Skip to content

feat: catalogue refresh to 402 systems + runtime .isc backfill #223

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ronaldtse merged 2 commits into from
Nov 3, 2026
Merged

feat: catalogue refresh to 402 systems + runtime .isc backfill #223

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
121eee0
feat: refresh catalogue to 402 systems; restore three runtime .isc files
ronaldtse Nov 3, 2026
954edb7
fix(ml): align the ledger template with the current models-catalogue …
ronaldtse Nov 3, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
181 changes: 181 additions & 0 deletions public/maps/bgnpcgn-av-Cyrl-Latn-2011.isc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,181 @@
system "BGN-PCGN:av-Cyrl:Latn:2011" {

metadata {
authority_id bgnpcgn
id 2011
language iso-639-1:av
source_script Cyrl
destination_script Latn
name Romanization of Avar (BGN/PCGN 2011 System)
url https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20AVAR.pdf
creation_date 2011
confirmation_date 2017-10
description { The BGN/PCGN system for Avar is designed for use in romanizing names written
in the Avar Cyrillic alphabet. Avar is a consonant-rich north-eastern Caucasian language,
spoken principally in Russia’s republic of Dagestan. It has been written in a modified
Cyrillic script since 1938 and, as other Caucasian languages, features glottalised
consonants, and though these are not marked with a uniform marker in Avar Cyrillic, an
apostrophe denotes the glottalised form of consonants in this romanization table.
}

notes {
note "Е should be romanized ‘ye’ word-initially, and after a vowel, and ‘e’ elsewhere."
note "In order to retain reversibility, where two consonant characters appear together and the resulting romanization is equivalent to a Roman-script digraph occurring in the system (i.e. gh, zh, tl, sh or ts), a medial dot may be employed between the Roman-script consonants (e.g. g·h) in order to distinguish these from the Roman-script digraphs."
note "Ё, Ф, Ъ, Ы and Ь occur only in loanwords, except as they appear in character combinations addressed elsewhere in the table, and are represented in the same style as in the BGN/PCGN Romanization System for Russian."
note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n\nAll apostrophes appearing in romanization are U+2019\n\nĠ (U+0047+0307) ġ (U+0067+0307)\nË (U+00CB) ë (U+00EB)"
note "The Romanization columns show only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
}
}

tests {
"МагӀарул" -> "Mag\u0307arul"
"магӀу" -> "mag\u0307u"
"Дагъистан" -> "Daghistan"
"авал" -> "awal"
"кьибил" -> "tl’ibil"
"лъимер" -> "lhimer"
"лъагӀал" -> "lhag\u0307al"
"чӀужу" -> "ch’uzhu"
"цӀар" -> "ts’ar"
"рухӀ" -> "ruh\u0331"
"тӀехь" -> "t’ekh"
"гьабе" -> "habe"
"гьечӀо" -> "hech’o"
"емен" -> "yemen"
"дуе" -> "duye"
"Емен" -> "Yemen"
"щу" -> "shshu"
"рукъ" -> "ruq’"
"хъизан" -> "qizan"
"жо" -> "zho"
"ши" -> "shi"
}

aliases {
av_vowel = any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
}

stage main {

# RULES
# note[1]: ‘ye’ word-initially and after a vowel, ‘e’ elsewhere
sub {
from "\u0415"
to "YЕ"
before av_vowel
}
sub {
from "\u0415"
to "Yе"
before boundary
}
sub {
from "\u0435"
to "yе"
before av_vowel
}
sub {
from "\u0435"
to "yе"
before boundary
}

# CHARACTERS
parallel {
sub "А" "A"
sub "а" "a"
sub "Б" "B"
sub "б" "b"
sub "В" "W"
sub "в" "w"
sub "Г" "G"
sub "г" "g"
sub "Гъ" "Gh"
sub "гъ" "gh"
sub "Гь" "H"
sub "гь" "h"
sub "ГӀ" "G\u0307"
sub "гӀ" "g\u0307"
sub "Д" "D"
sub "д" "d"
sub "Е" "E"
sub "е" "e"
sub "Ё" "Ë"
sub "ё" "ë"
sub "Ж" "Zh"
sub "ж" "zh"
sub "З" "Z"
sub "з" "z"
sub "И" "I"
sub "и" "i"
sub "Й" "Y"
sub "й" "y"
sub "К" "K"
sub "к" "k"
sub "Къ" "Q’"
sub "къ" "q’"
sub "Кь" "Tl’"
sub "кь" "tl’"
sub "КӀ" "K’"
sub "кӀ" "k’"
sub "Л" "L"
sub "л" "l"
sub "Лъ" "Lh"
sub "лъ" "lh"
sub "ЛӀ" "Tl"
sub "лӀ" "tl"
sub "М" "M"
sub "м" "m"
sub "Н" "N"
sub "н" "n"
sub "О" "O"
sub "о" "o"
sub "П" "P"
sub "п" "p"
sub "Р" "R"
sub "р" "r"
sub "С" "S"
sub "с" "s"
sub "Т" "T"
sub "т" "t"
sub "ТӀ" "T’"
sub "тӀ" "t’"
sub "У" "U"
sub "у" "u"
sub "Ф" "F"
sub "ф" "f"
sub "Х" "X"
sub "х" "x"
sub "Хъ" "Q"
sub "хъ" "q"
sub "Хь" "Kh"
sub "хь" "kh"
sub "ХӀ" "H\u0331"
sub "хӀ" "h\u0331"
sub "Ц" "Ts"
sub "ц" "ts"
sub "ЦӀ" "Ts’"
sub "цӀ" "ts’"
sub "Ч" "Ch"
sub "ч" "ch"
sub "ЧӀ" "Ch’"
sub "чӀ" "ch’"
sub "Ш" "Sh"
sub "ш" "sh"
sub "Щ" "Shsh"
sub "щ" "shsh"
sub "Ъ" "\u2019\u2019"
sub "ъ" "\u2019\u2019"
sub "Ы" "Y"
sub "ы" "y"
sub "Ь" "\u2019"
sub "ь" "\u2019"
sub "Э" "E"
sub "э" "e"
sub "Ю" "Yu"
sub "ю" "yu"
sub "Я" "Ya"
sub "я" "ya"
}
}
}
179 changes: 179 additions & 0 deletions public/maps/bgnpcgn-cv-Cyrl-Latn-2011.isc
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,179 @@
system "BGN-PCGN:cv-Cyrl:Latn:2011" {

metadata {
authority_id bgnpcgn
id 2011
language iso-639-1:cv
source_script Cyrl
destination_script Latn
name Romanization of Chuvash (BGN/PCGN 2011 System)
url https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20CHUVASH.pdf
creation_date 2011
confirmation_date 2017-10
description { The BGN/PCGN system for Chuvash is designed for use in romanizing names written
in the Chuvash Cyrillic alphabet. Chuvash is an official language within Chuvashiya, one of
the republics of the Russian Federation.
}

notes {
note "The character e should be romanized ye initially, after the vowel characters a, e, ё, и, о, у, ы, э, ю, and я, and after й, ъ, and ь. In all other instances, it should be romanized e."
note "The character ё should be romanized yë initially, after the vowel characters a, e, ё, и, о, у, ы, э, ю, and я, and after й, ъ, and ь. In all other instances, it should be romanized ё. Often the dieresis is not shown in Cyrillic, and in this case, the character should be romanized as ‘ë’/‘yë’, as outlined above, if known to be relevant, or otherwise ‘e’/‘ye’ as described in note 1."
note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:\n\nĂ (U+0102) ă (U+0103)\nË (U+00CB) ë (U+00EB)\nĔ (U+0114) ĕ (U+0115)\nŚ (U+015A) ś (U+015B)\nÜ (U+00DC) ü (U+00FC)\nĖ (U+0116) ė (U+0117)"
note "The Romanization columns show only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
note "The source table renders the Cyrillic letter ҫ (U+04AA, U+04AB) with the glyphs of Latin ç (U+00C7, U+00E7); this implementation maps from the Cyrillic codepoints."
}
}

tests {
"Чӑвашла" -> "Chăvashla"
"Шупашкар" -> "Shupashkar"
"Ҫӗнӗ Шупашкар" -> "Śĕnĕ Shupashkar"
"ҫын" -> "śyn"
"ӗмӗр" -> "ĕmĕr"
"шыв" -> "shyv"
"хӗвел" -> "khĕvel"
"ҫул" -> "śul"
"сӑмах" -> "sămakh"
"ӳсентӑран" -> "üsentăran"
"кӳлĕ" -> "külĕ"
"иҫҫе" -> "iśśe"
"пулес" -> "pules"
"Етӗрне" -> "Yetĕrne"
"проект" -> "proyekt"
"Ӗпхӳ" -> "Ĕpkhü"
"йывӑҫ" -> "yyvăś"
"Вырӑс" -> "Vyrăs"
"музей" -> "muzey"
"театр" -> "teatr"
}

aliases {
cv_extvowel = any("АаЕеЁёИиОоУуЫыЭэЮюЯяЙйЪъЬь")
}

stage main {

# RULES
# note[1]: ye initially, after the vowel characters and after й, ъ, and ь
sub {
from "\u0415"
to "YЕ"
before cv_extvowel
}
sub {
from "\u0415"
to "Yе"
before boundary
}
sub {
from "\u0435"
to "yе"
before cv_extvowel
}
sub {
from "\u0435"
to "yе"
before boundary
}

# note[2]: yë initially, after the vowel characters and after й, ъ, and ь
sub {
from "\u0401"
to "Yë"
before cv_extvowel
}
sub {
from "\u0401"
to "Yë"
before boundary
}
sub {
from "\u0451"
to "yë"
before cv_extvowel
}
sub {
from "\u0451"
to "yë"
before boundary
}

# CHARACTERS
parallel {
sub "А" "A"
sub "а" "a"
sub "Ӑ" "Ă"
sub "ӑ" "ă"
sub "Б" "B"
sub "б" "b"
sub "В" "V"
sub "в" "v"
sub "Г" "G"
sub "г" "g"
sub "Д" "D"
sub "д" "d"
sub "Е" "E"
sub "е" "e"
sub "Ё" "Ë"
sub "ё" "ë"
sub "Ӗ" "Ĕ"
sub "ӗ" "ĕ"
sub "Ж" "Zh"
sub "ж" "zh"
sub "З" "Z"
sub "з" "z"
sub "И" "I"
sub "и" "i"
sub "Й" "Y"
sub "й" "y"
sub "К" "K"
sub "к" "k"
sub "Л" "L"
sub "л" "l"
sub "М" "M"
sub "м" "m"
sub "Н" "N"
sub "н" "n"
sub "О" "O"
sub "о" "o"
sub "П" "P"
sub "п" "p"
sub "Р" "R"
sub "р" "r"
sub "С" "S"
sub "с" "s"
sub "Ҫ" "Ś"
sub "ҫ" "ś"
sub "Т" "T"
sub "т" "t"
sub "У" "U"
sub "у" "u"
sub "Ӳ" "Ü"
sub "ӳ" "ü"
sub "Ф" "F"
sub "ф" "f"
sub "Х" "Kh"
sub "х" "kh"
sub "Ц" "Ts"
sub "ц" "ts"
sub "Ч" "Ch"
sub "ч" "ch"
sub "Ш" "Sh"
sub "ш" "sh"
sub "Щ" "Shch"
sub "щ" "shch"
sub "Ъ" "\u201D"
sub "ъ" "\u201D"
sub "Ы" "Y"
sub "ы" "y"
sub "Ь" "\u2019"
sub "ь" "\u2019"
sub "Э" "Ė"
sub "э" "ė"
sub "Ю" "Yu"
sub "ю" "yu"
sub "Я" "Ya"
sub "я" "ya"
}
}
}
Loading
Loading