interscript-maps 2.5.1 → 3.0.0

data/maps/bas-rus-Cyrl-Latn-2017-bss.isc

@@ -40,6 +40,7 @@ tests {
 }
 
 dependency "posix"
+dependency "var-kor"
 
 stage main {
 

data/maps/bgnpcgn-ady-Cyrl-Latn-2012.isc

@@ -0,0 +1,333 @@
+system "BGN-PCGN:ady-Cyrl:Latn:2012" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2012
+  language iso-639-2:ady
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Adyghe (2012)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2012
+  confirmation_date 2017-10
+  description {
+    The BGN/PCGN system for Adyghe is designed for use in romanizing names written in the
+    Adyghe Cyrillic alphabet. Adyghe, a language of the north-western Caucasian family, is
+    principally spoken in Russia's republic of Adygeya and has been written in a modified
+    Cyrillic script since 1938. Also known as West Circassian, Adyghe is notable for its
+    rich density of consonant phonemes and corresponding paucity of vowels. Adyghe letters
+    are addressed in the romanizations as per their articulation: glottalised consonants
+    are marked with an apostrophe, labialized consonants with w, and retroflex consonants
+    with an underbar. Phonemes shared with Kabardian are represented as per the
+    BGN/PCGN Kabardian Romanization System.
+  }
+
+  notes {
+    note "У should be romanized as w or u according to context: w should be used word-initially, and u used elsewhere."
+    note "The characters Ё, Ъ, Ы and Ь (except as they occur in character combinations addressed elsewhere in the table) appear only in Russian loan words, and are thus romanized in the same style as in the BGN/PCGN Romanization System for Russian."
+    note "The palochka is romanized ’ except as it occurs in the combination Ӏу."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:"
+    note "All apostrophes appearing in romanization are U+2019"
+    note "Ë (U+00CB)  ë (U+00EB)  Ź (U+0179)  ź (U+017A)  Z͟H (U+005A+0048+035F)  z͟h (U+007A+0068+035F)  H̱ (0048+0031)  ẖ (0068+0031)  Č (U+010C)  č (U+010D)  S͟H (U+0053+0048+035F)  s͟h (U+0073+0068+035F)  Ś (U+015A)  ś (U+015B)  Ä (U+00C4)  ä (U+00E4)"
+    note "The source document prints the H̱ inventory codepoint as 0048+0031; the glyph shown is h with the combining macron below (U+0331) and the table column shows the precomposed ẖ (U+1E96). This map outputs ẖ (U+1E96)."
+    note "The Romanization columns show only lowercase forms but, when romanizing, uppercase and lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+  # every table row, upper and lower
+   "А" ->  "A"
+   "а" ->  "a"
+   "Б" ->  "B"
+   "б" ->  "b"
+   "В" ->  "V"
+   "в" ->  "v"
+   "Г" ->  "G"
+   "г" ->  "g"
+   "Гу" ->  "Gw"
+   "гу" ->  "gw"
+   "Гъ" ->  "Gh"
+   "гъ" ->  "gh"
+   "Гъу" ->  "Ghw"
+   "гъу" ->  "ghw"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Дж" ->  "J"
+   "дж" ->  "j"
+   "Дз" ->  "Dz"
+   "дз" ->  "dz"
+   "Дзу" ->  "Dzw"
+   "дзу" ->  "dzw"
+   "Е" ->  "E"
+   "е" ->  "e"
+   "Ё" ->  "Ë"
+   "ё" ->  "ë"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "Жь" ->  "Ź"
+   "жь" ->  "ź"
+   "Жъ" ->  "Z͟H"
+   "жъ" ->  "z͟h"
+   "Жъу" ->  "Z͟Hw"
+   "жъу" ->  "z͟hw"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "I"
+   "и" ->  "i"
+   "Й" ->  "Y"
+   "й" ->  "y"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Ку" ->  "Kw"
+   "ку" ->  "kw"
+   "КӀ" ->  "K’"
+   "кӀ" ->  "k’"
+   "КӀу" ->  "Kw’"
+   "кӀу" ->  "kw’"
+   "Къ" ->  "Q’"
+   "къ" ->  "q’"
+   "Къу" ->  "Qw’"
+   "къу" ->  "qw’"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "ЛӀ" ->  "L’"
+   "лӀ" ->  "l’"
+   "Лъ" ->  "Lh"
+   "лъ" ->  "lh"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "ПӀ" ->  "P’"
+   "пӀ" ->  "p’"
+   "ПӀу" ->  "Pw’"
+   "пӀу" ->  "pw’"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "ТӀ" ->  "T’"
+   "тӀ" ->  "t’"
+   "ТӀу" ->  "Tw’"
+   "тӀу" ->  "tw’"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "ФӀ" ->  "F’"
+   "фӀ" ->  "f’"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ху" ->  "Khw"
+   "ху" ->  "khw"
+   "Хъ" ->  "X"
+   "хъ" ->  "x"
+   "Хъу" ->  "Xw"
+   "хъу" ->  "xw"
+   "Хь" ->  "H̱"
+   "хь" ->  "ẖ"
+   "Ц" ->  "Ts"
+   "ц" ->  "ts"
+   "ЦӀ" ->  "Ts’"
+   "цӀ" ->  "ts’"
+   "Цу" ->  "Tsw"
+   "цу" ->  "tsw"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "ЧӀ" ->  "Ch’"
+   "чӀ" ->  "ch’"
+   "Чъ" ->  "Č"
+   "чъ" ->  "č"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "ШӀ" ->  "Sh’"
+   "шӀ" ->  "sh’"
+   "ШӀу" ->  "Shw’"
+   "шӀу" ->  "shw’"
+   "Шъ" ->  "S͟H"
+   "шъ" ->  "s͟h"
+   "Шъу" ->  "S͟Hw"
+   "шъу" ->  "s͟hw"
+   "Щ" ->  "Ś"
+   "щ" ->  "ś"
+   "Ъ" ->  "’’"
+   "ъ" ->  "’’"
+   "Ы" ->  "Y"
+   "ы" ->  "y"
+   "Ь" ->  "’"
+   "ь" ->  "’"
+   "Э" ->  "Ä"
+   "э" ->  "ä"
+   "Ю" ->  "Yu"
+   "ю" ->  "yu"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+   "Ӏ" ->  "’"
+   "Ӏу" ->  "’w"
+  # note 1: У word-initially w, elsewhere u
+   "У" ->  "W"
+   "у" ->  "w"
+   "Уфа" ->  "Wfa"
+   "уат" ->  "wat"
+   "мау" ->  "mau"
+}
+
+stage main {
+
+  # RULES
+  # note 1: У word-initially w, elsewhere u
+  sub {
+    from boundary + "У"
+    to "W"
+  }
+  sub {
+    from boundary + "у"
+    to "w"
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "Гъу" "Ghw"
+    sub "Жъу" "Z͟Hw"
+    sub "Къу" "Qw’"
+    sub "КӀу" "Kw’"
+    sub "ПӀу" "Pw’"
+    sub "ТӀу" "Tw’"
+    sub "Хъу" "Xw"
+    sub "Шъу" "S͟Hw"
+    sub "ШӀу" "Shw’"
+    sub "Дзу" "Dzw"
+    sub "Гу" "Gw"
+    sub "Гъ" "Gh"
+    sub "Дж" "J"
+    sub "Дз" "Dz"
+    sub "Жь" "Ź"
+    sub "Жъ" "Z͟H"
+    sub "Ку" "Kw"
+    sub "КӀ" "K’"
+    sub "Къ" "Q’"
+    sub "Лъ" "Lh"
+    sub "ЛӀ" "L’"
+    sub "ПӀ" "P’"
+    sub "ТӀ" "T’"
+    sub "ФӀ" "F’"
+    sub "Ху" "Khw"
+    sub "Хъ" "X"
+    sub "Хь" "H̱"
+    sub "Цу" "Tsw"
+    sub "ЦӀ" "Ts’"
+    sub "Чъ" "Č"
+    sub "ЧӀ" "Ch’"
+    sub "Шъ" "S͟H"
+    sub "ШӀ" "Sh’"
+    sub "Ӏу" "’w"
+    sub "Щ" "Ś"
+    sub "Ъ" "’’"
+    sub "Ы" "Y"
+    sub "Ь" "’"
+    sub "Э" "Ä"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ё" "Ë"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Й" "Y"
+    sub "К" "K"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub "О" "O"
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ц" "Ts"
+    sub "Ч" "Ch"
+    sub "Ш" "Sh"
+    sub "Ӏ" "’"
+
+    sub "гъу" "ghw"
+    sub "жъу" "z͟hw"
+    sub "къу" "qw’"
+    sub "кӀу" "kw’"
+    sub "пӀу" "pw’"
+    sub "тӀу" "tw’"
+    sub "хъу" "xw"
+    sub "шъу" "s͟hw"
+    sub "шӀу" "shw’"
+    sub "дзу" "dzw"
+    sub "гу" "gw"
+    sub "гъ" "gh"
+    sub "дж" "j"
+    sub "дз" "dz"
+    sub "жь" "ź"
+    sub "жъ" "z͟h"
+    sub "ку" "kw"
+    sub "кӀ" "k’"
+    sub "къ" "q’"
+    sub "лъ" "lh"
+    sub "лӀ" "l’"
+    sub "пӀ" "p’"
+    sub "тӀ" "t’"
+    sub "фӀ" "f’"
+    sub "ху" "khw"
+    sub "хъ" "x"
+    sub "хь" "ẖ"
+    sub "цу" "tsw"
+    sub "цӀ" "ts’"
+    sub "чъ" "č"
+    sub "чӀ" "ch’"
+    sub "шъ" "s͟h"
+    sub "шӀ" "sh’"
+    sub "щ" "ś"
+    sub "ъ" "’’"
+    sub "ы" "y"
+    sub "ь" "’"
+    sub "э" "ä"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "ë"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    sub "й" "y"
+    sub "к" "k"
+    sub "л" "l"
+    sub "м" "m"
+    sub "н" "n"
+    sub "о" "o"
+    sub "п" "p"
+    sub "р" "r"
+    sub "с" "s"
+    sub "т" "t"
+    sub "у" "u"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ц" "ts"
+    sub "ч" "ch"
+    sub "ш" "sh"
+  }
+
+}
+
+}

data/maps/bgnpcgn-av-Cyrl-Latn-2011.isc

@@ -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"
+  }
+}
+}