interscript-maps 2.4.2 → 2.5.0

data/maps/bgnpcgn-tat-Cyrl-Latn-2007.isc

@@ -0,0 +1,270 @@
+system "BGN-PCGN:tat-Cyrl:Latn:2007" {
+
+metadata {
+  authority_id bgnpcgn
+  id 2007
+  language iso-639-2:tat
+  source_script Cyrl
+  destination_script Latn
+  name Table of Correspondences for Tatar (Cyrillic-Roman) (2007 Agreement)
+  url https://geonames.nga.mil/gns/html/Romanization/TABLE%20OF%20CORRESPONDENCES%20FOR%20TATAR.pdf
+  creation_date 2007
+  confirmation_date 2017-11
+  description {    Tatar is an official language within Respublika Tatarstan, one 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 alphabet portrayed in the above table is referred to as yaꞑalif-2.\n      A set of simpler characters is also encountered; this is known as zamanalif.\n      In this latter set, the alternative characters ä, ñ and ö are used for letters\n      2, 17 and 19 respectively where the user has difficulty reproducing ə, ꞑ, and ө.\n      Please note that all three alternatives must be used as a set, and the letters should not be intermingled."
+    note "Used only in borrowed words."
+    note "The first option is used in words with back vowels, the second in words with front vowels (though this does not apply to borrowed words)."
+    note "yı/ye is used after a vowel (except и, ю), ъ and ь, also word-initially."
+    note "w is used after a vowel."
+    note "After ğ or q, ый is represented i"
+    note "Э is represented ’ after a vowel in words of Arabic origin."
+    note "Ю and Я are represented ü and a/ä respectively after и."
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the unmodified letters\n      of the basic Roman script is:\n          Ə (U+018F) ə (U+0259)\n          Ğ (U+011E) ğ (U+011F)\n          İ (U+0130) ı (U+0131)\n          Ü (U+00DC) ü (U+00FC)\n          Ꞑ (U+A790) ꞑ (U+A791)\n          Ɵ (U+019F) ɵ (U+0275)\n          Ç (U+00C7) ç (U+00E7)\n          Ş (U+015E) ş (U+015F)\n          Ä (U+00C4) ä (U+00E4)\n          ’ (U+2019)"
+    note "      The Roman-script columns show only lowercase forms but, when applying the table, uppercase and lowercase\n      Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+   "Гыйльмиев" ->  "Ğil’miew" #  # note[6] in the note it's Ğilmiev which incorrect according to the rules
+  # https://en.wikipedia.org/wiki/Tatar_alphabet
+   "баеды" ->  "bayıdı" # note[4]
+   "кардәш" ->  "qardəş"
+   "калынлык һәм аеру билгесе" ->  "qalınlıq həm ayıru bilgese" # note[4]
+   "Барлык кешеләр дә азат һәм үз абруйлары һәм хокуклары ягыннан тиң булып туалар.\nАларга акыл һәм вөҗдан бирелгән һәм бер-берсенә карата туганнарча мөнасәбәттә булырга тиешләр." ->  "Barlıq keşelər də azat həm üz abruyları həm xoquqları yağınnan tiꞑ bulıp tualar.\nAlarğa aqıl həm wocdan birelgən həm ber-bersenə qarata tuğannarça monasəbəttə bulırğa tieşlər."
+  # https://www.azatliq.org/a/30820571.html
+   "Әлдермештән Әлмәндәр" ->  "Əldermeştən Əlməndər"
+   "Әссәламү галәйкүм" ->  "Əssəlamü ğaləyküm"
+   "Танымаган кешегә" ->  "Tanımağan keşegə" # note[3]
+   "Иң әүвәл кул бирешеп күрешик" ->  "İꞑ əwwəl qul bireşep küreşiq" # note[5]
+   "Ялгышмыйсың" ->  "Yalğışmıysıꞑ"
+   "Нәкъ үзе" ->  "Nəq üze"
+   "Кирәгеннән артыгын" ->  "Kirəgennən artığın" # note[3]
+   "мәңгелеккә килмәгән" ->  "məꞑgeleqkə kilməgən"
+   "кулыңны куй" ->  "qulıꞑnı quy"
+   "Өммия" ->  "Ommiä" # note[8]
+   "Җиһангир" ->  "Cihangir" # note[3]
+}
+
+stage main {
+
+  # RULES
+  # note[3] http://www.hintfox.com/article/sistema-glasnih-zvykov-na-tatarskom-i-anglijskom-jazikah.html
+  # back vowels: у, а, ы, о,
+  # front vowels: е, ә, и, ө, ү, э
+  sub {
+    from "Г"
+    to "G"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "г"
+    to "g"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "К"
+    to "K"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "к"
+    to "k"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "Ю"
+    to "Yü"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "ю"
+    to "yü"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "Я"
+    to "Yä"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+  sub {
+    from "я"
+    to "yä"
+    after any("ЕеƏәИиӨөҮүЭэ")
+  }
+
+  # note[4]
+  sub {
+    from "\u0415"
+    to "Yı"
+    before any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
+  }
+  sub {
+    from "\u0435"
+    to "yı"
+    before any("АаЕеƏәОоӨөҮүУуЫыЭэЯяЪъЬь")
+  }
+
+  # note[5]
+  sub {
+    from "\u0423"
+    to "W"
+    before any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  }
+  sub {
+    from "\u0443"
+    to "w"
+    before any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  }
+  sub {
+    from "\u04AE"
+    to "W"
+    before any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  }
+  sub {
+    from "\u04AF"
+    to "w"
+    before any("АаЕеƏәИиОоӨөҮүУуЫыЭэЮюЯяЪъЬь")
+  }
+
+  # note[6]
+  sub {
+    from "ый"
+    to "i"
+    before any("Гг")
+  }
+
+  # note[8]
+  sub {
+    from "\u042E"
+    to "Ü"
+    before any("Ии")
+  }
+  sub {
+    from "\u044E"
+    to "ü"
+    before any("Ии")
+  }
+  sub {
+    from "\u042F"
+    to "Ä"
+    before any("Ии")
+  }
+  sub {
+    from "\u044F"
+    to "ä"
+    before any("Ии")
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub {
+    from "Ә"
+    to any("ƏÄ")
+  }
+    sub "Б" "B"
+    sub {
+    from "В"
+    to any("WV")
+  }
+    sub "Г" "Ğ"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ж" "J"
+    sub "Җ" "C"
+    sub "З" "Z"
+    sub "И" "İ"
+    sub "Й" "Y"
+    sub "К" "Q"
+    sub "Л" "L"
+    sub "М" "M"
+    sub "Н" "N"
+    sub {
+    from "Ң"
+    to any("ꞐÑ")
+  }
+    sub "О" "O"
+    sub {
+    from "Ө"
+    to any("OÖ")
+  }
+    sub "П" "P"
+    sub "Р" "R"
+    sub "С" "S"
+    sub "Т" "T"
+    sub "У" "U"
+    sub "Ү" "Ü"
+    sub "Ф" "F"
+    sub "Х" "Х"
+    sub "Һ" "H"
+    sub "Ц" "Ts"
+    sub "Ч" "Ç"
+    sub "Ш" "Ş"
+    sub "Щ" "ŞÇ"
+    sub "Ъ" ""
+    sub "Ы" "I"
+    sub "Ь" "’"
+    sub "Э" "E"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+
+    sub "\u0430" "a"
+    sub {
+    from "\u04D9"
+    to any("əä")
+  }
+    sub "\u0431" "b"
+    sub {
+    from "\u0432"
+    to any("wv")
+  }
+    sub "\u0433" "ğ"
+    sub "\u0434" "d"
+    sub "\u0435" "e"
+    sub "\u0436" "j"
+    sub "\u0497" "c"
+    sub "\u0437" "z"
+    sub "\u0438" "i"
+    sub "\u0439" "y"
+    sub "\u043A" "q"
+    sub "\u043B" "l"
+    sub "\u043C" "m"
+    sub "\u043D" "n"
+    sub {
+    from "\u04A3"
+    to any("ꞑñ")
+  }
+    sub "\u043E" "o"
+    sub {
+    from "\u04E9"
+    to any("oö")
+  }
+    sub "\u043F" "p"
+    sub "\u0440" "r"
+    sub "\u0441" "s"
+    sub "\u0442" "t"
+    sub "\u0443" "u"
+    sub "\u04AF" "ü"
+    sub "\u0444" "f"
+    sub "\u0445" "x"
+    sub "\u04BB" "h"
+    sub "\u0446" "ts"
+    sub "\u0447" "ç"
+    sub "\u0448" "ş"
+    sub "\u0449" "şç"
+    sub "ъ" ""
+    sub "\u044B" "ı"
+    sub "ь" "’"
+    sub "\u044D" "e"
+    sub "\u044E" "yu"
+    sub "\u044F" "ya"
+  }
+
+}
+}

data/maps/bgnpcgn-tgk-Cyrl-Latn-1994.isc

@@ -0,0 +1,199 @@
+system "BGN-PCGN:tgk-Cyrl:Latn:1994" {
+
+metadata {
+  authority_id bgnpcgn
+  id 1994
+  language iso-639-2:tgk
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Tajik (1994)
+  url https://geonames.nga.mil/gns/html/Romanization/ROMANIZATION%20OF%20TAJIK.pdf
+  creation_date 1994
+  confirmation_date 2017-11
+  description {    The BGN/PCGN system for Tajik was designed for use in romanizing names written in the Tajik Cyrillic alphabet.
+    The Tajik Cyrillic alphabet contains six characters not present in the Russian alphabet: ғ, ӣ, қ, ӯ, ҳ and ҷ. An
+    orthographic reform of the Tajik Cyrillic alphabet was implemented under the auspices of the Academy of Sciences of
+    Tajikistan. This reform was promulgated in a decree of 3 September 1998 by the government of the Republic of
+    Tajikistan. The reform abolished the characters ц, щ, ь and ы (see notes 2 through 5).
+  }
+
+  notes {
+    note "      The character sequences гҳ , зҳ , кҳ , and сҳ may be romanized g·h, z·h, k·h, and s·h in order\n      to differentiate those romanizations from the digraphs gh, zh, kh, and sh which are used to\n      render the characters ғ, ж, x, and ш."
+    note "      The obsolete character ц, abolished in 1998, should be romanized s (before a vowel and/or\n      after a consonant within a word) or ts intervocalically."
+    note "The obsolete character щ, replaced by ш in 1998, should be romanized sh."
+    note "The obsolete character ь, abolished in 1998, should not be romanized."
+    note "The obsolete character ы, replaced by и in 1998, should be romanized i."
+    note "Unicode values are shown with the uppercase Cyrillic character first, followed by the lowercase character."
+    note "      An inventory of letter-diacritic combinations, with their Unicode encoding, in addition to the\n      unmodified letters of the basic Roman script is:\n        All apostrophes appearing in romanization are U+2019\n          Í (U+00CD) í (U+00ED)\n          Ŭ (U+016C) ŭ (U+016D)\n          Ė (U+0116) ė (U+0117)"
+    note "      The Romanization column shows only lowercase forms but, when romanizing, uppercase and\n      lowercase Roman letters as appropriate should be used."
+  }
+}
+
+tests {
+  # https://ru.wikipedia.org/wiki/Таджикская_письменность#Образцы_записи
+   "Тамоми одамон озод ба дунё меоянд ва аз лиҳози манзилату ҳуқуқ бо ҳам баробаранд.\nҲама соҳиби ақлу виҷдонанд, бояд нисбат ба якдигар бародарвор муносабат намоянд." ->  "Tamomi odamon ozod ba dunyo meoyand va az lihozi manzilatu huquq bo ham barobarand.\nHama sohibi aqlu vijdonand, boyad nisbat ba yakdigar barodarvor munosabat namoyand."
+   "Баниодам аъзои як пайкаранд, ки дар офариниш зи як гавҳаранд. Чу узве ба дард оварад рӯзгор, дигар узвҳоро намонад қарор." ->  "Baniodam a’zoi yak paykarand, ki dar ofarinish zi yak gavharand. Chu uzve ba dard ovarad rŭzgor, digar uzvhoro namonad qaror."
+   "Саъдӣ" ->  "Sa’dí"
+   "Мурда будам, зинда шудам; гиря будам, xанда шудам. Давлати ишқ омаду ман давлати поянда шудам." ->  "Murda budam, zinda shudam; girya budam, xanda shudam. Davlati ishq omadu man davlati poyanda shudam."
+   "Мавлавӣ" ->  "Mavlaví"
+   "санг" ->  "sang"
+   "барг" ->  "barg"
+   "номвар" ->  "nomvar"
+   "Бағдод" ->  "Baghdod"
+   "ғор" ->  "ghor"
+   "модар" ->  "modar"
+   "меравам" ->  "meravam"
+   "дарё" ->  "daryo"
+   "осиёб" ->  "osiyob"
+   "жола" ->  "zhola"
+   "каждум" ->  "kazhdum"
+   "баъз" ->  "ba’z"
+   "назар" ->  "nazar"
+   "заҳоб" ->  "zahob"
+   "ихтиёр" ->  "ikhtiyor"
+   "зебоӣ" ->  "zeboí"
+   "май" ->  "may"
+   "кадом" ->  "kadom"
+   "қадам" ->  "qadam"
+   "лола" ->  "lola"
+   "мурдагӣ" ->  "murdagí"
+   "нон" ->  "non"
+   "орзу" ->  "orzu"
+   "панҷ" ->  "panj"
+   "ранг" ->  "rang"
+   "сар" ->  "sar"
+   "субҳ" ->  "subh"
+   "сурайё" ->  "surayyo"
+   "тоҷик" ->  "tojik"
+   "талаб" ->  "talab"
+   "дуд" ->  "dud"
+   "хӯрдан" ->  "khŭrdan"
+   "фурӯғ" ->  "furŭgh"
+   "хондан" ->  "khondan"
+   "ҳофиз" ->  "hofiz"
+   "чӣ" ->  "chí"
+   "ҷанг" ->  "jang"
+   "шаб" ->  "shab"
+   "таъриф" ->  "ta’rif"
+   "эй" ->  "ėy"
+   "июн" ->  "iyun"
+   "ягонагӣ" ->  "yagonagí"
+   "РАМЗҲО" ->  "RAMZ·HO"
+
+  # UN card tests
+   "Тоҷикистон" ->  "Tojikiston"
+   "Душанбе" ->  "Dushanbe"
+}
+
+stage main {
+
+  # RULES
+  # note[1]
+  sub {
+    from "\u04B3"
+    to "·h"
+    before any("ГгЗзКкСс")
+  }
+  sub {
+    from "\u04B2"
+    to "·H"
+    before any("ГгЗзКкСс")
+  }
+  # note[2]
+  sub {
+    from "\u0426"
+    to "S"
+    after any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
+  }
+  sub {
+    from "\u0446"
+    to "s"
+    after any("АаЕеЁёИиОоУуЫыЭэЮюЯя")
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "А" "A"
+    sub "Б" "B"
+    sub "В" "V"
+    sub "Г" "G"
+    sub "Ғ" "Gh"
+    sub "Д" "D"
+    sub "Е" "E"
+    sub "Ё" "Yo"
+    sub "Ж" "Zh"
+    sub "З" "Z"
+    sub "И" "I"
+    sub "Ӣ" "Í"
+    sub "Й" "Y"
+    sub "К" "K"
+    sub "Қ" "Q"
+    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 "Ӯ" "Ŭ"
+    sub "Ф" "F"
+    sub "Х" "Kh"
+    sub "Ҳ" "H"
+    sub "Ч" "Ch"
+    sub "Ҷ" "J"
+    sub "Ц" "Ts"
+    sub "Ш" "Sh"
+    sub "Щ" "Sh"
+    sub "Ъ" "’"
+    sub "Ы" "I"
+    sub "Ь" ""
+    sub "Э" "Ė"
+    sub "Ю" "Yu"
+    sub "Я" "Ya"
+
+    sub "а" "a"
+    sub "б" "b"
+    sub "в" "v"
+    sub "г" "g"
+    sub "ғ" "gh"
+    sub "д" "d"
+    sub "е" "e"
+    sub "ё" "yo"
+    sub "ж" "zh"
+    sub "з" "z"
+    sub "и" "i"
+    sub "ӣ" "í"
+    sub "й" "y"
+    sub "к" "k"
+    sub "қ" "q"
+    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 "ӯ" "ŭ"
+    sub "ф" "f"
+    sub "х" "kh"
+    sub "ҳ" "h"
+    sub "ч" "ch"
+    sub "ҷ" "j"
+    sub "ц" "ts"
+    sub "ш" "sh"
+    sub "щ" "sh"
+    sub "ъ" "’"
+    sub "ы" "i"
+    sub "ь" ""
+    sub "э" "ė"
+    sub "ю" "yu"
+    sub "я" "ya"
+  }
+
+}
+}