."
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 "Per-script extension cell (ISO 15919:2001 Kannada table, U+0CDE): transliterated la with line below + inherent a (U+1E3B 0061), per the owner-blessed transcription source; the second edition (DIS N125 Table 7.8) also prints this row (hex 1E3B)."
36
+ note "Adjudicated against the published ISO 15919:2001 edition: Table 8 refs 131a and 131b print the Kannada jihvamuliya and upadhmaniya signs with the transliterations h with dot below + combining macron below (0068 0331) and h with dot below + combining breve below (0068 032E); the single-character forms 1E96/1E2B are the second edition's Rule 17 values. Table 8 ref 222 prints the letter U+0CDE with la + line below + inherent a (1E3B 0061), confirming the encoded extension row; refs 156a/171a print the za and fa values as ja/pha + nukta combinations, already encoded."
35
37
  }
36
38
  }
37
39
 
@@ -48,6 +50,7 @@ tests {
48
50
  "ಕೆಲವು ತಿಂಗಳಿಂದ ರಷ್ಯಾ ದೇಶದ ಏನಾಟೊಲಿ ಇವ್ಯಾನಿಶಿನ್‌ ಮತ್ತು ಇವಾನ್‌ ವ್ಯಾಗನರ್‌ ಹಾಗೂ ಅಮೆರಿಕಾದ ಕ್ರಿಸ್‌ ಕ್ಯಾಸಿಡಿ ಈ ಉಪಗ್ರಹದಲ್ಲಿ ವಾಸಿಸುತ್ತಿದ್ದಾರೆ" -> "kaelavau taiṁgaḷaiṁda raṣayaā daēśada ēnaāṭaeūlai ivayaānaiśaina matatau ivaāna vayaāganara haāgaū amaeraikaāda karaisa kayaāsaiḍai ī upagarahadalalai vaāsaisautataidadaārae"
49
51
  "ಹಾಂಗ್ ಕಾಂಗ್" -> "haāṁga kaāṁga"
50
52
  "೧೮೧೪೦" -> "18140"
53
+ "ೞ" -> "ḻa"
51
54
  }
52
55
 
53
56
  stage main {
@@ -131,8 +134,8 @@ stage main {
131
134
  # Bisarga
132
135
  sub "ಃ" "ḥ"
133
136
 
134
- sub "ೱ" "ẖ"
135
- sub "ೲ" "ḫ"
137
+ sub "ೱ" "ḥ̱"
138
+ sub "ೲ" "ḥ̮"
136
139
 
137
140
 
138
141
  # candrabindu
@@ -145,6 +148,7 @@ stage main {
145
148
  # Anusvāra
146
149
  sub "ಂ" "ṁ"
147
150
 
151
+ sub "ೞ" "ḻa"
148
152
  sub "಼" ""
149
153
 
150
154
  # Medials # Needed for connecting constants
@@ -156,8 +160,8 @@ stage main {
156
160
 
157
161
  sub "ೃ" "ṛ"
158
162
  sub "ೄ" "ṝ"
159
- sub " ೢ" "ḷ"
160
- sub " ೣ" "ḹ"
163
+ sub "ೢ" "ḷ"
164
+ sub "ೣ" "ḹ"
161
165
 
162
166
  sub "ೆ" "e"
163
167
  sub "ೇ" "ē"
@@ -0,0 +1,229 @@
1
+ system "ISO:kan-Kana:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:kan
7
+ source_script Kana
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Kannada; 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 7.8 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 (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 53/59 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 ')."
24
+ }
25
+ }
26
+
27
+ languages opt98 opt99 opt10
28
+
29
+ tests {
30
+ "ಅ" -> "a"
31
+ "ಕ" -> "ka"
32
+ "ಆ" -> "ā"
33
+ "ಾ" -> "ā"
34
+ "ಖ" -> "kha"
35
+ "ಇ" -> "i"
36
+ "ಿ" -> "i"
37
+ "ಗ" -> "ga"
38
+ "ಈ" -> "ī"
39
+ "ೀ" -> "ī"
40
+ "ಘ" -> "gha"
41
+ "ಉ" -> "u"
42
+ "ು" -> "u"
43
+ "ಙ" -> "ṅa"
44
+ "ಊ" -> "ū"
45
+ "ೂ" -> "ū"
46
+ "ಚ" -> "ca"
47
+ "ಋ" -> "r̥"
48
+ "ೃ" -> "r̥"
49
+ "ಛ" -> "cha"
50
+ "ೠ" -> "r̥̄"
51
+ "ೄ" -> "r̥̄"
52
+ "ಜ" -> "ja"
53
+ "ಌ" -> "l̥"
54
+ "ೢ" -> "l̥"
55
+ "ಝ" -> "jha"
56
+ "ೡ" -> "l̥̄"
57
+ "ೣ" -> "l̥̄"
58
+ "ಞ" -> "ña"
59
+ "ಎ" -> "e"
60
+ "ೆ" -> "e"
61
+ "ಟ" -> "ṭa"
62
+ "ಏ" -> "ē"
63
+ "ೇ" -> "ē"
64
+ "ಠ" -> "ṭha"
65
+ "ಐ" -> "ai"
66
+ "ೈ" -> "ai"
67
+ "ಡ" -> "ḍa"
68
+ "ಒ" -> "o"
69
+ "ೊ" -> "o"
70
+ "ಢ" -> "ḍha"
71
+ "ಓ" -> "ō"
72
+ "ೋ" -> "ō"
73
+ "ಣ" -> "ṇa"
74
+ "ಔ" -> "au"
75
+ "ೌ" -> "au"
76
+ "ತ" -> "ta"
77
+ "ಶ" -> "śa"
78
+ "ಥ" -> "tha"
79
+ "ಷ" -> "ṣa"
80
+ "ದ" -> "da"
81
+ "ಸ" -> "sa"
82
+ "ಧ" -> "dha"
83
+ "ಹ" -> "ha"
84
+ "ನ" -> "na"
85
+ "ಳ" -> "ḷa"
86
+ "ಪ" -> "pa"
87
+ "ಱ" -> "ṟa"
88
+ "ಫ" -> "pha"
89
+ "ೞ" -> "ḻa"
90
+ "ಬ" -> "ba"
91
+ "ಜ಼" -> "za"
92
+ "ಭ" -> "bha"
93
+ "ಫ಼" -> "fa"
94
+ "ಮ" -> "ma"
95
+ "ಂ" -> "ṁ"
96
+ "ಯ" -> "ya"
97
+ "ಃ" -> "ḥ"
98
+ "ರ" -> "ra"
99
+ "ೱ" -> "ẖ"
100
+ "ಲ" -> "la"
101
+ "ೲ" -> "ḫ"
102
+ "ವ" -> "va"
103
+ "ಽ" -> "'"
104
+ "೦" -> "0"
105
+ "೧" -> "1"
106
+ "೨" -> "2"
107
+ "೩" -> "3"
108
+ "೪" -> "4"
109
+ "೫" -> "5"
110
+ "೬" -> "6"
111
+ "೭" -> "7"
112
+ "೮" -> "8"
113
+ "೯" -> "9"
114
+ }
115
+
116
+ stage main {
117
+
118
+ # Table 7.8 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
119
+ parallel {
120
+
121
+ sub "ಅ" "a"
122
+ sub "ಅ" "A" when opt98
123
+ sub "ಕ" "ka"
124
+ sub "ಆ" "ā"
125
+ sub "ಾ" "ā"
126
+ sub "ಆ" "Ā" when opt98
127
+ sub "ಖ" "kha"
128
+ sub "ಇ" "i"
129
+ sub "ಿ" "i"
130
+ sub "ಇ" "I" when opt98
131
+ sub "ಗ" "ga"
132
+ sub "ಈ" "ī"
133
+ sub "ೀ" "ī"
134
+ sub "ಈ" "Ī" when opt98
135
+ sub "ಘ" "gha"
136
+ sub "ಉ" "u"
137
+ sub "ು" "u"
138
+ sub "ಉ" "U" when opt98
139
+ sub "ಙ" "ṅa"
140
+ sub "ಊ" "ū"
141
+ sub "ೂ" "ū"
142
+ sub "ಊ" "Ū" when opt98
143
+ sub "ಚ" "ca"
144
+ sub "ಋ" "r̥"
145
+ sub "ೃ" "r̥"
146
+ sub "ಋ" "R̥" when opt98
147
+ sub "ಛ" "cha"
148
+ sub "ೠ" "r̥̄"
149
+ sub "ೄ" "r̥̄"
150
+ sub "ೠ" "R̥̄" when opt98
151
+ sub "ಜ" "ja"
152
+ sub "ಌ" "l̥"
153
+ sub "ೢ" "l̥"
154
+ sub "ಌ" "L̥" when opt98
155
+ sub "ಝ" "jha"
156
+ sub "ೡ" "l̥̄"
157
+ sub "ೣ" "l̥̄"
158
+ sub "ೡ" "L̥̄" when opt98
159
+ sub "ಞ" "ña"
160
+ sub "ಎ" "e"
161
+ sub "ೆ" "e"
162
+ sub "ಎ" "E" when opt98
163
+ sub "ಟ" "ṭa"
164
+ sub "ಏ" "ē"
165
+ sub "ೇ" "ē"
166
+ sub "ಏ" "Ē" when opt98
167
+ sub "ಠ" "ṭha"
168
+ sub "ಐ" "ai"
169
+ sub "ೈ" "ai"
170
+ sub "ಐ" "Ai" when opt98
171
+ sub "ಡ" "ḍa"
172
+ sub "ಒ" "o"
173
+ sub "ೊ" "o"
174
+ sub "ಒ" "O" when opt98
175
+ sub "ಢ" "ḍha"
176
+ sub "ಓ" "ō"
177
+ sub "ೋ" "ō"
178
+ sub "ಓ" "Ō" when opt98
179
+ sub "ಣ" "ṇa"
180
+ sub "ಔ" "au"
181
+ sub "ೌ" "au"
182
+ sub "ಔ" "Au" when opt98
183
+ sub "ತ" "ta"
184
+ sub "ಶ" "śa"
185
+ sub "ಥ" "tha"
186
+ sub "ಷ" "ṣa"
187
+ sub "ದ" "da"
188
+ sub "ಸ" "sa"
189
+ sub "ಧ" "dha"
190
+ sub "ಹ" "ha"
191
+ sub "ನ" "na"
192
+ sub "ಳ" "ḷa"
193
+ sub "ಪ" "pa"
194
+ sub "ಱ" "ṟa"
195
+ sub "ಫ" "pha"
196
+ sub "ೞ" "ḻa"
197
+ sub "ಬ" "ba"
198
+ sub "ಜ಼" "za"
199
+ sub "ಭ" "bha"
200
+ sub "ಫ಼" "fa"
201
+ sub "ಮ" "ma"
202
+ sub "ಂ" "ṁ"
203
+ sub "ಯ" "ya"
204
+ sub "ಃ" "ḥ"
205
+ sub "ರ" "ra"
206
+ sub "ೱ" "ẖ"
207
+ sub "ಲ" "la"
208
+ sub "ೲ" "ḫ"
209
+ sub "ವ" "va"
210
+ sub "ಽ" "'"
211
+ sub "್" ""
212
+ sub "್" "·" when opt10
213
+ sub "‍" ""
214
+ sub "‍" "=" when opt99
215
+ sub "೦" "0"
216
+ sub "೧" "1"
217
+ sub "೨" "2"
218
+ sub "೩" "3"
219
+ sub "೪" "4"
220
+ sub "೫" "5"
221
+ sub "೬" "6"
222
+ sub "೭" "7"
223
+ sub "೮" "8"
224
+ sub "೯" "9"
225
+ }
226
+
227
+ compose
228
+ }
229
+ }