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 +1,178 @@
1
+ system "ISO:tam-Taml:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:tam
7
+ source_script Taml
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Tamil; 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 7.6 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 36/37 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
+ "அ" -> "a"
31
+ "த" -> "ta"
32
+ "ஆ" -> "ā"
33
+ "ா" -> "ā"
34
+ "ந" -> "na"
35
+ "இ" -> "i"
36
+ "ி" -> "i"
37
+ "ப" -> "pa"
38
+ "ஈ" -> "ī"
39
+ "ீ" -> "ī"
40
+ "ம" -> "ma"
41
+ "உ" -> "u"
42
+ "ு" -> "u"
43
+ "ய" -> "ya"
44
+ "ஊ" -> "ū"
45
+ "ூ" -> "ū"
46
+ "ர" -> "ra"
47
+ "எ" -> "e"
48
+ "ெ" -> "e"
49
+ "ல" -> "la"
50
+ "ஏ" -> "ē"
51
+ "ே" -> "ē"
52
+ "வ" -> "va"
53
+ "ஐ" -> "ai"
54
+ "ை" -> "ai"
55
+ "ழ" -> "ḻa"
56
+ "ஒ" -> "o"
57
+ "ொ" -> "o"
58
+ "ள" -> "ḷa"
59
+ "ஓ" -> "ō"
60
+ "ோ" -> "ō"
61
+ "ற" -> "ṟa"
62
+ "ஔ" -> "au"
63
+ "ௌ" -> "au"
64
+ "ன" -> "ṉa"
65
+ "ஃ" -> "ḵ"
66
+ "ஜ" -> "ja"
67
+ "க" -> "ka"
68
+ "ஶ" -> "śa"
69
+ "ங" -> "ṅa"
70
+ "ஷ" -> "ṣa"
71
+ "ச" -> "ca"
72
+ "ஸ" -> "sa"
73
+ "ஞ" -> "ña"
74
+ "ஹ" -> "ha"
75
+ "ட" -> "ṭa"
76
+ "ண" -> "ṇa"
77
+ "௦" -> "0"
78
+ "௧" -> "1"
79
+ "௨" -> "2"
80
+ "௩" -> "3"
81
+ "௪" -> "4"
82
+ "௫" -> "5"
83
+ "௬" -> "6"
84
+ "௭" -> "7"
85
+ "௮" -> "8"
86
+ "௯" -> "9"
87
+ }
88
+
89
+ stage main {
90
+
91
+ # Table 7.6 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
92
+ parallel {
93
+
94
+ sub "அ" "a"
95
+ sub "அ" "A" when opt98
96
+ sub "த" "ta"
97
+ sub "ஆ" "ā"
98
+ sub "ா" "ā"
99
+ sub "ஆ" "Ā" when opt98
100
+ sub "ந" "na"
101
+ sub "இ" "i"
102
+ sub "ி" "i"
103
+ sub "இ" "I" when opt98
104
+ sub "ப" "pa"
105
+ sub "ஈ" "ī"
106
+ sub "ீ" "ī"
107
+ sub "ஈ" "Ī" when opt98
108
+ sub "ம" "ma"
109
+ sub "உ" "u"
110
+ sub "ு" "u"
111
+ sub "உ" "U" when opt98
112
+ sub "ய" "ya"
113
+ sub "ஊ" "ū"
114
+ sub "ூ" "ū"
115
+ sub "ஊ" "Ū" when opt98
116
+ sub "ர" "ra"
117
+ sub "எ" "e"
118
+ sub "ெ" "e"
119
+ sub "எ" "E" when opt98
120
+ sub "ல" "la"
121
+ sub "ஏ" "ē"
122
+ sub "ே" "ē"
123
+ sub "ஏ" "Ē" when opt98
124
+ sub "வ" "va"
125
+ sub "ஐ" "ai"
126
+ sub "ை" "ai"
127
+ sub "ஐ" "Ai" when opt98
128
+ sub "ழ" "ḻa"
129
+ sub "ஒ" "o"
130
+ sub "ொ" "o"
131
+ sub "ஒ" "O" when opt98
132
+ sub "ள" "ḷa"
133
+ sub "ஓ" "ō"
134
+ sub "ோ" "ō"
135
+ sub "ஓ" "Ō" when opt98
136
+ sub "ற" "ṟa"
137
+ sub "ஔ" "au"
138
+ sub "ௌ" "au"
139
+ sub "ஔ" "Au" when opt98
140
+ sub "ன" "ṉa"
141
+ sub "ஃ" "ḵ"
142
+ sub "ஃ" "Ḵ" when opt98
143
+ sub "ஜ" "ja"
144
+ sub "க" "ka"
145
+ sub "க" "Ka" when opt98
146
+ sub "ஶ" "śa"
147
+ sub "ங" "ṅa"
148
+ sub "ங" "Ṅa" when opt98
149
+ sub "ஷ" "ṣa"
150
+ sub "ச" "ca"
151
+ sub "ச" "Ca" when opt98
152
+ sub "ஸ" "sa"
153
+ sub "ஞ" "ña"
154
+ sub "ஞ" "Ña" when opt98
155
+ sub "ஹ" "ha"
156
+ sub "ட" "ṭa"
157
+ sub "ட" "Ṭa" when opt98
158
+ sub "ண" "ṇa"
159
+ sub "ண" "Ṇa" when opt98
160
+ sub "்" ""
161
+ sub "்" "·" when opt10
162
+ sub "‍" ""
163
+ sub "‍" "=" when opt99
164
+ sub "௦" "0"
165
+ sub "௧" "1"
166
+ sub "௨" "2"
167
+ sub "௩" "3"
168
+ sub "௪" "4"
169
+ sub "௫" "5"
170
+ sub "௬" "6"
171
+ sub "௭" "7"
172
+ sub "௮" "8"
173
+ sub "௯" "9"
174
+ }
175
+
176
+ compose
177
+ }
178
+ }
@@ -33,6 +33,7 @@ metadata {
33
33
  note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
34
34
  note "When the half-nasal in Telugu script is used for modern nasalization in writing Hindi or\n any other language, it shall be transliterated as a tilde above the transliterated vowel. In the case of the digraphs ai,\n au, the tilde shall be attached to the second vowel"
35
35
  note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
36
+ note "Adjudicated against the published ISO 15919:2001 edition: Table 7 ref 001 (ardhasunna, U+0C00) prints n with breve, Rule 7; ref 001a (U+0C01, footnote b: used in Sanskrit) prints m with dot below (1E43); ref 052a (U+0C34) prints la with line below + inherent a (1E3B 0061). Ref 026a (ca with nukta, c with circumflex) has no Unicode character and is not encodable; ref 028a (za) is printed via the ja + nukta combination already encoded."
36
37
  }
37
38
  }
38
39
 
@@ -48,6 +49,9 @@ tests {
48
49
  "ఇప్పుడు ఆ వీడియో వైరల్‌ అయింది. ‘ఆ కెమెరాను కొనాలనేది చాలాకాలంగా నా కల." -> "ipapauḍau ā vaīḍaiyaō vaairala ayaiṁdai. ‘ā kaemaeraānau kaonaālanaēdai caālaākaālaṁgaā naā kala."
49
50
  "మరో వైపు ఎన్టీఆర్‌, రామ్‌చరణ్‌ కలిసి ట్రిపుల్‌ ఆర్‌ సినిమాలో నటిస్తున్నారు" -> "maraō vaaipau enaṭaīāra, raāmacaraṇa kalaisai ṭaraipaula āra sainaimaālaō naṭaisataunanaārau"
50
51
  "౪౬౨౬౯" -> "46269"
52
+ "ఀ" -> "n̆"
53
+ "ఁ" -> "ṃ"
54
+ "ఴ" -> "ḻa"
51
55
  }
52
56
 
53
57
  stage main {
@@ -165,6 +169,9 @@ stage main {
165
169
  sub "ఽ" ":’"
166
170
 
167
171
 
172
+ sub "ఀ" "n̆"
173
+ sub "ఁ" "ṃ"
174
+ sub "ఴ" "ḻa"
168
175
  sub "\u0c4d" ""
169
176
  sub "ౕ\t" ""
170
177
  sub "ౖ\t" ""
@@ -0,0 +1,229 @@
1
+ system "ISO:tel-Telu:Latn:15919-2026" {
2
+
3
+ metadata {
4
+ authority_id iso
5
+ id 15919-2026
6
+ language iso-639-2:tel
7
+ source_script Telu
8
+ destination_script Latn
9
+ name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Telugu; 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 7.7 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 51/59 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
+ "అ" -> "a"
31
+ "క" -> "ka"
32
+ "ఆ" -> "ā"
33
+ "ా" -> "ā"
34
+ "ఖ" -> "kha"
35
+ "ఇ" -> "i"
36
+ "ి" -> "i"
37
+ "గ" -> "ga"
38
+ "ఈ" -> "ī"
39
+ "ీ" -> "ī"
40
+ "ఘ" -> "gha"
41
+ "ఉ" -> "u"
42
+ "ు" -> "u"
43
+ "ఙ" -> "ṅa"
44
+ "ఊ" -> "ū"
45
+ "ూ" -> "ū"
46
+ "చ" -> "ca"
47
+ "ఋ" -> "r̥"
48
+ "ృ" -> "r̥"
49
+ "ఛ" -> "cha"
50
+ "ౠ" -> "r̥̄"
51
+ "ౄ" -> "r̥̄"
52
+ "జ" -> "ja"
53
+ "ఌ" -> "l̥"
54
+ "ౢ" -> "l̥"
55
+ "ఝ" -> "jha"
56
+ "ౡ" -> "l̥̄"
57
+ "ౣ" -> "l̥̄"
58
+ "ఞ" -> "ña"
59
+ "ఎ" -> "e"
60
+ "ె" -> "e"
61
+ "ట" -> "ṭa"
62
+ "ఏ" -> "ē"
63
+ "ే" -> "ē"
64
+ "ఠ" -> "ṭha"
65
+ "ఐ" -> "ai"
66
+ "ై" -> "ai"
67
+ "డ" -> "ḍa"
68
+ "ఒ" -> "o"
69
+ "ొ" -> "o"
70
+ "ఢ" -> "ḍha"
71
+ "ఓ" -> "ō"
72
+ "ో" -> "ō"
73
+ "ణ" -> "ṇa"
74
+ "ఔ" -> "au"
75
+ "ౌ" -> "au"
76
+ "త" -> "ta"
77
+ "శ" -> "śa"
78
+ "థ" -> "tha"
79
+ "ష" -> "ṣa"
80
+ "ద" -> "da"
81
+ "స" -> "sa"
82
+ "ధ" -> "dha"
83
+ "న" -> "na"
84
+ "ళ" -> "ḷa"
85
+ "ప" -> "pa"
86
+ "ౘ" -> "ĉa"
87
+ "ఫ" -> "pha"
88
+ "ౙ" -> "za"
89
+ "బ" -> "ba"
90
+ "ఱ" -> "ṟa"
91
+ "భ" -> "bha"
92
+ "ఴ" -> "ḻa"
93
+ "మ" -> "ma"
94
+ "ం" -> "ṁ"
95
+ "య" -> "ya"
96
+ "ఁ" -> "n̆"
97
+ "ర" -> "ra"
98
+ "ః" -> "ḥ"
99
+ "ల" -> "la"
100
+ "ఀ" -> "m̐"
101
+ "వ" -> "va"
102
+ "ఽ" -> "'"
103
+ "౦" -> "0"
104
+ "౧" -> "1"
105
+ "౨" -> "2"
106
+ "౩" -> "3"
107
+ "౪" -> "4"
108
+ "౫" -> "5"
109
+ "౬" -> "6"
110
+ "౭" -> "7"
111
+ "౮" -> "8"
112
+ "౯" -> "9"
113
+ "హ" -> "ha"
114
+ }
115
+
116
+ stage main {
117
+
118
+ # Table 7.7 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
119
+ parallel {
120
+
121
+ sub "అ" "a"
122
+ sub "అ" "A" when opt98
123
+ sub "క" "ka"
124
+ sub "ఆ" "ā"
125
+ sub "ా" "ā"
126
+ sub "ఆ" "Ā" when opt98
127
+ sub "ఖ" "kha"
128
+ sub "ఇ" "i"
129
+ sub "ి" "i"
130
+ sub "ఇ" "I" when opt98
131
+ sub "గ" "ga"
132
+ sub "ఈ" "ī"
133
+ sub "ీ" "ī"
134
+ sub "ఈ" "Ī" when opt98
135
+ sub "ఘ" "gha"
136
+ sub "ఉ" "u"
137
+ sub "ు" "u"
138
+ sub "ఉ" "U" when opt98
139
+ sub "ఙ" "ṅa"
140
+ sub "ఊ" "ū"
141
+ sub "ూ" "ū"
142
+ sub "ఊ" "Ū" when opt98
143
+ sub "చ" "ca"
144
+ sub "ఋ" "r̥"
145
+ sub "ృ" "r̥"
146
+ sub "ఋ" "R̥" when opt98
147
+ sub "ఛ" "cha"
148
+ sub "ౠ" "r̥̄"
149
+ sub "ౄ" "r̥̄"
150
+ sub "ౠ" "R̥̄" when opt98
151
+ sub "జ" "ja"
152
+ sub "ఌ" "l̥"
153
+ sub "ౢ" "l̥"
154
+ sub "ఌ" "L̥" when opt98
155
+ sub "ఝ" "jha"
156
+ sub "ౡ" "l̥̄"
157
+ sub "ౣ" "l̥̄"
158
+ sub "ౡ" "L̥̄" when opt98
159
+ sub "ఞ" "ña"
160
+ sub "ఎ" "e"
161
+ sub "ె" "e"
162
+ sub "ఎ" "E" when opt98
163
+ sub "ట" "ṭa"
164
+ sub "ఏ" "ē"
165
+ sub "ే" "ē"
166
+ sub "ఏ" "Ē" when opt98
167
+ sub "ఠ" "ṭha"
168
+ sub "ఐ" "ai"
169
+ sub "ై" "ai"
170
+ sub "ఐ" "Ai" when opt98
171
+ sub "డ" "ḍa"
172
+ sub "ఒ" "o"
173
+ sub "ొ" "o"
174
+ sub "ఒ" "O" when opt98
175
+ sub "ఢ" "ḍha"
176
+ sub "ఓ" "ō"
177
+ sub "ో" "ō"
178
+ sub "ఓ" "Ō" when opt98
179
+ sub "ణ" "ṇa"
180
+ sub "ఔ" "au"
181
+ sub "ౌ" "au"
182
+ sub "ఔ" "Au" when opt98
183
+ sub "త" "ta"
184
+ sub "శ" "śa"
185
+ sub "థ" "tha"
186
+ sub "ష" "ṣa"
187
+ sub "ద" "da"
188
+ sub "స" "sa"
189
+ sub "హ" "ha"
190
+ sub "ధ" "dha"
191
+ sub "న" "na"
192
+ sub "ళ" "ḷa"
193
+ sub "ప" "pa"
194
+ sub "ౘ" "ĉa"
195
+ sub "ఫ" "pha"
196
+ sub "ౙ" "za"
197
+ sub "బ" "ba"
198
+ sub "ఱ" "ṟa"
199
+ sub "భ" "bha"
200
+ sub "ఴ" "ḻa"
201
+ sub "మ" "ma"
202
+ sub "ం" "ṁ"
203
+ sub "య" "ya"
204
+ sub "ఁ" "n̆"
205
+ sub "ర" "ra"
206
+ sub "ః" "ḥ"
207
+ sub "ల" "la"
208
+ sub "ఀ" "m̐"
209
+ sub "వ" "va"
210
+ sub "ఽ" "'"
211
+ sub "్" ""
212
+ sub "్" "·" when opt10
213
+ sub "‍" ""
214
+ sub "‍" "=" when opt99
215
+ sub "౦" "0"
216
+ sub "౧" "1"
217
+ sub "౨" "2"
218
+ sub "౩" "3"
219
+ sub "౪" "4"
220
+ sub "౫" "5"
221
+ sub "౬" "6"
222
+ sub "౭" "7"
223
+ sub "౮" "8"
224
+ sub "౯" "9"
225
+ }
226
+
227
+ compose
228
+ }
229
+ }
@@ -100,24 +100,16 @@ tests {
100
100
  # printed-key reading fails. Finding. | ь — the Other notes state the
101
101
  # standalone soft sign is not represented; the map encodes ь -> empty, which
102
102
  # the generator contract cannot express as a row (no printed value cell
103
- # exists either). Findings (map-vs-source, map untouched): пӏ (п +
104
- # palochka): printed value "p"; map lacks the lowercase digraph rule (falls
105
- # through to "p'") and encodes uppercase Пӏ as "Ph", which no printed cell
106
- # supports. | цӏ (ц + palochka, U+0446+U+04CF): printed value "ts"; map
107
- # encodes the single-codepoint ҹ (U+04B9) instead of the printed glyph
108
- # sequence, so printed-key input falls through to "ts'". | ц: printed row ц
109
- # -> ts has NO map rule at all (plain U+0446 passes through unchanged); only
110
- # ҹ (U+04B9) is encoded. | 1 (palochka-cell ASCII-1 key): map normalization
111
- # rules do not fire at string edges; standalone "1" unchanged. | ъ: footnote
112
- # 3 (word-initial ъ dropped) is not implemented in the map (ъ -> '
113
- # unconditionally); row skipped as context-dependent. | е: footnote 1
114
- # variant ye is implemented by the map as a word-initial rule; printed
115
- # wording differs ("preceded by the sound of a 'y' consonant"); row skipped
116
- # as context-dependent. | Uppercase Ы carries two sub rules in the map (Ы ->
117
- # Y at the letter table and a second Ы -> Е further down); only the printed
118
- # lowercase row ы -> e is testable and passes. The duplicate uppercase rule
119
- # is recorded here as an observation; map untouched this round.
120
- # Provenance artifact: scripts/row-sources/odni-che-Cyrl-Latn-2015.json (38 rows).
103
+ # exists either). Findings (map-vs-source) resolved in the E3 corpus-fixes round (2026-11-17):
104
+ # the printed ц -> ts row is now encoded (plain U+0446 had no rule at all), the
105
+ # printed цӏ key (the two-glyph sequence U+0446+U+04CF) is now encoded alongside
106
+ # the precomposed ҹ single-codepoint rules the old map carried, and the пӏ
107
+ # digraph is completed (lowercase пӏ -> p added; uppercase Пӏ re-voiced
108
+ # "Ph" -> "P" — no printed cell supports "Ph"). Still recorded, untouched: the
109
+ # "1"-at-string-edge normalization gap (standalone "1" unchanged), footnote 3
110
+ # (word-initial ъ dropped) not implemented, footnote 1's е/ye wording difference,
111
+ # and the duplicate uppercase Ы rules (observation).
112
+ # Provenance artifact: scripts/row-sources/odni-che-Cyrl-Latn-2015.json (41 rows).
121
113
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
122
114
  "а" -> "a"
123
115
  "б" -> "b"
@@ -139,6 +131,7 @@ tests {
139
131
  "н" -> "n"
140
132
  "о" -> "o"
141
133
  "п" -> "p"
134
+ "пӏ" -> "p"
142
135
  "р" -> "r"
143
136
  "с" -> "s"
144
137
  "т" -> "t"
@@ -148,6 +141,8 @@ tests {
148
141
  "х" -> "kh"
149
142
  "хь" -> "h"
150
143
  "хӏ" -> "h"
144
+ "ц" -> "ts"
145
+ "цӏ" -> "ts"
151
146
  "ч" -> "ch"
152
147
  "чӏ" -> "ch"
153
148
  "ш" -> "sh"
@@ -211,7 +206,7 @@ stage main {
211
206
  sub "\u041D" 'N'
212
207
  sub "\u041E" 'O'
213
208
  sub "\u041F" 'P'
214
- sub "\u041F\u04C0" 'Ph'
209
+ sub "\u041F\u04C0" 'P'
215
210
  sub "\u0420" 'R'
216
211
  sub "\u0421" 'S'
217
212
  sub "\u0422" 'T'
@@ -221,6 +216,8 @@ stage main {
221
216
  sub "\u0425" 'Kh'
222
217
  sub "\u0425\u044C" 'H'
223
218
  sub "\u0425\u04C0" 'H'
219
+ sub "\u0426" 'Ts'
220
+ sub "\u0426\u04C0" 'Ts'
224
221
  sub "\u04B8" 'Ts'
225
222
  sub "\u04B8\u04C0" 'Ts'
226
223
  sub "\u0427" 'Ch'
@@ -255,6 +252,7 @@ stage main {
255
252
  sub "\u043D" 'n'
256
253
  sub "\u043E" 'o'
257
254
  sub "\u043F" 'p'
255
+ sub "\u043F\u04CF" 'p'
258
256
  sub "\u0440" 'r'
259
257
  sub "\u0441" 's'
260
258
  sub "\u0442" 't'
@@ -264,6 +262,8 @@ stage main {
264
262
  sub "\u0445" 'kh'
265
263
  sub "\u0445\u044C" 'h'
266
264
  sub "\u0445\u04CF" 'h'
265
+ sub "\u0446" 'ts'
266
+ sub "\u0446\u04CF" 'ts'
267
267
  sub "\u04B9" 'ts'
268
268
  sub "\u04B9\u04CF" 'ts'
269
269
  sub "\u0447" 'ch'
@@ -65,18 +65,13 @@ tests {
65
65
  # the row is transcribed as Ѕ -> Dz / ѕ -> dz and, failing end-to-end,
66
66
  # recorded as a finding. The text layer for the same cell stores "Ss"/"Dz
67
67
  # dz". Skipped printed rows: ’ (apostrophe sign) — printed value cell "[Not
68
- # represented]" — instruction cell, no romanization value. | Ѕ/ѕ (dze) —
69
- # printed value cell "Dz dz" FAILS end-to-end on the Cyrillic key: the map
70
- # encodes the annex’s substitute glyphs literally (Latin S/s, U+0053/U+0073
71
- # -> Dz/dz) while the actual Cyrillic dze letters Ѕ/ѕ (U+0405/U+0455) carry
72
- # no rule and pass through unchanged ("Ѕ" -> "Ѕ"). Finding, never forced
73
- # green. Findings (map-vs-source, map untouched): Ѕ/ѕ (U+0405/U+0455):
74
- # printed row Dz/dz untestable — the map has no rule for the Cyrillic dze
75
- # letters; it instead maps Latin S/s -> Dz/dz (the annex’s substituted
76
- # letter cell taken literally), so Cyrillic dze passes through unencoded AND
77
- # Latin-letter input is silently rewritten to Dz/dz, against the annex’s own
78
- # convention of spelling Latin-letter names as-is.
79
- # Provenance artifact: scripts/row-sources/odni-mkd-Cyrl-Latn-2015.json (60 rows).
68
+ # represented]" — instruction cell, no romanization value.
69
+ # E3 corpus-fixes round (2026-11-17): the dze finding is fixed — the map's
70
+ # rules now key the actual Cyrillic dze letters Ѕ/ѕ (U+0405/U+0455) -> Dz/dz
71
+ # (the annex's letter cell prints "S s" as a substitute-glyph rendering of
72
+ # Ѕ ѕ; the Latin S/s keys the old map encoded literally are removed, so
73
+ # Latin-letter input passes through as-is per the annex's own convention).
74
+ # Provenance artifact: scripts/row-sources/odni-mkd-Cyrl-Latn-2015.json (62 rows).
80
75
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
81
76
  "А" -> "A"
82
77
  "а" -> "a"
@@ -96,6 +91,8 @@ tests {
96
91
  "ж" -> "zh"
97
92
  "З" -> "Z"
98
93
  "з" -> "z"
94
+ "Ѕ" -> "Dz"
95
+ "ѕ" -> "dz"
99
96
  "И" -> "I"
100
97
  "и" -> "i"
101
98
  "Ј" -> "J"
@@ -142,10 +139,6 @@ tests {
142
139
 
143
140
  stage main {
144
141
  parallel {
145
- # RULES
146
- sub "\u0053" "Dz"
147
- sub "\u0073" "dz"
148
-
149
142
  # CHARACTERS
150
143
  sub "\u0410" "A"
151
144
  sub "\u0411" "B"
@@ -156,6 +149,7 @@ stage main {
156
149
  sub "\u0415" "E"
157
150
  sub "\u0416" "Zh"
158
151
  sub "\u0417" "Z"
152
+ sub "\u0405" "Dz"
159
153
  sub "\u0418" "I"
160
154
  sub "\u0408" "J"
161
155
  sub "\u041A" "K"
@@ -188,6 +182,7 @@ stage main {
188
182
  sub "\u0435" "e"
189
183
  sub "\u0436" "zh"
190
184
  sub "\u0437" "z"
185
+ sub "\u0455" "dz"
191
186
  sub "\u0438" "i"
192
187
  sub "\u0458" "j"
193
188
  sub "\u043A" "k"