interscript-maps 2.5.2 → 3.0.0

data/maps/bgnpcgn-iu-Cans-Latn-2013.isc

@@ -0,0 +1,280 @@
+system "BGN-PCGN:iu-Cans:Latn:2013" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2013
+  language iso-639-2:iu
+  source_script Cans
+  destination_script Latn
+  name Romanization of Inuktitut (2013 Agreement)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2013
+  confirmation_date 2018-06
+  description {
+    The BGN/PCGN system for Inuktitut romanizes Canadian Aboriginal Syllabics
+    (qaniujaaqpait) used for geographic names in Nunavut. The syllabic chart was
+    approved by the Inuit Cultural Institute at Arviat in 1976. The BGN/PCGN
+    agreement is dated 2013 and was checked for validity and accuracy in June 2018.
+  }
+
+  notes {
+    note "Syllabics are official for geographic names only in Nunavut, Canada. The 1976 chart applies to all Inuktitut dialects."
+    note "The s/h column is pronounced s in eastern dialects and h in the Kivalliq and Qitirmiut dialects. This map romanizes it as s."
+    note "The ng column is a single consonant. It is romanized ng; Nattilingmiutut sources may write the velar nasal with the letter eng (U+014B)."
+    note "The letters ł, š, and ř occur in Nattilingmiutut. The Roman encodings are U+0142, U+0161, and U+0159."
+    note "Naaniit (finals) are superscript consonant forms and denote syllable-final consonants. A final followed by a consonant-initial syllable is the only occurrence of a consonant cluster in Inuktitut."
+    note "A lengthened vowel is marked by a dot above the syllabic and is romanized as a doubled vowel. The map accepts the precomposed long-vowel characters."
+    note "The barred-s column (header h, footnote 2) and the š column have no Unicode encoding in the source document; the source presents them as raster images. This map does not accept those characters."
+    note "The ř column is stored in the source PDF at the Unicode TH-CREE codepoints U+15A7, U+15AA, U+15AC, and U+15AE. The map romanizes those codepoints as ři, řu, řa, and ř."
+    note "The Roman letter H is inserted in syllabics for some words borrowed from English and is romanized h."
+    note "The glottal stop is written with an inverted apostrophe (U+2018) in both syllabics and Roman script and is retained."
+    note "Generally no more than two vowels appear in a row. The sequence uai occurs in the North Qikiqtani dialect."
+    note "Consonants assimilate to the following consonant in pronunciation. The map romanizes the written final, so the written form of an assimilated sequence is preserved."
+    note "The Roman-script columns are shown in lower case in the source. This map applies title case to each word."
+  }
+}
+
+tests {
+   "ᐃ" ->  "I"
+   "ᐄ" ->  "Ii"
+   "ᐅ" ->  "U"
+   "ᐆ" ->  "Uu"
+   "ᐊ" ->  "A"
+   "ᐋ" ->  "Aa"
+   "ᐱ" ->  "Pi"
+   "ᐲ" ->  "Pii"
+   "ᐳ" ->  "Pu"
+   "ᐴ" ->  "Puu"
+   "ᐸ" ->  "Pa"
+   "ᐹ" ->  "Paa"
+   "ᑉ" ->  "P"
+   "ᑎ" ->  "Ti"
+   "ᑏ" ->  "Tii"
+   "ᑐ" ->  "Tu"
+   "ᑑ" ->  "Tuu"
+   "ᑕ" ->  "Ta"
+   "ᑖ" ->  "Taa"
+   "ᑦ" ->  "T"
+   "ᑭ" ->  "Ki"
+   "ᑮ" ->  "Kii"
+   "ᑯ" ->  "Ku"
+   "ᑰ" ->  "Kuu"
+   "ᑲ" ->  "Ka"
+   "ᑳ" ->  "Kaa"
+   "ᒃ" ->  "K"
+   "ᒋ" ->  "Gi"
+   "ᒌ" ->  "Gii"
+   "ᒍ" ->  "Gu"
+   "ᒎ" ->  "Guu"
+   "ᒐ" ->  "Ga"
+   "ᒑ" ->  "Gaa"
+   "ᒡ" ->  "G"
+   "ᒥ" ->  "Mi"
+   "ᒦ" ->  "Mii"
+   "ᒧ" ->  "Mu"
+   "ᒨ" ->  "Muu"
+   "ᒪ" ->  "Ma"
+   "ᒫ" ->  "Maa"
+   "ᒻ" ->  "M"
+   "ᓂ" ->  "Ni"
+   "ᓃ" ->  "Nii"
+   "ᓄ" ->  "Nu"
+   "ᓅ" ->  "Nuu"
+   "ᓇ" ->  "Na"
+   "ᓈ" ->  "Naa"
+   "ᓐ" ->  "N"
+   "ᓯ" ->  "Si"
+   "ᓰ" ->  "Sii"
+   "ᓱ" ->  "Su"
+   "ᓲ" ->  "Suu"
+   "ᓴ" ->  "Sa"
+   "ᓵ" ->  "Saa"
+   "ᔅ" ->  "S"
+   "ᓕ" ->  "Li"
+   "ᓖ" ->  "Lii"
+   "ᓗ" ->  "Lu"
+   "ᓘ" ->  "Luu"
+   "ᓚ" ->  "La"
+   "ᓛ" ->  "Laa"
+   "ᓪ" ->  "L"
+   "ᔨ" ->  "Ji"
+   "ᔩ" ->  "Jii"
+   "ᔪ" ->  "Ju"
+   "ᔫ" ->  "Juu"
+   "ᔭ" ->  "Ja"
+   "ᔮ" ->  "Jaa"
+   "ᔾ" ->  "J"
+   "ᕕ" ->  "Vi"
+   "ᕖ" ->  "Vii"
+   "ᕗ" ->  "Vu"
+   "ᕘ" ->  "Vuu"
+   "ᕙ" ->  "Va"
+   "ᕚ" ->  "Vaa"
+   "ᕝ" ->  "V"
+   "ᕆ" ->  "Ri"
+   "ᕇ" ->  "Rii"
+   "ᕈ" ->  "Ru"
+   "ᕉ" ->  "Ruu"
+   "ᕋ" ->  "Ra"
+   "ᕌ" ->  "Raa"
+   "ᕐ" ->  "R"
+   "ᕿ" ->  "Qi"
+   "ᖀ" ->  "Qii"
+   "ᖁ" ->  "Qu"
+   "ᖂ" ->  "Quu"
+   "ᖃ" ->  "Qa"
+   "ᖄ" ->  "Qaa"
+   "ᖅ" ->  "Q"
+   "ᖏ" ->  "Ngi"
+   "ᖐ" ->  "Ngii"
+   "ᖑ" ->  "Ngu"
+   "ᖒ" ->  "Nguu"
+   "ᖓ" ->  "Nga"
+   "ᖔ" ->  "Ngaa"
+   "ᖕ" ->  "Ng"
+   "ᖠ" ->  "Łi"
+   "ᖡ" ->  "Łii"
+   "ᖢ" ->  "Łu"
+   "ᖣ" ->  "Łuu"
+   "ᖤ" ->  "Ła"
+   "ᖥ" ->  "Łaa"
+   "ᖦ" ->  "Ł"
+   "ᖧ" ->  "Ři"
+   "ᖨ" ->  "Řii"
+   "ᖪ" ->  "Řu"
+   "ᖫ" ->  "Řuu"
+   "ᖬ" ->  "Řa"
+   "ᖭ" ->  "Řaa"
+   "ᖮ" ->  "Ř"
+   "H" ->  "H"
+   "‘" ->  "‘"
+   "ᐃ‘" ->  "I‘"
+   "ᐃᓄᒃ" ->  "Inuk"
+   "ᓇᐅᔮᑦ" ->  "Naujaat"
+   "ᓄᓇᕗᑦ" ->  "Nunavut"
+   "ᓄᓇᕗᒻᒥ" ->  "Nunavummi"
+}
+
+stage main {
+
+  parallel {
+    sub "ᐃ" "i"
+    sub "ᐄ" "ii"
+    sub "ᐅ" "u"
+    sub "ᐆ" "uu"
+    sub "ᐊ" "a"
+    sub "ᐋ" "aa"
+    sub "ᐱ" "pi"
+    sub "ᐲ" "pii"
+    sub "ᐳ" "pu"
+    sub "ᐴ" "puu"
+    sub "ᐸ" "pa"
+    sub "ᐹ" "paa"
+    sub "ᑉ" "p"
+    sub "ᑎ" "ti"
+    sub "ᑏ" "tii"
+    sub "ᑐ" "tu"
+    sub "ᑑ" "tuu"
+    sub "ᑕ" "ta"
+    sub "ᑖ" "taa"
+    sub "ᑦ" "t"
+    sub "ᑭ" "ki"
+    sub "ᑮ" "kii"
+    sub "ᑯ" "ku"
+    sub "ᑰ" "kuu"
+    sub "ᑲ" "ka"
+    sub "ᑳ" "kaa"
+    sub "ᒃ" "k"
+    sub "ᒋ" "gi"
+    sub "ᒌ" "gii"
+    sub "ᒍ" "gu"
+    sub "ᒎ" "guu"
+    sub "ᒐ" "ga"
+    sub "ᒑ" "gaa"
+    sub "ᒡ" "g"
+    sub "ᒥ" "mi"
+    sub "ᒦ" "mii"
+    sub "ᒧ" "mu"
+    sub "ᒨ" "muu"
+    sub "ᒪ" "ma"
+    sub "ᒫ" "maa"
+    sub "ᒻ" "m"
+    sub "ᓂ" "ni"
+    sub "ᓃ" "nii"
+    sub "ᓄ" "nu"
+    sub "ᓅ" "nuu"
+    sub "ᓇ" "na"
+    sub "ᓈ" "naa"
+    sub "ᓐ" "n"
+    sub "ᓯ" "si"
+    sub "ᓰ" "sii"
+    sub "ᓱ" "su"
+    sub "ᓲ" "suu"
+    sub "ᓴ" "sa"
+    sub "ᓵ" "saa"
+    sub "ᔅ" "s"
+    sub "ᓕ" "li"
+    sub "ᓖ" "lii"
+    sub "ᓗ" "lu"
+    sub "ᓘ" "luu"
+    sub "ᓚ" "la"
+    sub "ᓛ" "laa"
+    sub "ᓪ" "l"
+    sub "ᔨ" "ji"
+    sub "ᔩ" "jii"
+    sub "ᔪ" "ju"
+    sub "ᔫ" "juu"
+    sub "ᔭ" "ja"
+    sub "ᔮ" "jaa"
+    sub "ᔾ" "j"
+    sub "ᕕ" "vi"
+    sub "ᕖ" "vii"
+    sub "ᕗ" "vu"
+    sub "ᕘ" "vuu"
+    sub "ᕙ" "va"
+    sub "ᕚ" "vaa"
+    sub "ᕝ" "v"
+    sub "ᕆ" "ri"
+    sub "ᕇ" "rii"
+    sub "ᕈ" "ru"
+    sub "ᕉ" "ruu"
+    sub "ᕋ" "ra"
+    sub "ᕌ" "raa"
+    sub "ᕐ" "r"
+    sub "ᕿ" "qi"
+    sub "ᖀ" "qii"
+    sub "ᖁ" "qu"
+    sub "ᖂ" "quu"
+    sub "ᖃ" "qa"
+    sub "ᖄ" "qaa"
+    sub "ᖅ" "q"
+    sub "ᖏ" "ngi"
+    sub "ᖐ" "ngii"
+    sub "ᖑ" "ngu"
+    sub "ᖒ" "nguu"
+    sub "ᖓ" "nga"
+    sub "ᖔ" "ngaa"
+    sub "ᖕ" "ng"
+    sub "ᖠ" "łi"
+    sub "ᖡ" "łii"
+    sub "ᖢ" "łu"
+    sub "ᖣ" "łuu"
+    sub "ᖤ" "ła"
+    sub "ᖥ" "łaa"
+    sub "ᖦ" "ł"
+    sub "ᖧ" "ři"
+    sub "ᖨ" "řii"
+    sub "ᖪ" "řu"
+    sub "ᖫ" "řuu"
+    sub "ᖬ" "řa"
+    sub "ᖭ" "řaa"
+    sub "ᖮ" "ř"
+    sub "H" "h"
+    sub "h" "h"
+    sub "‘" "‘"
+  }
+
+  title_case
+}
+
+}

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

@@ -0,0 +1,295 @@
+system "BGN-PCGN:kbd-Cyrl:Latn:2011" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2011
+  language iso-639-2:kbd
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Kabardian (2011)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2011
+  confirmation_date 2017-10
+  description {
+    The BGN/PCGN system for Kabardian is designed for use in romanizing names written in the
+    Kabardian Cyrillic alphabet. Kabardian, of the north-western Caucasian language family, is
+    principally spoken in Russia's republics of Kabardino-Balkariya and Karachayevo-Cherkesiya
+    and has been written in a modified Cyrillic script since 1936. Also known as East
+    Circassian, Kabardian is notable for its rich density of consonant phonemes (most
+    commentators agree on an inventory of 47 or 48) and corresponding paucity of vowels.
+    Kabardian letters are addressed in the romanizations as per their articulation:
+    glottalised consonants are marked with an apostrophe, and labialized consonants with w.
+  }
+
+  notes {
+    note "У should be romanized as w or u according to context: w should be used word-initially, and u used elsewhere, except as in combinations occurring elsewhere in the table."
+    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 letter Хь is romanized h with the combining macron below (U+0048+0033 for the capital; U+1E96 precomposed for the lower case); the table column shows the precomposed ẖ."
+    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 "Ä (U+00C4)  ä (U+00E4)  Ź (U+0179)  ź (U+017A)  Ś (U+015A)  ś (U+015B)  Ë (U+00CB)  ë (U+00EB)  H̱ (0048+0031)  ẖ (0068+0031)"
+    note "The source document prints the H̱ inventory codepoint as 0048+0031; the glyph shown is h with the combining macron below (U+0331)."
+    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"
+   "Э" ->  "Ä"
+   "э" ->  "ä"
+   "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"
+   "Е" ->  "E"
+   "е" ->  "e"
+   "Ё" ->  "Ë"
+   "ё" ->  "ë"
+   "Ж" ->  "Zh"
+   "ж" ->  "zh"
+   "Жь" ->  "Ź"
+   "жь" ->  "ź"
+   "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’"
+   "Кхъ" ->  "Q"
+   "кхъ" ->  "q"
+   "Кхъу" ->  "Qw"
+   "кхъу" ->  "qw"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "Лъ" ->  "Lh"
+   "лъ" ->  "lh"
+   "ЛӀ" ->  "L’"
+   "лӀ" ->  "l’"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "ПӀ" ->  "P’"
+   "пӀ" ->  "p’"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "ТӀ" ->  "T’"
+   "тӀ" ->  "t’"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "ФӀ" ->  "F’"
+   "фӀ" ->  "f’"
+   "Х" ->  "Kh"
+   "х" ->  "kh"
+   "Ху" ->  "Khw"
+   "ху" ->  "khw"
+   "Хь" ->  "H̱"
+   "хь" ->  "ẖ"
+   "Хъ" ->  "X"
+   "хъ" ->  "x"
+   "Хъу" ->  "Xw"
+   "хъу" ->  "xw"
+   "Ц" ->  "Ts"
+   "ц" ->  "ts"
+   "ЦӀ" ->  "Ts’"
+   "цӀ" ->  "ts’"
+   "Ч" ->  "Ch"
+   "ч" ->  "ch"
+   "Ш" ->  "Sh"
+   "ш" ->  "sh"
+   "Щ" ->  "Ś"
+   "щ" ->  "ś"
+   "ЩӀ" ->  "Ś’"
+   "щӀ" ->  "ś’"
+   "Ъ" ->  "’’"
+   "ъ" ->  "’’"
+   "Ы" ->  "Y"
+   "ы" ->  "y"
+   "Ь" ->  "’"
+   "ь" ->  "’"
+   "Ю" ->  "Yu"
+   "ю" ->  "yu"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+   "Ӏ" ->  "’"
+   "Ӏу" ->  "’w"
+  # note 1: У word-initially w, elsewhere u
+   "У" ->  "W"
+   "у" ->  "w"
+   "Ужи" ->  "Wzhi"
+   "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 "Кхъу" "Qw"
+    sub "Гъу" "Ghw"
+    sub "Къу" "Qw’"
+    sub "КӀу" "Kw’"
+    sub "Хъу" "Xw"
+    sub "Кхъ" "Q"
+    sub "Гу" "Gw"
+    sub "Гъ" "Gh"
+    sub "Дж" "J"
+    sub "Дз" "Dz"
+    sub "Жь" "Ź"
+    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 "Хь" "H̱"
+    sub "Хъ" "X"
+    sub "ЦӀ" "Ts’"
+    sub "ЩӀ" "Ś’"
+    sub "Ӏу" "’w"
+    sub "Ъ" "’’"
+    sub "Ы" "Y"
+    sub "Ь" "’"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+    sub "А" "A"
+    sub "Э" "Ä"
+    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 "Щ" "Ś"
+    sub "Ӏ" "’"
+
+    sub "кхъу" "qw"
+    sub "гъу" "ghw"
+    sub "къу" "qw’"
+    sub "кӀу" "kw’"
+    sub "хъу" "xw"
+    sub "кхъ" "q"
+    sub "гу" "gw"
+    sub "гъ" "gh"
+    sub "дж" "j"
+    sub "дз" "dz"
+    sub "жь" "ź"
+    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 "хь" "ẖ"
+    sub "хъ" "x"
+    sub "цӀ" "ts’"
+    sub "щӀ" "ś’"
+    sub "ъ" "’’"
+    sub "ы" "y"
+    sub "ь" "’"
+    sub "ю" "yu"
+    sub "я" "ya"
+    sub "а" "a"
+    sub "э" "ä"
+    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 "щ" "ś"
+  }
+
+}
+
+}