interscript-maps 2.4.2 → 2.5.0

data/maps/un-asm-Beng-Latn-1972.isc

@@ -0,0 +1,347 @@
+system "UN:asm-Beng:Latn:1972" {
+
+metadata {
+  authority_id un
+  id 1972
+  language iso-639-2:asm
+  source_script Beng
+  destination_script Latn
+  name Romanization of Assamese -- UNGEGN 4.0
+  url https://www.eki.ee/wgrs/rom1_as.htm
+  creation_date 1972
+  confirmation_date 2016
+  description {    The United Nations recommended system was approved in 1972 (II/11) and amended in 1977 (III/12),
+    based on a report prepared by D. N. Sharma. The tables and their corrections were published in
+    volume II of the conference reports.
+
+    There is no evidence of the use of the system either in India or in international cartographic products.
+
+    Assamese (Asamīyā) uses an alphasyllabic script whereby each character represents a syllable rather
+    than one sound. Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially)
+    and in an abbreviated form, to denote vowels after consonants. The romanization table is unambiguous but the user
+    would have to recognize many ligatures not given in the original table. The system is mostly reversible but there
+    exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters) and consonants
+    (ligatures vs. character sequences).
+
+    References
+
+    Second United Nations Conference on the Standardization of Geographical Names.
+    London, 10–31 May 1972. Vol. II. Technical papers. United Nations. New York 1974, pp. 141–142.
+
+    Third United Nations Conference on the Standardization of Geographical Names. Athens,
+    17 August – 7 September 1977. Vol. II, Technical papers, pp. 393 etc.
+  }
+
+  notes {
+     note "       ু Exceptions: গু gu; রু ru; শু shu; হু hu; ন্তু ntu; স্তু stu."
+     note "       ূ Exceptions: রূ rū."
+     note "       ৃ Exceptions: হৃ hṛ."
+     note "       ্‌  Pronunciation without a vowel; special form: ৎ t."
+     note "       Dotted variants of the characters: ড় ṙa; ঢ় ṙha; য় ya."
+  }
+}
+
+tests {
+   "অসমীয়া কবিতা" ->  "asamīyā kabitā"
+   "কবিৰ আজি জন্মদিন" ->  "kabira āji janmadina"
+   "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড" ->  "beruṭata emāhara pāchhate punara bhayaṁkara agnikāṇḍa"
+   "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ" ->  "bhaṅāra biruddhe āvedana dākhila kaṁganāra"
+   "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি" ->  "āpuni paṙhi bhāla pāba parā bātari"
+   "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক" ->  "shrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
+   "কেনে আছে প্ৰাক্তন" ->  "kene āchhe prāktana"
+   "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ" ->  "kamumbāira meyarara dehata kobhiḍa pajiṭibha"
+   "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা" ->  "ṭuiṭāraj̱oge khoda sadarī kare ei kathā"
+   "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়" ->  "lakhimapura jilāra nārāyaṇapurara barapathārata āji prashānti dhāma nāmere ekhana bṛddhāshramara shubhārambha karā haya"
+
+  # Note: UN card expects this to start with an uppercase letter, but that would break the other tests
+   "অসম" ->  "asama"
+   "দিছপুৰ" ->  "dichhapura"
+}
+
+aliases {
+  beng_chars_1 = any("\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u09cd")
+}
+
+stage main {
+
+  # RULES
+    sub {
+    from "ক"
+    to "k"
+    after beng_chars_1
+  }
+    sub {
+    from "খ"
+    to "kh"
+    after beng_chars_1
+  }
+    sub {
+    from "গ"
+    to "g"
+    after beng_chars_1
+  }
+    sub {
+    from "ঘ"
+    to "gh"
+    after beng_chars_1
+  }
+    sub {
+    from "ঙ"
+    to "ṅ"
+    after beng_chars_1
+  }
+    sub {
+    from "চ"
+    to "ch"
+    after beng_chars_1
+  }
+    sub {
+    from "ছ"
+    to "chh"
+    after beng_chars_1
+  }
+    sub {
+    from "জ"
+    to "j"
+    after beng_chars_1
+  }
+    sub {
+    from "ঝ"
+    to "jh"
+    after beng_chars_1
+  }
+    sub {
+    from "ঞ"
+    to "ñ"
+    after beng_chars_1
+  }
+    sub {
+    from "ট"
+    to "ṭ"
+    after beng_chars_1
+  }
+    sub {
+    from "ঠ"
+    to "ṭh"
+    after beng_chars_1
+  }
+    sub {
+    from "ড"
+    to "ḍ"
+    after beng_chars_1
+  }
+    sub {
+    from "ঢ"
+    to "ḍh"
+    after beng_chars_1
+  }
+    sub {
+    from "ণ"
+    to "ṇ"
+    after beng_chars_1
+  }
+    sub {
+    from "ত"
+    to "t"
+    after beng_chars_1
+  }
+    sub {
+    from "থ"
+    to "th"
+    after beng_chars_1
+  }
+    sub {
+    from "দ"
+    to "d"
+    after beng_chars_1
+  }
+    sub {
+    from "ধ"
+    to "dh"
+    after beng_chars_1
+  }
+    sub {
+    from "ন"
+    to "n"
+    after beng_chars_1
+  }
+    sub {
+    from "প"
+    to "p"
+    after beng_chars_1
+  }
+    sub {
+    from "ফ"
+    to "ph"
+    after beng_chars_1
+  }
+    sub {
+    from "ব"
+    to "b"
+    after beng_chars_1
+  }
+    sub {
+    from "ভ"
+    to "bh"
+    after beng_chars_1
+  }
+    sub {
+    from "ম"
+    to "m"
+    after beng_chars_1
+  }
+    sub {
+    from "য"
+    to "j̱"
+    after beng_chars_1
+  }
+    sub {
+    from "ৰ"
+    to "r"
+    after beng_chars_1
+  }
+    sub {
+    from "ল"
+    to "l"
+    after beng_chars_1
+  }
+    sub {
+    from "ৱ"
+    to "v"
+    after beng_chars_1
+  }
+    sub {
+    from "শ"
+    to "sh"
+    after beng_chars_1
+  }
+    sub {
+    from "ষ"
+    to "ṣh"
+    after beng_chars_1
+  }
+    sub {
+    from "স"
+    to "s"
+    after beng_chars_1
+  }
+    sub {
+    from "হ"
+    to "h"
+    after beng_chars_1
+  }
+    sub {
+    from "ড়"
+    to "ṙ"
+    after beng_chars_1
+  }
+    sub {
+    from "ঢ়"
+    to "ṙh"
+    after beng_chars_1
+  }
+    sub {
+    from "য়"
+    to "y"
+    after beng_chars_1
+  }
+    sub {
+    from "ড়"
+    to "ṙ"
+    after beng_chars_1
+  }
+    sub {
+    from "ঢ়"
+    to "ṙh"
+    after beng_chars_1
+  }
+    sub {
+    from "য়"
+    to "y"
+    after beng_chars_1
+  }
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Independent vowel characters
+    sub "অ" "a"
+    sub "আ" "ā"
+    sub "ই" "i"
+    sub "ঈ" "ī"
+    sub "উ" "u"
+    sub "ঊ" "ū"
+    sub "ঋ" "ṛ"
+    sub "এ" "e"
+    sub "ঐ" "ai"
+    sub "ও" "o"
+    sub "ঔ" "au"
+
+    # II. Abbreviated vowel characters
+    sub "\u09be" "ā"
+    sub "\u09bf" "i"
+    sub "\u09c0" "ī"
+    sub "\u09c1" "u"
+    sub "\u09c2" "ū"
+    sub "\u09c3" "ṛ"
+    sub "\u09c7" "e"
+    sub "\u09c8" "ai"
+    sub "\u09cb" "o"
+    sub "\u09cc" "au"
+
+    # III. Other symbols
+    sub "\u0982" "ṁ"
+    sub "\u0981" "m̐"
+    sub "\u0983" "ḥ"
+    sub "\u09cd" ""
+
+    # IV. Consonant characters
+    sub "ক" "ka"
+    sub "খ" "kha"
+    sub "গ" "ga"
+    sub "ঘ" "gha"
+    sub "ঙ" "ṅa"
+    sub "চ" "cha"
+    sub "ছ" "chha"
+    sub "জ" "ja"
+    sub "ঝ" "jha"
+    sub "ঞ" "ña"
+    sub "ট" "ṭa"
+    sub "ঠ" "ṭha"
+    sub "ড" "ḍa"
+    sub "ঢ" "ḍha"
+    sub "ণ" "ṇa"
+    sub "ত" "ta"
+    sub "থ" "tha"
+    sub "দ" "da"
+    sub "ধ" "dha"
+    sub "ন" "na"
+    sub "প" "pa"
+    sub "ফ" "pha"
+    sub "ব" "ba"
+    sub "ভ" "bha"
+    sub "ম" "ma"
+    sub "য" "j̱a"
+    sub "ৰ" "ra"
+    sub "ল" "la"
+    sub "ৱ" "va"
+    sub "শ" "sha"
+    sub "ষ" "ṣha"
+    sub "স" "sa"
+    sub "হ" "ha"
+    sub "ৎ" "t"
+
+    # Note V Dotted variants
+    sub "ড়" "ṙa"
+    sub "ঢ়" "ṙha"
+    sub "য়" "ya"
+    sub "য়" "ya"
+    sub "ড়" "ṙa"
+    sub "ঢ়" "ya"
+  }
+
+  compose
+}
+
+}

data/maps/un-bel-Cyrl-Latn-2007.isc

@@ -0,0 +1,81 @@
+system "UN:bel-Cyrl:Latn:2007" {
+
+metadata {
+  authority_id un
+  id 2007
+  language iso-639-2:bel
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Belarusian geographic names (2007)
+  url https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/9th-uncsgn-docs/crp/9th_UNCSGN_e-conf-98-crp-21.pdf
+  creation_date 2007
+  description {    RESOLUTION OF THE STATE COMMITTEE
+    ON PROPERTY OF THE REPUBLIC OF BELARUS June 11, 2007 No. 38
+
+    8/16668 (06/18/2007) On amendments and additions to the Instructions
+    for the transliteration of geographical names of the
+    Republic of Belarus in letters of the Latin alphabet
+
+    Based on the Regulation on the State Property Committee of the Republic of Belarus,
+    approved by the Decree of the Council of Ministers of the Republic of Belarus dated July 29, 2006
+    No. 958 "Issues of the State Committee on Property of the Republic of Belarus"
+  }
+}
+
+tests {
+  # the same as "by-bel-cyrl-Latn-2007"
+   "Аршанскi" ->  "Aršanski"
+   "Бешанковічы" ->  "Biešankovičy"
+   "Віцебск" ->  "Viciebsk"
+   "Гомель" ->  "Homieĺ"
+   "Гаўя" ->  "Haŭja"
+   "Добруш" ->  "Dobruš"
+   "Ельск" ->  "Jeĺsk"
+   "Бабаедава" ->  "Babajedava"
+   "Венцавічы" ->  "Viencavičy"
+   "Ёды" ->  "Jody"
+   "Вераб'ёвічы" ->  "Vierabjovičy"
+   "Мёры" ->  "Miory"
+   "Зэльва" ->  "Zeĺva"
+   "Iванава" ->  "Ivanava"
+   "Iўе" ->  "Iŭje"
+   "Лагойск" ->  "Lahojsk"
+   "Круглае" ->  "Kruhlaje"
+   "Лошыца" ->  "Lošyca"
+   "Любань" ->  "Liubań"
+   "Магілёў" ->  "Mahilioŭ"
+   "Нясвіж" ->  "Niasviž"
+   "Орша" ->  "Orša"
+   "Паставы" ->  "Pastavy"
+   "Рагачоў" ->  "Rahačoŭ"
+   "Смаргонь" ->  "Smarhoń"
+   "Талачын" ->  "Talačyn"
+   "Узда" ->  "Uzda"
+   "Шаркаўшчына" ->  "Šarkaŭščyna"
+   "Фаніпаль" ->  "Fanipaĺ"
+   "Хоцімск" ->  "Chocimsk"
+   "Цёмны Лес" ->  "Ciomny Lies"
+   "Чавусы" ->  "Čavusy"
+   "Шумілiна" ->  "Šumilina"
+   "Чыгірынка" ->  "Čyhirynka"
+   "Чэрвень" ->  "Červień"
+   "Друць" ->  "Druć"
+   "Чачэрск" ->  "Čačersk"
+   "Юхнаўка" ->  "Juchnaŭka"
+   "Гаюціна" ->  "Hajucina"
+   "Цюрлi" ->  "Ciurli"
+   "Любонічы" ->  "Liuboničy"
+   "Ямнае" ->  "Jamnaje"
+   "Баяры" ->  "Bajary"
+   "Валяр'яны" ->  "Valiarjany"
+   "Вязынка" ->  "Viazynka"
+}
+
+dependency "by-bel-Cyrl-Latn-2007" as cyrllatn
+
+stage main {
+
+  run  map.cyrllatn.stage.main
+
+}
+}