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
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 7c5ec85faa5eb30d2bd2265b1b7d21965e31d82fd8c460442d691bbb22dd152e
4
- data.tar.gz: 8161cbaa91376a68243e78a6297a83134ce7f71ecb346ec479e554f27e1847c1
3
+ metadata.gz: 7f458919b89990c9308e1ea6e6c0ff0552ccb3b047678f38d1f8d993d868ecb9
4
+ data.tar.gz: f96956ff2cf0631c85a2e83d4a7c2d196c28cbcaba292163afe3b9187fb3732a
5
5
  SHA512:
6
- metadata.gz: 54a62529575119fa93a04d5fce7e13d4b1619535c5fd00c4e11fe9279fac63414841838d3eeb61aa5c914b749891bdf4425505d4ffbfb9878ea93d5a4395ff38
7
- data.tar.gz: 06742d6c4b171dc068a15d08b54a818ff52a0b4ed15453a04bcc044bf760eacacf936737505498b1d70ddd44e6021e43c9960f8fa0ef4683bc47794dd159005a
6
+ metadata.gz: 6c2ba430e0086eef042db18a5f135f373c05dfd7188b3e7d4c7a6035c01b3d0f811c797a885133d64e522747b14be31e38a045042f61db8b148740b5f24e850c
7
+ data.tar.gz: 4f6f25e31febe1e00c54e77bc31831b8377a786d7a460db01257a0b2ea0fc99316eb295c29cafe387959c50c1de5fbe2485dc14606c3695e63c941080feb51eb
@@ -1,4 +1,4 @@
1
- INTERSCRIPT_MAPS_VERSION = "3.2.4"
1
+ INTERSCRIPT_MAPS_VERSION = "3.3.0"
2
2
 
3
3
  Gem::Specification.new do |spec|
4
4
  spec.name = "interscript-maps"
@@ -19,9 +19,9 @@ metadata {
19
19
 
20
20
  tests {
21
21
  # from internet
22
- "Азәрбајҹан дили" -> "Azărbaı̐jan dili"
23
- "Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.\nОнларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар." -> "Bu̇tu̇n insanlar lăı̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.\nOnlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar."
24
- "Азәрбајҹан! Азәрбајҹан!\nЕј гәһрәман өвладын шанлы Вәтәни!\nСәндән өтрү ҹан вермәјә ҹүмлә һазырыз!\nСәндән өтрү ган төкмәјә ҹүмлә гадириз!\nҮчрәнҝли бајрағынла мәсуд јаша!\nҮчрәнҝли бајрағынла мәсуд јаша!\nМинләрлә ҹан гурбан олду,\nСинән һәрбә мејдан олду!\nҺүгугундан кечән әсҝәр,\nҺәрә бир гәһрәман олду!\nСән оласан ҝүлүстан,\nСәнә һәр ан ҹан гурбан!\nСәнә мин бир мәһәббәт\nСинәмдә тутмуш мәкан!\nНамусуну һифз етмәјә,\nБајрағыны јүксәлтмәјә\nНамусуну һифз етмәјә,\nҸүмлә ҝәнҹләр мүштагдыр!\nШанлы Вәтән! Шанлы Вәтән!\nАзәрбајҹан! Азәрбајҹан!\nАзәрбајҹан! Азәрбајҹан!" -> "Azărbaı̐jan! Azărbaı̐jan!\nEı̐ găḣrăman ȯvladyn shanly Vătăni!\nSăndăn ȯtru̇ jan vermăı̐ă ju̇mlă ḣazyryz!\nSăndăn ȯtru̇ gan tȯkmăı̐ă ju̇mlă gadiriz!\nU̇chrănġli baı̐raghynla măsud ı̐asha!\nU̇chrănġli baı̐raghynla măsud ı̐asha!\nMinlărlă jan gurban oldu,\nSinăn ḣărbă meı̐dan oldu!\nḢu̇gugundan kechăn ăsġăr,\nḢără bir găḣrăman oldu!\nSăn olasan ġu̇lu̇stan,\nSănă ḣăr an jan gurban!\nSănă min bir măḣăbbăt\nSinămdă tutmush măkan!\nNamusunu ḣifz etmăı̐ă,\nBaı̐raghyny ı̐u̇ksăltmăı̐ă\nNamusunu ḣifz etmăı̐ă,\nJu̇mlă ġănjlăr mu̇shtagdyr!\nShanly Vătăn! Shanly Vătăn!\nAzărbaı̐jan! Azărbaı̐jan!\nAzărbaı̐jan! Azărbaı̐jan!"
22
+ "Азәрбајҹан дили" -> "Azărbai̐jan dili"
23
+ "Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.\nОнларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар." -> "Bu̇tu̇n insanlar lăi̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.\nOnlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar."
24
+ "Азәрбајҹан! Азәрбајҹан!\nЕј гәһрәман өвладын шанлы Вәтәни!\nСәндән өтрү ҹан вермәјә ҹүмлә һазырыз!\nСәндән өтрү ган төкмәјә ҹүмлә гадириз!\nҮчрәнҝли бајрағынла мәсуд јаша!\nҮчрәнҝли бајрағынла мәсуд јаша!\nМинләрлә ҹан гурбан олду,\nСинән һәрбә мејдан олду!\nҺүгугундан кечән әсҝәр,\nҺәрә бир гәһрәман олду!\nСән оласан ҝүлүстан,\nСәнә һәр ан ҹан гурбан!\nСәнә мин бир мәһәббәт\nСинәмдә тутмуш мәкан!\nНамусуну һифз етмәјә,\nБајрағыны јүксәлтмәјә\nНамусуну һифз етмәјә,\nҸүмлә ҝәнҹләр мүштагдыр!\nШанлы Вәтән! Шанлы Вәтән!\nАзәрбајҹан! Азәрбајҹан!\nАзәрбајҹан! Азәрбајҹан!" -> "Azărbai̐jan! Azărbai̐jan!\nEi̐ găḣrăman ȯvladyn shanly Vătăni!\nSăndăn ȯtru̇ jan vermăi̐ă ju̇mlă ḣazyryz!\nSăndăn ȯtru̇ gan tȯkmăi̐ă ju̇mlă gadiriz!\nU̇chrănġli bai̐raghynla măsud i̐asha!\nU̇chrănġli bai̐raghynla măsud i̐asha!\nMinlărlă jan gurban oldu,\nSinăn ḣărbă mei̐dan oldu!\nḢu̇gugundan kechăn ăsġăr,\nḢără bir găḣrăman oldu!\nSăn olasan ġu̇lu̇stan,\nSănă ḣăr an jan gurban!\nSănă min bir măḣăbbăt\nSinămdă tutmush măkan!\nNamusunu ḣifz etmăi̐ă,\nBai̐raghyny i̐u̇ksăltmăi̐ă\nNamusunu ḣifz etmăi̐ă,\nJu̇mlă ġănjlăr mu̇shtagdyr!\nShanly Vătăn! Shanly Vătăn!\nAzărbai̐jan! Azărbai̐jan!\nAzărbai̐jan! Azărbai̐jan!"
25
25
  # Exhaustive per-row tests for alalc-aze-Cyrl-Latn-1997, generated from the source
26
26
  # document's table.
27
27
  # Source: ALA-LC Azerbaijani Romanization Table, 2017 version, pp. 6-7
@@ -44,8 +44,11 @@ tests {
44
44
  # byte-exact embedded test passes. | ө: printed glyph "ȯ"; the runtime
45
45
  # emits the canonically equivalent byte form 'ȯ'; the row is stored in the
46
46
  # runtime's byte form so the byte-exact embedded test passes. Failing
47
- # printed rows (findings): Ё — printed cell "Ë"; runtime gives 'Ё'. Failing
48
- # row, finding below — never forced green. | Й — printed cell "Ĭ"; runtime
47
+ # E3 corpus-fixes round (2026-11-17): all 19 failing rows fixed in the map —
48
+ # the 8 missing letter pairs (Ё/ё, Ц/ц, Щ/щ, Ъ/ъ, Ь/ь, Э/э, Ю/ю, Я/я) encoded
49
+ # from the printed cells, Й/й re-voiced Y/y -> Ĭ/ĭ and ј re-voiced ı̐ -> i̐
50
+ # per the printed table; the three pre-existing internet-sourced example
51
+ # tests carried the old ı̐ expectation and were updated with the fix.
49
52
  # gives 'Y'. Failing row, finding below — never forced green. | Ц — printed
50
53
  # cell "TS͡"; runtime gives 'Ц'. Failing row, finding below — never forced
51
54
  # green. | Щ — printed cell "Shch"; runtime gives 'Щ'. Failing row, finding
@@ -58,7 +61,7 @@ tests {
58
61
  # gives 'Я'. Failing row, finding below — never forced green. | ё — printed
59
62
  # cell "ë"; runtime gives 'ё'. Failing row, finding below — never forced
60
63
  # green. | й — printed cell "ĭ"; runtime gives 'y'. Failing row, finding
61
- # below — never forced green. | ј — printed cell "i̐"; runtime gives 'ı̐'.
64
+ # below — never forced green. | ј — printed cell "i̐"; runtime gives 'i̐'.
62
65
  # Failing row, finding below — never forced green. | ц — printed cell "ts͡";
63
66
  # runtime gives 'ц'. Failing row, finding below — never forced green. | щ —
64
67
  # printed cell "shch"; runtime gives 'щ'. Failing row, finding below — never
@@ -69,7 +72,7 @@ tests {
69
72
  # ю — printed cell "iu͡"; runtime gives 'ю'. Failing row, finding below —
70
73
  # never forced green. | я — printed cell "ia͡"; runtime gives 'я'. Failing
71
74
  # row, finding below — never forced green.
72
- # Provenance artifact: scripts/row-sources/alalc-aze-Cyrl-Latn-1997.json (64 rows).
75
+ # Provenance artifact: scripts/row-sources/alalc-aze-Cyrl-Latn-1997.json (83 rows).
73
76
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
74
77
  "А" -> "A"
75
78
  "Б" -> "B"
@@ -78,10 +81,12 @@ tests {
78
81
  "Ғ" -> "Gh"
79
82
  "Д" -> "D"
80
83
  "Е" -> "E"
84
+ "Ё" -> "Ë"
81
85
  "Ә" -> "Ă"
82
86
  "Ж" -> "Zh"
83
87
  "З" -> "Z"
84
88
  "И" -> "I"
89
+ "Й" -> "Ĭ"
85
90
  "Ј" -> "I̐"
86
91
  "К" -> "K"
87
92
  "Ҝ" -> "Ġ"
@@ -99,10 +104,17 @@ tests {
99
104
  "Ф" -> "F"
100
105
  "Х" -> "Kh"
101
106
  "Һ" -> "Ḣ"
107
+ "Ц" -> "TS͡"
102
108
  "Ч" -> "Ch"
103
109
  "Ҹ" -> "J"
104
110
  "Ш" -> "Sh"
111
+ "Щ" -> "Shch"
112
+ "Ъ" -> "ʺ"
105
113
  "Ы" -> "Y"
114
+ "Ь" -> "ʹ"
115
+ "Э" -> "Ė"
116
+ "Ю" -> "IU͡"
117
+ "Я" -> "IA͡"
106
118
  "а" -> "a"
107
119
  "б" -> "b"
108
120
  "в" -> "v"
@@ -110,10 +122,13 @@ tests {
110
122
  "ғ" -> "gh"
111
123
  "д" -> "d"
112
124
  "е" -> "e"
125
+ "ё" -> "ë"
113
126
  "ә" -> "ă"
114
127
  "ж" -> "zh"
115
128
  "з" -> "z"
116
129
  "и" -> "i"
130
+ "й" -> "ĭ"
131
+ "ј" -> "i̐"
117
132
  "к" -> "k"
118
133
  "ҝ" -> "ġ"
119
134
  "л" -> "l"
@@ -130,10 +145,17 @@ tests {
130
145
  "ф" -> "f"
131
146
  "х" -> "kh"
132
147
  "һ" -> "ḣ"
148
+ "ц" -> "ts͡"
133
149
  "ч" -> "ch"
134
150
  "ҹ" -> "j"
135
151
  "ш" -> "sh"
152
+ "щ" -> "shch"
153
+ "ъ" -> "ʺ"
136
154
  "ы" -> "y"
155
+ "ь" -> "ʹ"
156
+ "э" -> "ė"
157
+ "ю" -> "iu͡"
158
+ "я" -> "ia͡"
137
159
  "’" -> "’"
138
160
  }
139
161
 
@@ -148,14 +170,14 @@ stage main {
148
170
  sub "\u0492" "Gh"
149
171
  sub "\u0414" "D"
150
172
  sub "\u0415" "E"
173
+ sub "\u0401" "Ë"
151
174
  sub "\u04D8" "Ă"
152
175
  sub "\u0416" "Zh"
153
176
  sub "\u0417" "Z"
154
177
  sub "\u0418" "I"
155
178
  sub "\u042B" "Y"
156
179
  sub "\u0408" "I̐"
157
- sub "\u0419" "Y"
158
- sub "\u0419" "Y"
180
+ sub "\u0419" "Ĭ"
159
181
  sub "\u041A" "K"
160
182
  sub "\u049C" "Ġ"
161
183
  sub "\u041B" "L"
@@ -173,8 +195,15 @@ stage main {
173
195
  sub "\u0425" "Kh"
174
196
  sub "\u04BA" "Ḣ"
175
197
  sub "\u0427" "Ch"
198
+ sub "\u0426" "TS͡"
176
199
  sub "\u04B8" "J"
177
200
  sub "\u0428" "Sh"
201
+ sub "\u0429" "Shch"
202
+ sub "\u042A" "ʺ"
203
+ sub "\u042C" "ʹ"
204
+ sub "\u042D" "Ė"
205
+ sub "\u042E" "IU͡"
206
+ sub "\u042F" "IA͡"
178
207
 
179
208
  sub "\u0430" "a"
180
209
  sub "\u0431" "b"
@@ -183,13 +212,14 @@ stage main {
183
212
  sub "\u0493" "gh"
184
213
  sub "\u0434" "d"
185
214
  sub "\u0435" "e"
215
+ sub "\u0451" "ë"
186
216
  sub "\u04D9" "ă"
187
217
  sub "\u0436" "zh"
188
218
  sub "\u0437" "z"
189
219
  sub "\u0438" "i"
190
220
  sub "\u044B" "y"
191
- sub "\u0458" "ı̐"
192
- sub "\u0439" "y"
221
+ sub "\u0458" "i̐"
222
+ sub "\u0439" "ĭ"
193
223
  sub "\u043A" "k"
194
224
  sub "\u049D" "ġ"
195
225
  sub "\u043B" "l"
@@ -207,8 +237,15 @@ stage main {
207
237
  sub "\u0445" "kh"
208
238
  sub "\u04BB" "ḣ"
209
239
  sub "\u0447" "ch"
240
+ sub "\u0446" "ts͡"
210
241
  sub "\u04B9" "j"
211
242
  sub "\u0448" "sh"
243
+ sub "\u0449" "shch"
244
+ sub "\u044A" "ʺ"
245
+ sub "\u044C" "ʹ"
246
+ sub "\u044D" "ė"
247
+ sub "\u044E" "iu͡"
248
+ sub "\u044F" "ia͡"
212
249
 
213
250
  sub "\u2019" "\u2019"
214
251
  }
@@ -48,26 +48,22 @@ tests {
48
48
  # transcribed; the duplicate printed listing is documented here. | ঁ
49
49
  # (candrabindu) — printed value cell "n̐, m̐ (see Note 4)": Note 4 splits
50
50
  # the value by the following consonant class — position-dependent,
51
- # un-expressible as a plain row; skipped. Failing printed rows (findings): ই
52
- # — printed cell "I"; runtime gives 'i'. Failing row, finding below — never
53
- # forced green. | চ — printed cell "ca"; runtime gives 'cha'. Failing row,
54
- # finding below — never forced green. | ছ — printed cell "cha"; runtime
55
- # gives 'chha'. Failing row, finding below — never forced green. | ড় —
56
- # printed cell "ṛa"; runtime gives 'ṙa'. Failing row, finding below — never
57
- # forced green. | ঢ় — printed cell "ṛha"; runtime gives 'ṙha'. Failing row,
58
- # finding below — never forced green. | য — printed cell "ya"; runtime gives
59
- # 'j̱a'. Failing row, finding below — never forced green. | য় — printed
60
- # cell "ẏ"; runtime gives 'ya'. Failing row, finding below — never forced
61
- # green. | শ — printed cell "śa"; runtime gives 'sha'. Failing row, finding
62
- # below — never forced green. | ষ — printed cell "sha"; runtime gives 'ṣha'.
63
- # Failing row, finding below — never forced green. | ং — printed cell "ṃ";
64
- # runtime gives 'ṁ'. Failing row, finding below — never forced green. | ঽ —
65
- # printed cell "’"; runtime gives 'ঽ'. Failing row, finding below — never
66
- # forced green.
67
- # Provenance artifact: scripts/row-sources/alalc-ben-Beng-Latn-2017.json (41 rows).
51
+ # un-expressible as a plain row; skipped. E3 corpus-fixes round (2026-11-17): all 11 failing rows are fixed. The
52
+ # map's own letter table already carried the printed values but sat AFTER
53
+ # the "run map.benglatn.stage.main" item in stage main — the base stage
54
+ # consumes the Bengali letters, so those rules matched nothing and every
55
+ # divergent cell emitted the base map's 1997-era value. The fix applies the
56
+ # printed values to the raw text BEFORE the base run (a pre-empt parallel
57
+ # with elision variants mirroring the base RULES machinery and both nukta
58
+ # composite forms), so the eleven cells — and every cluster string embedding
59
+ # them — now transliterate per the printed table. The rows are part of the
60
+ # generated set; the provenance artifact's note replaces this findings
61
+ # record.
62
+ # Provenance artifact: scripts/row-sources/alalc-ben-Beng-Latn-2017.json (52 rows).
68
63
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
69
64
  "অ" -> "a"
70
65
  "আ" -> "ā"
66
+ "ই" -> "I"
71
67
  "ঈ" -> "ī"
72
68
  "উ" -> "u"
73
69
  "ঊ" -> "ū"
@@ -83,13 +79,17 @@ tests {
83
79
  "গ" -> "ga"
84
80
  "ঘ" -> "gha"
85
81
  "ঙ" -> "ṅa"
82
+ "চ" -> "ca"
83
+ "ছ" -> "cha"
86
84
  "জ" -> "ja"
87
85
  "ঝ" -> "jha"
88
86
  "ঞ" -> "ña"
89
87
  "ট" -> "ṭa"
90
88
  "ঠ" -> "ṭha"
91
89
  "ড" -> "ḍa"
90
+ "ড়" -> "ṛa"
92
91
  "ঢ" -> "ḍha"
92
+ "ঢ়" -> "ṛha"
93
93
  "ণ" -> "ṇa"
94
94
  "ত" -> "ta"
95
95
  "ৎ" -> "t"
@@ -102,17 +102,68 @@ tests {
102
102
  "ব" -> "ba"
103
103
  "ভ" -> "bha"
104
104
  "ম" -> "ma"
105
+ "য" -> "ya"
106
+ "য়" -> "ẏa"
105
107
  "র" -> "ra"
106
108
  "ল" -> "la"
109
+ "শ" -> "śa"
110
+ "ষ" -> "sha"
107
111
  "স" -> "sa"
108
112
  "হ" -> "ha"
113
+ "ং" -> "ṃ"
109
114
  "ঃ" -> "ḥ"
115
+ "ঽ" -> "’"
110
116
  }
111
117
 
112
118
  dependency "un-ben-Beng-Latn-2016" as benglatn
113
119
 
120
+ aliases {
121
+ beng_signs = any("\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd")
122
+ }
114
123
 
115
124
  stage main {
125
+
126
+ # E3 corpus-fixes round (2026-11-17): the printed 2017 values for the
127
+ # eleven letter-table cells where ALA-LC diverges from the UN 2016 base
128
+ # machinery (the depth-batch findings: ই I, চ ca, ছ cha, ড় ṛa, ঢ় ṛha,
129
+ # য ya, য় ẏ, শ śa, ষ sha, ং ṃ, ঽ ’) are applied to the RAW text BEFORE
130
+ # the base stage runs. The base stage consumes the Bengali letters, so a
131
+ # rule placed after the run can never fire — the map's own table sat
132
+ # there and matched nothing, leaving the base's 1997-era values in every
133
+ # divergent cell. Elision variants mirror the base RULES machinery (a
134
+ # consonant followed by a vowel sign or hasanta loses its inherent a);
135
+ # the two-glyph nukta composites are keyed in both the precomposed and
136
+ # the decomposed form; constrained variants precede their unconstrained
137
+ # forms; longer keys precede their shorter prefixes.
138
+ parallel {
139
+ sub "ড়" "ṛa"
140
+ sub { from "ড়" to "ṛ" after beng_signs }
141
+ sub "ড়" "ṛa"
142
+ sub { from "ড়" to "ṛ" after beng_signs }
143
+ sub "ঢ়" "ṛha"
144
+ sub { from "ঢ়" to "ṛh" after beng_signs }
145
+ sub "ঢ়" "ṛha"
146
+ sub { from "ঢ়" to "ṛh" after beng_signs }
147
+ sub "য়" "ẏa"
148
+ sub { from "য়" to "ẏ" after beng_signs }
149
+ sub "য়" "ẏa"
150
+ sub { from "য়" to "ẏ" after beng_signs }
151
+ sub "ই" "I"
152
+ sub "চ" "ca"
153
+ sub { from "চ" to "c" after beng_signs }
154
+ sub "ছ" "cha"
155
+ sub { from "ছ" to "ch" after beng_signs }
156
+ sub "য" "ya"
157
+ sub { from "য" to "y" after beng_signs }
158
+ sub "শ" "śa"
159
+ sub { from "শ" to "ś" after beng_signs }
160
+ sub "ষ" "sha"
161
+ sub { from "ষ" to "sh" after beng_signs }
162
+ sub "ং" "ṃ"
163
+ sub "ঽ" "’"
164
+ sub "ঽ" "’"
165
+ }
166
+
116
167
  run map.benglatn.stage.main
117
168
 
118
169
  # CHARACTERS
@@ -46,9 +46,11 @@ tests {
46
46
  # context-dependent. (The composite row ᱟᱹ -> ạ̄ above is the table's own
47
47
  # printed composite and is tested.) | The marks ᱻ (vowel prolongation,
48
48
  # omitted) and ᱼ (separator, omitted) — instruction rows on p. 2, no
49
- # romanization values. Failing printed rows (findings): ᱱ — printed cell
50
- # "n"; runtime gives 'ᱱ'. Failing row, finding below — never forced green.
51
- # Provenance artifact: scripts/row-sources/alalc-sat-Olck-Latn-2017.json (31 rows).
49
+ # romanization values.
50
+ # E3 corpus-fixes round (2026-11-17): the ᱱ finding is fixed — the map now
51
+ # carries the printed ᱱ -> n rule (the table's last consonant row), and the
52
+ # row is part of the generated set.
53
+ # Provenance artifact: scripts/row-sources/alalc-sat-Olck-Latn-2017.json (32 rows).
52
54
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
53
55
  "ᱚ" -> "a"
54
56
  "ᱩ" -> "u"
@@ -80,6 +82,7 @@ tests {
80
82
  "ᱛ" -> "t"
81
83
  "ᱫ" -> "d"
82
84
  "ᱝ" -> "ṃ"
85
+ "ᱱ" -> "n"
83
86
  "ᱽ" -> "’"
84
87
  }
85
88
 
@@ -109,6 +112,7 @@ stage main {
109
112
  sub "ᱽ" "’"
110
113
  sub "ᱫ" "d"
111
114
  sub "ᱝ" "ṃ"
115
+ sub "ᱱ" "n"
112
116
  sub "ᱸ" "m̐"
113
117
  }
114
118
 
@@ -0,0 +1,233 @@
1
+ system "BSI:rus-Cyrl:Latn:2979-1958" {
2
+
3
+ metadata {
4
+ authority_id bsi
5
+ id 2979-1958
6
+ language iso-639-2:rus
7
+ source_script Cyrl
8
+ destination_script Latn
9
+ name "BS 2979:1958 Transliteration of Cyrillic and Greek characters - Table A, Russian column (the British system)"
10
+ url https://www.bsigroup.com
11
+ creation_date 1958
12
+ confirmation_date 1998-12
13
+ description { BS 2979:1958, Table A, Russian column: the "British" system for (modern) Cyrillic.
14
+ Table A is a five-column family table (East Slavonic: Russian, Ukrainian,
15
+ Byelorussian; South Slavonic: Bulgarian, Serbian and Macedonian); this map is the
16
+ Russian column, all 48 rows of which are transcribed here (including the two the
17
+ scan previously could not resolve: 46 fita and 47 izhitsa as parenthesized obsolete
18
+ values; 45 is the old Bulgarian big-yus ligature with an empty Russian cell).
19
+ British Standard approved 30 July 1958, confirmed December 1998; the BSI 05-2000
20
+ reprint is the digitized edition.
21
+ }
22
+
23
+ notes {
24
+ note "PROVENANCE: transcribed visually from the held scan of BS 2979:1958 (BSI 05-2000 reprint; 24 PDF pages = printed inside front cover and pages i-v, 1-15). Every cell of the Russian column was read from the rendered pages at 6-30x zoom and cross-checked against the Table B (back transliteration) rows that cite the same Table A row numbers."
25
+ note "SCOPE: Section 1 (the British system for (modern) Cyrillic), Table A (Cyrillic-English transliteration, British system), Russian column, rows 1-48 upper and lower case plus digraph row 28+27 (Тс тс romanized t-s). The document's own Russian periodical-title examples (items 1-6 of the examples section inside the front cover) are embedded as tests. Section 1 NOTE 3 (the Serbian and Macedonian column gives the latinica) does not apply to this column; the other four columns of Table A are separate maps."
26
+ note "Section 1 NOTE 1. For extreme simplicity, when avoidance of ambiguity in back transliteration is not a paramount consideration, all accents, diacritics, etc., may be omitted in the English rendering. This map applies the table as printed, with the diacritics (the printed examples keep them too: ȳ in Promȳshlennost, Ĭ in Khozyaĭstvo)."
27
+ note "Section 1 NOTE 2. Cyrillic characters for which the transliteration is given in parentheses (і, ѣ, Ѳ, Ѵ, and the row 48 apostrophe), though no longer in official use, are sometimes found in the literature of the relevant language, e.g. in emigre or the older literature. This map renders them as given in the parentheses."
28
+ note "Section 1 NOTE 4. For transliteration of Moldavian, see Table C in Section 2 (ISO/R9). Sections 2 and 3 of the standard (the International system, Tables C/D/E/F, and Greek, Table G) are separate systems, not encoded here."
29
+ note "Row 38: the table gives the choice of right double quotation mark or straight double quotation mark for ъ; this map renders the right double quotation mark (U+201D). Row 40 likewise offers two apostrophe forms for ь; this map renders the right single quotation mark (U+2019)."
30
+ note "Row 28+27: the character sequence тс is romanized t-s with a hyphen, distinguishing it from ц, romanized ts."
31
+ note "Table A footnote: final ъ, now obsolete in Russian (and Bulgarian), is disregarded when encountered — implemented as a word-final rule deleting ъ/Ъ; non-final ъ carries the row 38 rendering."
32
+ note "Row 41 (ѣ, yat): the printed value is parenthesized ê (e with circumflex), cross-checked against Table B (Ë ë back-transliterates to Ѣ ѣ, row 41); row 8b (Ё) carries the caron ě — the two must not be conflated (an earlier transcription of this map had them swapped)."
33
+ note "Row 45 is the old Bulgarian ligature form of the big yus Ѫ, abandoned at the 1945 Bulgarian spelling reform (per the standard's Appendix: the characters ѣ and ѫ were abandoned at the time of the spelling reform of 1945); its Russian column cell is EMPTY (the parenthesized ū belongs to the Bulgarian column only) and it is therefore absent from this map. Row 46 (Ѳ ѳ, fita) is the parenthesized Ḟ ḟ — f with DOT above, not a macron, per Table B (F Ḟ / f ḟ back-transliterates to Ѳ ѳ). Row 47 (Ѵ ѵ, izhitsa) is the parenthesized Ŷ ŷ — y with CIRCUMFLEX (U+0176 U+0177), per Table A row 47 and Table B (Ŷ ŷ back-transliterates to Ѵ ѵ, row 47); the breve family belongs to row 17 (Ĭ ĭ) only."
34
+ note "Table B (Back transliteration: English-Cyrillic) is a separate Latin-to-Cyrillic table. Its Russian-relevant rows are recorded here: A to А (1), B to Б (2), C to Ц (33), Ĉ/Č/Ch to Ч (34), D to Д (6), E to Е (8a), Ě to Ё (8b), Ê to Э (42), Ë to Ѣ (41), F to Ф (31), Ḟ to Ѳ (46), G to Г (4), I to И (13), Ī to І (14), Ĭ to Й (17), K to К (18), Kh to Х (32), L to Л (19), M to М (21), N to Н (22), O to О (24), P to П (25), R to Р (26), S to С (27), Sh to Ш (36), Shch to Щ (37), T to Т (28), t-s to Тс (28+27), Ȳ to Ы (39), Ŷ to Ѵ (47), Ya to Я (44), Yu to Ю (43), Z to З (11), Ž/Zh to Ж (10), the double-quotation-mark forms to Ъ (38) and the apostrophe forms to Ь (40). The corpus encodes the forward direction only."
35
+ note "Examples section (Examples of titles of periodicals in Cyrillic with their British and International transliterations for comparison), items 1-6 Russian, British lines: transcribed as tests. Item 4's printed British rendering Sobranie departs from the table's я to ya (row 44; the same examples print Torgovlya, Khimiya, Observatoriya) — a 1958 typesetting inconsistency; the table governs and the word is not embedded as a test."
36
+ }
37
+ }
38
+
39
+ tests {
40
+ # document examples (Russian items 1-6, British lines)
41
+ "Бюллетень" -> "Byulleten’"
42
+ "Энгельгардтовская Астрономическая Обсерватория" -> "Éngel’gardtovskaya Astronomicheskaya Observatoriya"
43
+ "Гидротехническое Строительство. Москва" -> "Gidrotekhnicheskoe Stroitel’stvo. Moskva"
44
+ "Извѣстія Общества Археологіи, Исторіи и Этнографіи" -> "Izvêstiya Obshchestva Arkheologii, Istorii i Étnografii"
45
+ "Техника, Промышленность и Торговля" -> "Tekhnika, Promȳshlennost’ i Torgovlya"
46
+ "Химия и социалистическое Хозяйство. Москва" -> "Khimiya i sotsialisticheskoe Khozyaĭstvo. Moskva"
47
+ # item 4 fragment (Академии Наук, Ленинград table-consistent; printed Sobranie deviates, see notes)
48
+ "Академии Наук" -> "Akademii Nauk"
49
+ "Ленинград" -> "Leningrad"
50
+ "Известия" -> "Izvestiya"
51
+ "Москва" -> "Moskva"
52
+ # final-ъ footnote: final ъ is disregarded; non-final ъ carries row 38
53
+ "Херсонъ" -> "Kherson"
54
+ "объект" -> "ob”ekt"
55
+ "подъезд" -> "pod”ezd"
56
+ # table rows, upper and lower
57
+ "А" -> "A"
58
+ "а" -> "a"
59
+ "Б" -> "B"
60
+ "б" -> "b"
61
+ "В" -> "V"
62
+ "в" -> "v"
63
+ "Г" -> "G"
64
+ "г" -> "g"
65
+ "Д" -> "D"
66
+ "д" -> "d"
67
+ "Е" -> "E"
68
+ "е" -> "e"
69
+ "Ё" -> "Ě"
70
+ "ё" -> "ě"
71
+ "Ж" -> "Zh"
72
+ "ж" -> "zh"
73
+ "З" -> "Z"
74
+ "з" -> "z"
75
+ "И" -> "I"
76
+ "и" -> "i"
77
+ "Й" -> "Ĭ"
78
+ "й" -> "ĭ"
79
+ "К" -> "K"
80
+ "к" -> "k"
81
+ "Л" -> "L"
82
+ "л" -> "l"
83
+ "М" -> "M"
84
+ "м" -> "m"
85
+ "Н" -> "N"
86
+ "н" -> "n"
87
+ "О" -> "O"
88
+ "о" -> "o"
89
+ "П" -> "P"
90
+ "п" -> "p"
91
+ "Р" -> "R"
92
+ "р" -> "r"
93
+ "С" -> "S"
94
+ "с" -> "s"
95
+ "Т" -> "T"
96
+ "т" -> "t"
97
+ "Тс" -> "T-s"
98
+ "тс" -> "t-s"
99
+ "У" -> "U"
100
+ "у" -> "u"
101
+ "Ф" -> "F"
102
+ "ф" -> "f"
103
+ "Х" -> "Kh"
104
+ "х" -> "kh"
105
+ "Ц" -> "Ts"
106
+ "ц" -> "ts"
107
+ "Ч" -> "Ch"
108
+ "ч" -> "ch"
109
+ "Ш" -> "Sh"
110
+ "ш" -> "sh"
111
+ "Щ" -> "Shch"
112
+ "щ" -> "shch"
113
+ # standalone ъ is word-final: the Table A footnote disregards it (row 38 shows in non-final position only)
114
+ "Ъ" -> ""
115
+ "ъ" -> ""
116
+ "Ы" -> "Ȳ"
117
+ "ы" -> "ȳ"
118
+ "Ь" -> "’"
119
+ "ь" -> "’"
120
+ "Э" -> "É"
121
+ "э" -> "é"
122
+ "Ю" -> "Yu"
123
+ "ю" -> "yu"
124
+ "Я" -> "Ya"
125
+ "я" -> "ya"
126
+ "І" -> "I"
127
+ "і" -> "i"
128
+ "Ѣ" -> "Ê"
129
+ "ѣ" -> "ê"
130
+ "Ѳ" -> "Ḟ"
131
+ "ѳ" -> "ḟ"
132
+ "Ѵ" -> "Ŷ"
133
+ "ѵ" -> "ŷ"
134
+ }
135
+
136
+ stage main {
137
+
138
+ # TABLE A FOOTNOTE: final ъ, now obsolete in Russian, is disregarded when encountered
139
+ sub {
140
+ from "ъ"
141
+ to ""
142
+ after boundary
143
+ }
144
+ sub {
145
+ from "Ъ"
146
+ to ""
147
+ after boundary
148
+ }
149
+
150
+ # CHARACTERS (Table A, Russian column)
151
+ parallel {
152
+ sub "Тс" "T-s"
153
+ sub "тс" "t-s"
154
+ sub "Щ" "Shch"
155
+ sub "Ё" "Ě"
156
+ sub "Ж" "Zh"
157
+ sub "Й" "Ĭ"
158
+ sub "Х" "Kh"
159
+ sub "Ц" "Ts"
160
+ sub "Ч" "Ch"
161
+ sub "Ш" "Sh"
162
+ sub "Ы" "Ȳ"
163
+ sub "Э" "É"
164
+ sub "Ю" "Yu"
165
+ sub "Я" "Ya"
166
+ sub "Ѣ" "Ê"
167
+ sub "Ѳ" "Ḟ"
168
+ sub "Ѵ" "Ŷ"
169
+ sub "Ъ" "”"
170
+ sub "Ь" "’"
171
+ sub "А" "A"
172
+ sub "Б" "B"
173
+ sub "В" "V"
174
+ sub "Г" "G"
175
+ sub "Д" "D"
176
+ sub "Е" "E"
177
+ sub "З" "Z"
178
+ sub "И" "I"
179
+ sub "І" "I"
180
+ sub "К" "K"
181
+ sub "Л" "L"
182
+ sub "М" "M"
183
+ sub "Н" "N"
184
+ sub "О" "O"
185
+ sub "П" "P"
186
+ sub "Р" "R"
187
+ sub "С" "S"
188
+ sub "Т" "T"
189
+ sub "У" "U"
190
+ sub "Ф" "F"
191
+
192
+ sub "щ" "shch"
193
+ sub "ё" "ě"
194
+ sub "ж" "zh"
195
+ sub "й" "ĭ"
196
+ sub "х" "kh"
197
+ sub "ц" "ts"
198
+ sub "ч" "ch"
199
+ sub "ш" "sh"
200
+ sub "ы" "ȳ"
201
+ sub "э" "é"
202
+ sub "ю" "yu"
203
+ sub "я" "ya"
204
+ sub "ѣ" "ê"
205
+ sub "ѳ" "ḟ"
206
+ sub "ѵ" "ŷ"
207
+ sub "ъ" "”"
208
+ sub "ь" "’"
209
+ sub "а" "a"
210
+ sub "б" "b"
211
+ sub "в" "v"
212
+ sub "г" "g"
213
+ sub "д" "d"
214
+ sub "е" "e"
215
+ sub "з" "z"
216
+ sub "и" "i"
217
+ sub "і" "i"
218
+ sub "к" "k"
219
+ sub "л" "l"
220
+ sub "м" "m"
221
+ sub "н" "n"
222
+ sub "о" "o"
223
+ sub "п" "p"
224
+ sub "р" "r"
225
+ sub "с" "s"
226
+ sub "т" "t"
227
+ sub "у" "u"
228
+ sub "ф" "f"
229
+ }
230
+
231
+ }
232
+
233
+ }
@@ -47,9 +47,12 @@ tests {
47
47
  # runtime gives 'k'. Failing row, finding below — never forced green. | ѵ
48
48
  # (position 71) — the printed cell carries the value parenthesized ("(у̇)"),
49
49
  # DIN's optional-value notation; transcribed without the typographic
50
- # parentheses; the row passes end-to-end. Findings (map-vs-source, map
51
- # untouched): к̢ (position 37): printed cell "ķ" vs runtime 'k'.
52
- # Provenance artifact: scripts/row-sources/din-ab-Cyrl-Latn-1460-2-2011.json (39 rows).
50
+ # parentheses; the row passes end-to-end. Findings (map-vs-source) resolved in the E3 corpus-fixes round (2026-11-17): the
51
+ # map values now carry the printed cedilla (ķ/ņ, the DIN uvular/nasal
52
+ # series letters); the atv/az pos-37 stray-paren empty-target sub rule is
53
+ # replaced by the printed (ķ) value. The rows are part of the generated
54
+ # set; the per-cell notes above record the printed readings.
55
+ # Provenance artifact: scripts/row-sources/din-ab-Cyrl-Latn-1460-2-2011.json (40 rows).
53
56
  # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-16); regenerate from the artifact, do not hand-edit.
54
57
  "a" -> "a"
55
58
  "б" -> "b"
@@ -65,6 +68,7 @@ tests {
65
68
  "ӡ" -> "z̈"
66
69
  "и" -> "i"
67
70
  "к" -> "k"
71
+ "к̢" -> "ķ"
68
72
  "ҟ" -> "q"
69
73
  "л" -> "l"
70
74
  "м" -> "m"
@@ -108,7 +112,7 @@ stage main {
108
112
  sub "ӡ" "z̈"
109
113
  sub "и" "i"
110
114
  sub "к" "k"
111
- sub "к̢" "k"
115
+ sub "к̢" "ķ"
112
116
  sub "ҟ" "q"
113
117
  sub "л" "l"
114
118
  sub "м" "m"