interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-bal-Arab-Latn-2008.isc

@@ -0,0 +1,294 @@
+system "BGN-PCGN:bal-Arab:Latn:2008" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2008
+  language iso-639-2:bal
+  source_script Arab
+  destination_script Latn
+  name ROMANIZATION OF BALUCHI -- BGN/PCGN 2008 System
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/693687/ROMANIZATION_OF_BALUCHI.pdf
+  creation_date 2008
+  confirmation_date 2017-11
+  description {    The following is the BGN/PCGN-approved romanization
+    system for deriving standard spellings of Baluchi
+    geographic names. The romanization system is based on
+    the Hunterian system of romanization, which has been
+    used by the Surveys of India and Pakistan for
+    romanizing Baluchi geographic names for more than one
+    hundred years. The romanization system is compatible
+    with all dialects of Baluchi, including Eastern
+    Baluchi, Western Baluchi, and Southern Baluchi.
+
+    The BGN/PCGN system laid out below includes diacritical
+    marks in order that the original script can be derived
+    from the romanized form (i.e. it is reversible). For
+    desk users requiring a diacritic-free form, these
+    diacritics can simply be removed. In almost every case
+    the same basic Roman-script characters are kept as are
+    used in the Hunterian system. The BGN/PCGN forms have
+    further been designed to harmonize with the BGN/PCGN
+    Urdu romanization system. In rigorous romanization
+    (i.e. including diacritics), retroflexion is marked by
+    a sub-dot, and aspiration is marked by an apostrophe,
+    where confusion with fricative digraphs could arise.
+    For letters used only in Arabic loan words, the
+    rigorous forms have further been designed to harmonize
+    with the BGN/PCGN Persian romanization system.
+  }
+
+  notes {
+    note "Occasionally, sequences of /z/ or /s/ plus /h/ may be\n encountered, i.e. z·h, s·h. These may be romanized with the\n Unicode 'center dot' (U+00B7) separating the two letters,\n to distinguish them from the digraphs /zh/ and /sh/."
+
+    note "The character ة is found very rarely in Baluchi, principally in certain Arabic religious terms, e.g. zakāt\n ('alms'). It should be romanized t."
+
+    note "When the letters ال are found, representing the Arabic\n definite article, the ل is assimilated to a following 'sun letter' ,د ,ث ,ت\n ل ,ظ ,ط , ض , ,ص ,ش ,س , ,ر ,ذ or ن and is romanized t, , d, , r, z, s, sh, ş, ẕ ţ z , l, n accordingly."
+
+    note "In romanization, the suffixes ءَ (-ā, singular definite)\n and ءِ (-ay, possessive) are connected to the previous word\n by a hyphen, though they are usually written separately."
+
+    note "The word for 'and', written as و or ءُ, should be\n romanized as –u-, linked by hyphens to the two words it\n connects; e.g.,\n ہ ٹد و س ٹد → Sind-u-Hind ('The Gangetic Plain')."
+
+    note "Except as specified in notes 4 and 5, word division in romanization should follow word division in the Baluchi script."
+
+    note "Note that the short vowels in the Baluchi examples are not pointed."
+
+    note "Certain initial, medial and final characters are not\n readily available in a Unicode-encoded font in a standalone form."
+
+    note "The Romanization columns show only lowercase forms but,\n when romanizing, uppercase and lowercase Roman letters as\n appropriate should be used."
+  }
+}
+
+tests {
+  # commented tests are blocked by https://github.com/interscript/interscript/issues/620
+  # 'cultivable patch of riverbed'
+   "بےنٹَگ" ->  "Benṭag"
+  # 'Japan'
+   "جاپان" ->  "Jāpān"
+   "اَرَبِستان" ->  "Arabistān"
+   "بُنجاه" ->  "Bunjāh"
+   "بَلوچِستان" ->  "Balochistān"
+  # 'village'
+   "حَلق" ->  "Ḩalq"
+  # 'foothills or skirts of a mountain'
+   "دامان" ->  "Dāmān"
+   "ڈاڈَر" ->  "Ḍāḍar"
+  # 'tomb'
+   "گُمبُذ" ->  "Gumbud͟h"
+  # 'crossroads'
+   "چار راہ" ->  "Chār Rāh"
+  # 'market'
+   "بازار" ->  "Bāzār"
+   "سےبِى" ->  "Sebī"
+  # - source: اِيشيا
+  #   expected: Eshyā
+  #   # 'homeland'
+  # - source: وَطَن
+  #   expected: Waţan
+  # 'Bandar Abbas'
+   "عَبّاس" ->  "‘Abbās"
+  # 'Taiwan'
+   "فارموسا" ->  "Fārmosā"
+   "ڈاک" ->  "Ḍāk"
+  # 'stream, irrigated area, pasture'
+   "مَلّ" ->  "Mall"
+  # - source: ہ یرات
+  #   expected: Herāt
+  # 'Philippines'
+   "فِلپائِن" ->  "Filpā’in"
+   "مُرگاپ" ->  "Murgāp"
+  # - source: مَرو
+  #   expected: Marw
+}
+
+stage main {
+  # CHARACTERS
+  parallel {
+
+    # consonant characters
+
+    sub "\u0628" "b"
+    sub "\u067E" "p"
+    sub "\u062a" "t"
+    sub "\u0679" "ṭ"
+    sub "\u067C" "ṭ"
+    sub "\u062B" "t͟h"
+    sub "\u067F" "t͟h"
+    sub "\u062c" "j"
+    sub "\u0686" "ch"
+    sub "\u062d" "ḩ"
+    sub "\u062e" "kh"
+    sub "\u062f" "d"
+    sub "\u0688" "ḍ"
+    sub "\u0689" "ḍ"
+    sub "\u0630" "d͟h"
+    sub "\u0631" "r"
+    sub "\u0691" "ṛ"
+    sub "\u0693" "ṛ"
+    sub "\u0632" "z"
+    sub "\u0698" "zh"
+    sub "\u0633" "s"
+    sub "\u0634" "sh"
+    sub "\u0635" "ş"
+    sub "\u0636" "ẕ"
+    sub "\u0637" "ţ"
+    sub "\u0638" "z̧"
+    sub "\u0639" "‘"
+    sub "\u063a" "gh"
+    sub "\u0641" "f"
+    sub "\u0642" "q"
+    sub "\u0643" "k"
+    sub "\u06A9" "k"
+    sub "\u06AF" "g"
+    sub "\u0644" "l"
+    sub "\u0645" "m"
+    sub "\u0646" "n"
+    sub "\u06BA" "ñ"
+    sub "\u0648" "o"
+
+    sub "\u0648" "w"
+    sub "\u0647" "h"
+    sub "\u06C1" "h"
+    sub "\u06BE" "h"
+    sub "\u0621" "’"
+    sub "\u0626" "’"
+    sub "\u0649" "y"
+    sub "\u064A" "y"
+
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u0628\u06BE" "bh"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u067E\u06BE" "ph"
+
+    # Aspiration is only contrastive in Eastern Baluchi.
+    # Apostrophe distinguishes from fricative /th/.
+    sub "\u062A\u06BE" "th’"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u0679\u06BE" "ṭh"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u062C\u06BE" "jh"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u0686\u06BE" "chh"
+
+    # Aspiration is only contrastive in Eastern Baluchi.
+    # Apostrophe distinguishes from fricative /dh/
+    sub "\u062D\u06BE" "dh’"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u0688\u06BE" "ḍh"
+
+    # Aspiration is only contrastive in Eastern Baluchi
+    sub "\u0631\u06BE" "\u1E5B\u0068"
+
+    # Aspiration is only contrastive in Eastern Baluchi.
+    # Apostrophe distinguishes from fricative /kh/
+    sub "\u06A9\u06BE" "kh’"
+
+    # Aspiration is only contrastive in Eastern Baluchi.
+    # Apostrophe distinguishes from fricative /gh/
+    sub "\u06AF\u06BE" "gh’"
+    sub "\u0644\u0627" "lā"
+    sub "\u06A9\u0627" "kā"
+    sub "\u06AF\u0627" "gā"
+    sub "\u06A9\u0644" "kl"
+    sub "\u06AF\u0644" "gl"
+
+    # Vowels, Diphthongs, and Diacritical Marks
+    sub "\u0650\u0649" "ī"
+    sub "\u0650" "i"
+    sub "\u06D2" "e"
+    sub {
+    from boundary + "\u0627"
+    to ""
+  }
+    sub "\u0627" "ā"
+    sub "\u0622" "ā"
+    sub "\u064E" "a"
+    sub "\u064F" "u"
+    sub "\u064F\u0648" "ū"
+    sub "\u064E\u06D2" "ay"
+    sub "\u064E\u0648" "aw"
+    sub "\u0652" ""
+    sub "\u0670" "á"
+
+    sub "\u0628\u0651" "bb"
+    sub "\u067E\u0651" "pp"
+    sub "\u062a\u0651" "tt"
+    sub "\u0679\u0651" "ṭṭ"
+    sub "\u067C\u0651" "ṭṭ"
+    sub "\u062B\u0651" "t͟ht͟h"
+    sub "\u067F\u0651" "t͟ht͟h"
+    sub "\u062c\u0651" "jj"
+    sub "\u0686\u0651" "chch"
+    sub "\u062d\u0651" "ḩḩ"
+    sub "\u062e\u0651" "khkh"
+    sub "\u062f\u0651" "dd"
+    sub "\u0688\u0651" "ḍḍ"
+    sub "\u0689\u0651" "ḍḍ"
+    sub "\u0630\u0651" "d͟hd͟h"
+    sub "\u0631\u0651" "rr"
+    sub "\u0691\u0651" "ṛṛ"
+    sub "\u0693\u0651" "ṛṛ"
+    sub "\u0632\u0651" "zz"
+    sub "\u0698\u0651" "zhzh"
+    sub "\u0633\u0651" "ss"
+    sub "\u0634\u0651" "shsh"
+    sub "\u0635\u0651" "şş"
+    sub "\u0636\u0651" "ẕẕ"
+    sub "\u0637\u0651" "ţţ"
+    sub "\u0638\u0651" "z̧z̧"
+    sub "\u0639\u0651" "‘‘"
+    sub "\u063a\u0651" "ghgh"
+    sub "\u0641\u0651" "ff"
+    sub "\u0642\u0651" "qq"
+    sub "\u0643\u0651" "kk"
+    sub "\u06A9\u0651" "kk"
+    sub "\u06AF\u0651" "gg"
+    sub "\u0644\u0651" "ll"
+    sub "\u0645\u0651" "mm"
+    sub "\u0646\u0651" "nn"
+    sub "\u06BA\u0651" "ññ"
+    sub "\u0648\u0651" "ww"
+    sub "\u0647\u0651" "hh"
+    sub "\u06C1\u0651" "hh"
+    sub "\u06BE\u0651" "hh"
+    sub "\u0621\u0651" "’’"
+    sub "\u0626\u0651" "’’"
+    sub "\u0649\u0651" "yy"
+
+    sub "\u0621\u064E" "-ā"
+    sub "\u0621\u0650" "-ay"
+
+    # Numerals
+    sub "۰" "0"
+    sub "۱" "1"
+    sub "۲" "2"
+    sub "۳" "3"
+    sub "۴" "4"
+    sub "۵" "5"
+    sub "۶" "6"
+    sub "۷" "7"
+    sub "۸" "8"
+    sub "۹" "9"
+    # Although Perso-Arabic script is written from right to
+    # left, numerical expressions, e.g. ۸۶۹۱ → 1968, are
+    # written from left to right. A comma is inserted into
+    # longer sequences, either after thousands, millions,     etc.
+  }
+
+
+  # POSTRULES
+  sub {
+    from any("\u0061".."\uFFFF")
+    to upcase
+    before boundary
+    not_before boundary + any("‘’'")
+  }
+
+
+}
+}

data/maps/bgnpcgn-bel-Cyrl-Latn-1979.isc

@@ -0,0 +1,207 @@
+system "BGN-PCGN:bel-Cyrl:Latn:1979" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1979
+  language iso-639-2:bel
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Belarusian (1979)
+  url https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/811510/ROMANIZATION_OF_BELARUSIAN.pdf
+  creation_date 1979
+  description {    The BGN/PCGN system for Belarusian (formerly referred to as Byelorussian) was designed for use in
+    romanizing names written in the Belarusian Cyrillic alphabet. The Belarusian alphabet contains three
+    characters not present in the Russian alphabet: і, ў, and ’.
+
+    United States Board on Geographic Names Foreign Names Committee Staff, 1994.
+    Romanization Systems and Roman-Script Spelling Conventions, p. 23.
+  }
+
+  notes {
+   note "The character sequences зг, кг, сг, тс and цг and may be romanized z·h, k·h, s·h, t·s and ts·h in order to differentiate those romanizations from the digraphs zh, kh, sh, ts, and the letter sequence tsh, which are used to render the characters ж, x, ш, ц, and the character sequence тш"
+   note "All apostrophes appearing in romanization are Unicode encoding 2019."
+  }
+}
+
+tests {
+   "Антон" ->  "Anton"
+   "Вілейка" ->  "Vilyeyka"
+   "Брэст" ->  "Brest"
+   "Дубна" ->  "Dubna"
+   "Віцебск" ->  "Vitsyebsk"
+   "Асіповічы" ->  "Asipovichy"
+   "Гродна" ->  "Hrodna"
+   "Брагін" ->  "Brahin"
+   "Добруш" ->  "Dobrush"
+   "Ліда" ->  "Lida"
+   "Гомель" ->  "Homyel’"
+   "Беліца" ->  "Byelitsa"
+   "Ёдкавічы" ->  "Yodkavichy"
+   "Нёман" ->  "Nyoman"
+   "Жлобін" ->  "Zhlobin"
+   "Ружаны" ->  "Ruzhany"
+   "Зоя" ->  "Zoya"
+   "князь" ->  "knyaz’"
+   "Ігнат" ->  "Ihnat"
+   "Мінск" ->  "Minsk"
+   "Йосель" ->  "Yosyel’"
+   "Койданава" ->  "Koydanava"
+   "Крапіўна" ->  "Krapiwna"
+   "Менск" ->  "Myensk"
+   "Лаўна" ->  "Lawna"
+   "Лёсік" ->  "Lyosik"
+   "Купала" ->  "Kupala"
+   "Вілейка" ->  "Vilyeyka"
+   "Міхал" ->  "Mikhal"
+   "Вільня" ->  "Vil’nya"
+   "Лепель" ->  "Lyepyel’"
+   "Магілёў" ->  "Mahilyow"
+   "Няміга" ->  "Nyamiha"
+   "Наваградак" ->  "Navahradak"
+   "Баранавічы" ->  "Baranavichy"
+   "Орша" ->  "Orsha"
+   "Востраў" ->  "Vostraw"
+   "Пінск" ->  "Pinsk"
+   "Дняпро" ->  "Dnyapro"
+   "Рагачоў" ->  "Rahachow"
+   "Сураж" ->  "Surazh"
+   "Смаляны" ->  "Smalyany"
+   "Арэса" ->  "Aresa"
+   "Рось" ->  "Ros’"
+   "Талочын" ->  "Talochyn"
+   "Масты" ->  "Masty"
+   "Уладзімір" ->  "Uladzimir"
+   "Бабруйск" ->  "Babruysk"
+   "Быхаў" ->  "Bykhaw"
+   "Воўпа" ->  "Vowpa"
+   "Іўе" ->  "Iwye"
+   "Фолюш" ->  "Folyush"
+   "фортка" ->  "fortka"
+   "Хатынь" ->  "Khatyn’"
+   "Быхаў" ->  "Bykhaw"
+   "Ганцавічы" ->  "Hantsavichy"
+   "Стоўбцы" ->  "Stowbtsy"
+   "цьмяны" ->  "ts’myany"
+   "мясцовы" ->  "myastsovy"
+   "Астравец" ->  "Astravyets"
+   "Прыпяць" ->  "Prypyats’"
+   "Чэрыкаў" ->  "Cherykaw"
+   "Шчара" ->  "Shchara"
+   "Нарач" ->  "Narach"
+   "Шклоў" ->  "Shklow"
+   "Ашмяны" ->  "Ashmyany"
+   "Ыттык-Кёль" ->  "Yttyk-Kyol’"
+   "Кобрын" ->  "Kobryn"
+   "Солы" ->  "Soly"
+   "Копысь" ->  "Kopys’"
+   "рунь" ->  "run’"
+   "Эйсманты" ->  "Eysmanty"
+   "Крэва" ->  "Kreva"
+   "Юры" ->  "Yury"
+   "уюн" ->  "uyun"
+   "Язэп" ->  "Yazep"
+   "Івянец" ->  "Ivyanyets"
+   "з’езд" ->  "z”yezd"
+   "Вялiкiя Вераб’евічы" ->  "Vyalikiya Vyerab”yevichy"
+   "Дзям’янаўцы" ->  "Dzyam”yanawtsy"
+   "Задвор’е" ->  "Zadvor”ye"
+   "Гезгалы" ->  "Hyez·haly"
+   "Вадасховішча Гезгальскае" ->  "Vadaskhovishcha Hyez·hal’skaye"
+}
+
+stage main {
+
+  # RULES
+  parallel {
+    sub "\u0417\u0413" "Z·H"
+    sub "\u0437\u0433" "z·h"
+    sub "\u041A\u0413" "K·H"
+    sub "\u043A\u0433" "k·h"
+    sub "\u0421\u0413" "S·H"
+    sub "\u0441\u0433" "s·h"
+    sub "\u0422\u0421" "T·S"
+    sub "\u0442\u0441" "t·s"
+    sub "\u0426\u0413" "TS·H"
+    sub "\u0446\u0433" "ts·h"
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "\u00B4" "”"
+    sub "\u02BC" "”"
+    sub "\u2019" "”"
+
+    sub "\u0410" "A"
+    sub "\u0411" "B"
+    sub "\u0412" "V"
+    sub "\u0413" "H"
+    sub "\u0414" "D"
+    sub "\u0415" "Ye"
+    sub "\u0401" "Yo"
+    sub "\u0416" "Zh"
+    sub "\u0417" "Z"
+    sub "\u0406" "I"
+    sub "\u0419" "Y"
+    sub "\u041A" "K"
+    sub "\u041B" "L"
+    sub "\u041C" "M"
+    sub "\u041D" "N"
+    sub "\u041E" "O"
+    sub "\u041F" "P"
+    sub "\u0420" "R"
+    sub "\u0421" "S"
+    sub "\u0422" "T"
+    sub "\u0423" "U"
+    sub "\\U040E" "W"
+    sub "\u0424" "F"
+    sub "\u0425" "Kh"
+    sub "\u0426" "Ts"
+    sub "\u0427" "Ch"
+    sub "\u0428" "Sh"
+    sub "\u042B" "Y"
+    sub "\u042D" "E"
+    sub "\u042E" "Yu"
+    sub "\u042F" "Ya"
+    sub "\u0490" "G"
+
+    sub "\u0430" "a"
+    sub "\u0431" "b"
+    sub "\u0432" "v"
+    sub "\u0433" "h"
+    sub "\u0434" "d"
+    sub "\u0435" "ye"
+    sub "\u0451" "yo"
+    sub "\u0436" "zh"
+    sub "\u0437" "z"
+    sub "\u0456" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "k"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub "\u043E" "o"
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u045E" "w"
+    sub "\u0444" "f"
+    sub "\u0445" "kh"
+    sub "\u0446" "ts"
+    sub "\u0447" "ch"
+    sub "\u0448" "sh"
+    sub "\u044B" "y"
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+    sub "\u0491" "g"
+  }
+
+  # POSTRULES
+  sub "\u042C" "’"
+  sub "\u044C" "’"
+  # Per documentation those rules are optional
+}
+}