interscript-maps 2.5.1 → 3.0.0

data/maps/bgnpcgn-krc-Cyrl-Latn-2008.isc

@@ -0,0 +1,218 @@
+system "BGN-PCGN:krc-Cyrl:Latn:2008" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2008
+  language iso-639-2:krc
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Karachay-Balkar (Cyrillic-Roman) (2008 Agreement)
+  url https://www.gov.uk/government/organisations/permanent-committee-on-geographical-names
+  creation_date 2008
+  confirmation_date 2017-10
+  description {
+    Karachay-Balkar is an official language within Karachayevo-Cherkesiya and
+    Kabardino-Balkariya, two of the republics of the Russian Federation. It will normally
+    be encountered in Cyrillic script, in which case it should be romanized by means of
+    the Cyrillic-Roman table of correspondences given below.
+  }
+
+  notes {
+    note "The characters в, ц, щ and ь occur only in loan words."
+    note "J is the appropriate Roman rendering for ж, except when it occurs as a component of дж, which is rendered in Roman as a unitary character c."
+    note "У should be romanized as u, except when preceded by а, е, ё, и, о, у, ы, ю or я when it should be rendered w (e.g. яу = yaw)."
+    note "Ъ is not romanized, except in the combinations гъ, къ or нъ, which are rendered in Roman as ğ, q and ng respectively."
+    note "The Roman rendering yu is sometimes encountered in loan words and after certain vowels; this map renders ю as ü throughout."
+    note "An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters of the basic Roman script is:"
+    note "Ğ (U+011E)  ğ (U+011F)  Ö (U+00D6)  ö (U+00F6)  İ (U+0130)  ı (U+0131)  Ç (U+00C7)  ç (U+00E7)  Ş (U+015E)  ş (U+015F)  Ü (U+00DC)  ü (U+00FC)"
+    note "The Roman-script columns show only lowercase forms but, when applying the table, 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"
+   "Гъ" ->  "Ğ"
+   "гъ" ->  "ğ"
+   "Д" ->  "D"
+   "д" ->  "d"
+   "Дж" ->  "C"
+   "дж" ->  "c"
+   "Е" ->  "E"
+   "е" ->  "e"
+   "Ё" ->  "Ö"
+   "ё" ->  "ö"
+   "Ж" ->  "J"
+   "ж" ->  "j"
+   "З" ->  "Z"
+   "з" ->  "z"
+   "И" ->  "İ"
+   "и" ->  "i"
+   "Й" ->  "Y"
+   "й" ->  "y"
+   "К" ->  "K"
+   "к" ->  "k"
+   "Къ" ->  "Q"
+   "къ" ->  "q"
+   "Л" ->  "L"
+   "л" ->  "l"
+   "М" ->  "M"
+   "м" ->  "m"
+   "Н" ->  "N"
+   "н" ->  "n"
+   "Нъ" ->  "Ng"
+   "нъ" ->  "ng"
+   "нг" ->  "ng"
+   "Нг" ->  "Ng"
+   "О" ->  "O"
+   "о" ->  "o"
+   "П" ->  "P"
+   "п" ->  "p"
+   "Р" ->  "R"
+   "р" ->  "r"
+   "С" ->  "S"
+   "с" ->  "s"
+   "Т" ->  "T"
+   "т" ->  "t"
+   "Ў" ->  "W"
+   "ў" ->  "w"
+   "Ф" ->  "F"
+   "ф" ->  "f"
+   "Х" ->  "X"
+   "х" ->  "x"
+   "Ц" ->  "S"
+   "ц" ->  "s"
+   "Ч" ->  "Ç"
+   "ч" ->  "ç"
+   "Ш" ->  "Ş"
+   "ш" ->  "ş"
+   "Щ" ->  "Şç"
+   "щ" ->  "şç"
+   "Ъ" ->  ""
+   "ъ" ->  ""
+   "Ы" ->  "I"
+   "ы" ->  "ı"
+   "Ь" ->  ""
+   "ь" ->  ""
+   "Э" ->  "E"
+   "э" ->  "e"
+   "Ю" ->  "Ü"
+   "ю" ->  "ü"
+   "Я" ->  "Ya"
+   "я" ->  "ya"
+  # note 3: у after the listed vowels is w; source example яу = yaw
+   "яу" ->  "yaw"
+   "ую" ->  "uü"  # у + ю
+   "эу" ->  "eu"
+   "у" ->  "u"
+}
+
+stage main {
+
+  # RULES
+  # note 3: у after а, е, ё, и, о, у, ы, ю or я is w
+  sub {
+    from "У"
+    to "W"
+    before any("АаЕеЁёИиОоУуЫыЮюЯя")
+  }
+  sub {
+    from "у"
+    to "w"
+    before any("АаЕеЁёИиОоУуЫыЮюЯя")
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "НГ" "NG"
+    sub "Нг" "Ng"
+    sub "Гъ" "Ğ"
+    sub "Къ" "Q"
+    sub "Нъ" "Ng"
+    sub "Дж" "C"
+    sub "Ё" "Ö"
+    sub "И" "İ"
+    sub "Ч" "Ç"
+    sub "Ш" "Ş"
+    sub "Щ" "Şç"
+    sub "Ы" "I"
+    sub "Ю" "Ü"
+    sub "Я" "Ya"
+    sub "Ў" "W"
+    sub "Ъ" ""
+    sub "Ь" ""
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ж" "J"
+    sub "З" "Z"
+    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" "X"
+    sub "Ц" "S"
+    sub "Э" "E"
+
+    sub "нг" "ng"
+    sub "нъ" "ng"
+    sub "гъ" "ğ"
+    sub "къ" "q"
+    sub "дж" "c"
+    sub "ё" "ö"
+    sub "и" "i"
+    sub "ч" "ç"
+    sub "ш" "ş"
+    sub "щ" "şç"
+    sub "ы" "ı"
+    sub "ю" "ü"
+    sub "я" "ya"
+    sub "ў" "w"
+    sub "ъ" ""
+    sub "ь" ""
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ж" "j"
+    sub "з" "z"
+    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" "x"
+    sub "ц" "s"
+    sub "э" "e"
+  }
+
+}
+
+}

data/maps/bgnpcgn-kur-Arab-Latn-2007.isc

@@ -51,6 +51,8 @@ metadata {
 
     note "In pure Kurdish words, the vowel ى is always long î, e.g. كانى ماسێ\n Kanî Masê. When it represents îzafe, it is also romanized î and joined\n by means of a hyphen to its preceding word e.g. پارێزگاى دهۆك Parêzga-î\n Dihok."
 
+    note "The rare vowel row (waw with the combining macron above, U+0648+0304) is romanized ö; the source marks it rare and notes that it was previously written waw-waw. This map renders the marked sequence; the plain waw renders u per the vowel table."
+
     note "      An inventory of letter-diacritic combinations, used in addition to\n      the unmodified letters of the basic Roman script in the Romanization of\n      Kurdish, with their Unicode encoding, is:\n\n        '‘': '\\u2018' , '’': '2019'\n        'Ç': '00C7' , 'ç': '00E7'\n        'Ḍ': '1E0C' , 'ḍ': '1E0D'\n        'Ê': '00CA' , 'ê': '00EA'\n\n        # There is no single Unicode encoding for these letter-diacritic combinations.\n        'Ḧ': '0048+0308' , 'ḧ': '0068+0308'\n        'Î': '00CE' , 'î': '00EE'\n        'Ł': '0141' , 'ł': '0142'\n        'Ö': '00D6' , 'ö': '00F6'\n        'Ṟ': '1E5E' , 'ṟ': '1E5F'\n        'Ş': '015E' , 'ş': '015F'\n        'Ṣ': '1E62' , 'ṣ': '1E63'\n        'Ṭ': '1E6C' , 'ṭ': '1E6D'\n        'Û': '00DB' , 'û': '00FB'\n        'Ü': '00DC' , 'ü': '00FC'\n        'Ẍ': '1E8C' , 'ẍ': '1E8D'"
 
     note "The Romanization column shows only lowercase forms but, when\n romanizing, uppercase and lowercase Roman letters as appropriate should\n be used."
@@ -78,6 +80,7 @@ tests {
    "كِرِن" ->  "Kirin"
    "ئاگِر" ->  "Agir"
    "موحەممەد" ->  "Muḧemmed"
+   "و̄" ->  "Ö"  # waw + combining macron above (the rare vowel row; word-initial upcase applies)
   # - source: موسەننا # issue 604
   #   expected: Musanna
    "لەكوردِستانێ" ->  "Le Kurdistanê"
@@ -169,7 +172,7 @@ stage main {
     sub "\u0626\u0648\u0648" "û"
     sub "\u06C6" "o"
     sub "\u0626\u06C6" "o"
-    sub "\u0648" "ö"
+    sub "\u0648\u0304" "ö"
     sub "\u06CA" "ü"
   }
 

data/maps/bgnpcgn-mkd-Cyrl-Latn-1981.isc

@@ -47,6 +47,7 @@ tests {
 }
 
 dependency "var-Cyrl"
+dependency "var-kor"
 
 stage main {
 

data/maps/bgnpcgn-mkd-Cyrl-Latn-2013.isc

@@ -62,6 +62,7 @@ tests {
 }
 
 dependency "posix"
+dependency "var-kor"
 
 stage main {
 

data/maps/bgnpcgn-os-Cyrl-Latn-2009.isc

@@ -0,0 +1,187 @@
+system "BGN-PCGN:os-Cyrl:Latn:2009" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2009
+  language iso-639-1:os
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Ossetian (BGN/PCGN 2009 System)
+  url https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20OSSETIAN.pdf
+  creation_date 2009
+  confirmation_date 2017-11
+  description {    The BGN/PCGN system for Ossetian is designed for use in romanizing names written
+    in the Ossetian Cyrillic alphabet. Ossetian is a member of the north-eastern Iranian language
+    group and has over half a million speakers. It has principally been written in a modified
+    Cyrillic alphabet though a Roman alphabet was used between 1923 and 1938. The BGN/PCGN
+    Romanization System is derived from the correspondences between that Roman alphabet and
+    the Cyrillic alphabet used for Ossetian today, with modifications to suit an
+    English-language user.
+  }
+
+  notes {
+    note "The characters ё, ж, ш, щ, ъ, ь, э, ю, and я appear only in loan words and their romanizations in the Ossetian System are therefore as they appear in the BGN/PCGN Romanization System for Russian Cyrillic."
+    note "У has several different functions:\n\n• In combination with another vowel (either preceding or following) У is a ‘semi-vowel’ and should be romanized ‘w’ [e.g. Дзау → Dzaw (=Java)]\n\n• У also serves to labialize the consonants Г, Гъ, К, Къ, Х and Хъ and should also be romanized ‘w’ after each of these [e.g. Гуырдзы → Gwyrdzy (=Georgia)]\n\n• elsewhere У should be romanized ‘u’ [e.g. Республикӕ → Respublikӕ (=Republic)]."
+    note "Ъ should be represented with ”, except as it occurs in the digraph combinations гъ, къ, пъ, тъ, хъ or чъ representing the glottal consonants as shown separately in the table."
+    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\nÆ (U+00C6) æ (U+00E6)\nË (U+00CB) ë (U+00EB)"
+    note "The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase Roman letters as appropriate should be used."
+    note "Table footnotes: (1) Formerly /j/ in the Ossetian Roman-script alphabet. (2) Formerly /kh/ in the Ossetian Roman-script alphabet. (3) Formerly /h/ in the Ossetian Roman-script alphabet. (4) Formerly /dž/ in the Ossetian Roman-script alphabet. (5) Formerly /ph/ in the Ossetian Roman-script alphabet. (6) Formerly /th/ in the Ossetian Roman-script alphabet. (7) Formerly /x/ in the Ossetian Roman-script alphabet. (8) Formerly /c/ in the Ossetian Roman-script alphabet. (9) Formerly /ch/ in the Ossetian Roman-script alphabet. (10) Formerly /č/ in the Ossetian Roman-script alphabet. (11) Formerly /čh/ in the Ossetian Roman-script alphabet."
+    note "The source table’s Romanization column renders Е (U+0415, U+0435) with the Cyrillic glyph е; this is a typographical error in the source — Е is romanized as the Latin letter e, per the Russian-Cyrillic convention noted above."
+  }
+}
+
+tests {
+   "Дзау" ->  "Dzaw"
+   "Гуырдзы" ->  "Gwyrdzy"
+   "Республикӕ" ->  "Respublikæ"
+   "Ирыстон" ->  "Iryston"
+   "Цхинвал" ->  "Tskhinval"
+   "фӕндаг" ->  "fændag"
+   "хӕдзар" ->  "khædzar"
+   "мад" ->  "mad"
+   "дзуар" ->  "dzwar"
+   "куывд" ->  "kwyvd"
+   "къах" ->  "k’akh"
+   "цъити" ->  "ts’iti"
+   "чъыри" ->  "ch’yri"
+   "къуыри" ->  "k’wyri"
+   "хъӕу" ->  "qæw"
+   "объект" ->  "ob”ekt"
+   "адъютант" ->  "ad”yutant"
+   "машина" ->  "mashina"
+   "ӕвзаг" ->  "ævzag"
+}
+
+aliases {
+  os_vowel = any("АаІиЕеЁёОоЭэЮюЯяӔӕЫы")
+}
+
+stage main {
+
+  # RULES
+  # note[2]: У is a semi-vowel ‘w’ in combination with another vowel,
+  # either preceding or following
+  sub {
+    from "у"
+    to "w"
+    before os_vowel
+  }
+  sub {
+    from "у"
+    to "w"
+    after os_vowel
+  }
+  sub {
+    from "У"
+    to "W"
+    before os_vowel
+  }
+  sub {
+    from "У"
+    to "W"
+    after os_vowel
+  }
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "а" "a"
+    sub "Ӕ" "Æ"
+    sub "ӕ" "æ"
+    sub "Б" "B"
+    sub "б" "b"
+    sub "В" "V"
+    sub "в" "v"
+    sub "Г" "G"
+    sub "г" "g"
+    sub "Гу" "Gw"
+    sub "гу" "gw"
+    sub "Гъ" "Gh"
+    sub "гъ" "gh"
+    sub "Гъу" "Ghw"
+    sub "гъу" "ghw"
+    sub "Д" "D"
+    sub "д" "d"
+    sub "Дж" "J"
+    sub "дж" "j"
+    sub "Дз" "Dz"
+    sub "дз" "dz"
+    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 "Ку" "Kw"
+    sub "ку" "kw"
+    sub "Къ" "K’"
+    sub "къ" "k’"
+    sub "Къу" "K’w"
+    sub "къу" "k’w"
+    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 "Пъ" "P’"
+    sub "пъ" "p’"
+    sub "Р" "R"
+    sub "р" "r"
+    sub "С" "S"
+    sub "с" "s"
+    sub "Т" "T"
+    sub "т" "t"
+    sub "Тъ" "T’"
+    sub "тъ" "t’"
+    sub "У" "U"
+    sub "у" "u"
+    sub "Ф" "F"
+    sub "ф" "f"
+    sub "Х" "Kh"
+    sub "х" "kh"
+    sub "Ху" "Khw"
+    sub "ху" "khw"
+    sub "Хъ" "Q"
+    sub "хъ" "q"
+    sub "Хъу" "Qw"
+    sub "хъу" "qw"
+    sub "Ц" "Ts"
+    sub "ц" "ts"
+    sub "Цъ" "Ts’"
+    sub "цъ" "ts’"
+    sub "Ч" "Ch"
+    sub "ч" "ch"
+    sub "Чъ" "Ch’"
+    sub "чъ" "ch’"
+    sub "Ш" "Sh"
+    sub "ш" "sh"
+    sub "Щ" "Shch"
+    sub "щ" "shch"
+    sub "Ъ" "”"
+    sub "ъ" "”"
+    sub "Ы" "Y"
+    sub "ы" "y"
+    sub "Ь" "’"
+    sub "ь" "’"
+    sub "Э" "E"
+    sub "э" "e"
+    sub "Ю" "Yu"
+    sub "ю" "yu"
+    sub "Я" "Ya"
+    sub "я" "ya"
+  }
+}
+}