interscript-maps 2.2.0 → 2.2.1

data/maps/un-ara-Arab-Latn-2017.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  name: Romanization of Arabic -- UNGEGN (2017)
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 2017
   confirmation_date: 2018-06
@@ -141,20 +141,20 @@ stage {
     # (B) Marks doubling of the consonant.
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "at t" # الت
-    sub boundary + "\u0627\u0644\u062b", "ath th" # الث
-    sub boundary + "\u0627\u0644\u062f", "ad d" # الد
-    sub boundary + "\u0627\u0644\u0630", "adh dh" # الذ
-    sub boundary + "\u0627\u0644\u0631", "ar r" # الر
-    sub boundary + "\u0627\u0644\u0632", "az z" # الز
-    sub boundary + "\u0627\u0644\u0633", "as s" # الس
-    sub boundary + "\u0627\u0644\u0634", "ash sh" # الش
-    sub boundary + "\u0627\u0644\u0635", "as̱ s̱" # الص
-    sub boundary + "\u0627\u0644\u0636", "aḏ ḏ" # الض
-    sub boundary + "\u0627\u0644\u0637", "aṯ ṯ" # الط
-    sub boundary + "\u0627\u0644\u0638", "ad͟h d͟h" # الظ
-    sub boundary + "\u0627\u0644\u0644", "al l" # الل
-    sub boundary + "\u0627\u0644\u0646", "an n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "at t" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "ath th" # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "ad d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "adh dh" # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "ar r" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "az z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), "as s" # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "ash sh" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "as̱ s̱" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḏ ḏ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aṯ ṯ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "ad͟h d͟h" # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "al l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "an n" # الن
 
     # TODO: shorten this fragment
     # ta' marboota

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Assamese Romanization, Version 4.0
+  name: Romanization of Assamese -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_as.htm
   creation_date: 1972
   confirmation_date: 2016

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

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:bel
   source_script: Cyrl
   destination_script: Latn
-  name: National System of Geographic Names Transmission into Roman Alphabet in Belarus
+  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: |
@@ -16,7 +16,7 @@ metadata {
     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 Belarusdated July 29, 2006
+    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"
 }
 

data/maps/un-ben-Beng-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ben
   source_script: Beng
   destination_script: Latn
-  name: Bengali Romanization, Version 4.0
+  name: Romanization of Bengali -- UNGEGN 4.0
   url: http://www.eki.ee/wgrs/rom1_bn.htm
   creation_date: 2016
   description: |

data/maps/un-bul-Cyrl-Latn-1977.imp

@@ -0,0 +1,197 @@
+metadata {
+  authority_id: un
+  id: 1977
+  language: iso-639-2:bul
+  source_script: Cyrl
+  destination_script: Latn
+  name: Romanization of Bulgarian geographical names (1977)
+  url: https://www.eki.ee/wgrs/res/res_3_10.htm
+  creation_date: 1977
+  description: |
+    The System of Transliteration and Transcription of Bulgarian Geographical Names into Roman letters,
+    as shown in the annex below, be adopted as the international system for the romanization of Bulgarian geographical names.
+}
+
+tests {
+  test "нунатак Абрит", "nunatak Abrit"
+  test "връх Академия", "vrǎh Akademiya"
+  test "връх Ами Буе", "vrǎh Ami Bue"
+  test "нос Айтос", "nos Ajtos"
+  test "залив Баба Тонка", "zaliv Baba Tonka"
+  test "Балабански камък", "Balabanski kamǎk"
+  test "Бедечки поток", "Bedečki potok"
+  test "нос Бяга БЯГА", "nos Byaga BYAGA"
+  test "остров Качо", "ostrov Kačo" # wiki ostrov Cacho
+  test "Чакъров остров", "Čakǎrov ostrov"
+  test "връх Дъбник", "vrǎh Dǎbnik"
+  test "залив Десислава", "zaliv Desislava"
+  test "ледник Джераси", "lednik Džerasi"
+  test "Джегова скала", "Džegova skala"
+  test "Нунатак Едуард", "Nunatak Eduard"
+  test "Елховска седловина", "Elhovska sedlovina"
+  test "ледник Етър", "lednik Etǎr"
+  test "нунатак Филип Тотю", "nunatak Filip Totyu"
+  test "ледник Габаре", "lednik Gabare"
+  test "риф Гергини", "rif Gergini"
+  test "Гяуров връх", "Gyaurov vrǎh"
+  test "Гуцалски рид", "Gucalski rid" # not found
+  test "Хараламбиев остров", "Haralambiev ostrov"
+  test "връх Ичера", "vrǎh Ičera"
+  test "полуостров Йоан Павел II", "poluostrov Joan Pavel II"
+  test "нос Иван Александър", "nos Ivan Aleksandǎr"
+  test "нос Иречек", "nos Ireček"
+  test "нос Кърджали", "nos Kǎrdžali"
+  test "седловина Кърнаре", "sedlovina Kǎrnare"
+  test "нунатак Керсеблепт", "nunatak Kerseblept"
+  test "Кондофрейски възвишения", "Kondofrejski vǎzvišeniya"
+  test "Костинбродски проход", "Kostinbrodski prohod"
+  test "връх Кожух", "vrǎh Kožuh"
+  test "Кукерски нунатаци", "Kukerski nunataci"
+  test "залив Лазурен бряг", "zaliv Lazuren bryag"
+  test "връх Лудогорие", "vrǎh Ludogorie"
+  test "Лютибродски скали", "Lyutibrodski skali"
+  test "Масларов нунатак", "Maslarov nunatak"
+  test "Михневски връх", "Mihnevski vrǎh"
+  test "рид Митино", "rid Mitino"
+  test "езеро Наяда", "ezero Nayada"
+  test "нос Никюп НИКЮП", "nos Nikyup NIKYUP"
+  test "рид Оборище ОБОРИЩЕ", "rid Oborište OBORIŠTE"
+  test "залив Олуша", "zaliv Oluša"
+  test "Оряховски възвишения", "Oryahovski vǎzvišeniya"
+  test "нунатак Памидово", "nunatak Pamidovo"
+  test "връх Парангалица", "vrǎh Parangalica"
+  test "Първомайски провлак", "Pǎrvomajski provlak"
+  test "ледник Патлейна", "lednik Patlejna"
+  test "полуостров Перник", "poluostrov Pernik"
+  test "връх Петко Войвода", "vrǎh Petko Vojvoda"
+  test "остров Фанагория", "ostrov Fanagoriya"
+  test "нос Плас", "nos Plas"
+  test "Пресиянов рид", "Presiyanov rid"
+  test "връх Принсипе де Астуриас", "vrǎh Prinsipe de Asturias" # wiki: vrǎh Príncipe de Asturias
+  test "нунатак Ръченица", "nunatak Rǎčenica"
+  test "връх Райна Княгиня", "vrǎh Rajna Knyaginya"
+  test "Рид Ръжана", "Rid Rǎžana"
+  test "връх Ригс", "vrǎh Rigs"
+  test "остров Рогулят", "ostrov Rogulyat"
+  test "ледник Сабазий", "lednik Sabazij"
+  test "ледник Съединение", "lednik Sǎedinenie"
+  test "нунатак Сенокос", "nunatak Senokos"
+  test "Сейдолски камък", "Sejdolski kamǎk"
+  test "ледник Щерна", "lednik Šterna"
+  test "връх Шишман", "vrǎh Šišman"
+  test "ледник Сигмен", "lednik Sigmen"
+  test "Седловина Синитово", "Sedlovina Sinitovo"
+  test "Ледник Скаплизо", "Lednik Skaplizo"
+  test "залив Слънчев бряг", "zaliv Slǎnčev bryag"
+  test "остров Соатрис", "ostrov Soatris"
+  test "планина Софийски Университет", "planina Sofijski Universitet"
+  test "ледник Сребърна", "lednik Srebǎrna"
+  test "Средногорски възвишения", "Srednogorski vǎzvišeniya"
+  test "Св. Евтимиев камък", "Sv. Evtimiev kamǎk"
+  test "база Св. Климент Охридски", "baza Sv. Kliment Ohridski"
+  test "връх Стъргел", "vrǎh Stǎrgel"
+  test "нунатак Сторгозия", "nunatak Storgoziya" # nunatak Storgozia according to wiki
+  test "нунатак Сурвакари", "nunatak Survakari"
+  test "ледник Световрачене", "lednik Svetovračene"
+  test "остров Теменуга", "ostrov Temenuga"
+  test "Тракийски възвишения", "Trakijski vǎzvišeniya"
+  test "хълм Цамблак", "hǎlm Camblak"
+  test "ледник Урдовиза", "lednik Urdoviza"
+  test "остров Вълчедръм", "ostrov Vǎlčedrǎm"
+  test "острови Вардим", "ostrovi Vardim"
+  test "Владигеров проток", "Vladigerov protok"
+  test "ледник Ябланица", "lednik Yablanica"
+  test "залив Ямфорина", "zaliv Yamforina"
+  test "Йовков нос", "Jovkov nos"
+  test "рид Заберново", "rid Zabernovo"
+  test "ледник Збелсурд", "lednik Zbelsurd"
+  test "Жефарович камък", "Žefarovič kamǎk"
+  test "връх Зиези", "vrǎh Ziezi"
+  test "залив Златни пясъци", "zaliv Zlatni pyasǎci"
+  test "ледник Злокучене", "lednik Zlokučene"
+  test "проток Злогош", "protok Zlogoš"
+}
+
+dependency "posix", import: true
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Д", "D"
+    sub "Е", "E"
+    sub "Ж", "Ž"
+    sub "З", "Z"
+    sub "И", "I"
+    sub "Й", "J"
+    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", "H"
+    sub "Ц", "C"
+    sub "Ч", "Č"
+    sub "Ш", "Š"
+    sub "Щ", "Št"
+    sub "Ъ", "Ǎ"
+    sub "Ь", "J"
+    sub "Ю", "Yu"
+    sub "Я", "Ya"
+
+    sub "а", "a"
+    sub "б", "b"
+    sub "в", "v"
+    sub "г", "g"
+    sub "д", "d"
+    sub "е", "e"
+    sub "ж", "ž"
+    sub "з", "z"
+    sub "и", "i"
+    sub "й", "j"
+    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", "h"
+    sub "ц", "c"
+    sub "ч", "č"
+    sub "ш", "š"
+    sub "щ", "št"
+    sub "ъ", "ǎ"
+    sub "ь", "j"
+    sub "ю", "yu"
+    sub "я", "ya"
+
+  }
+
+  # ŠT
+  sub capture(maybe(upper)) + "Št" + capture(upper), ref(1) + "ŠT" + ref(2)
+  sub capture(upper) + "Št" +  capture(maybe(upper)), ref(1) + "ŠT" + ref(2)
+
+  # YU
+  sub capture(maybe(upper)) + "Yu" + capture(upper), ref(1) + "YU" + ref(2)
+  sub capture(upper) + "Yu" +  capture(maybe(upper)), ref(1) + "YU" + ref(2)
+
+  # YA
+  sub capture(maybe(upper)) + "Ya" + capture(upper), ref(1) + "YA" + ref(2)
+  sub capture(upper) + "Ya" +  capture(maybe(upper)), ref(1) + "YA" + ref(2)
+}
+

data/maps/un-ell-Grek-Latn-1987-phonetic.imp

@@ -4,12 +4,16 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: UNGEGN Greek v1.0, Fifth United Nations Conference on the Standardization of Geographical Names. Writing Systems and Guides to Pronunciation Romanization > Conversion of the Greek alphabet into Latin characters. Paper submitted by Greece and Cyprus.
+  name: Romanization of Greek 1.0 (Phonetic transcription)
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |
     UNGEGN Romanization table for Greek: Phonetic transcription
 
+    UNGEGN Greek v1.0, Fifth United Nations Conference on the Standardization of
+    Geographical Names. Writing Systems and Guides to Pronunciation Romanization
+    > Conversion of the Greek alphabet into Latin characters. Paper submitted by
+    Greece and Cyprus.
 
   notes:
     - Also included in ISO 843:1997, Annex B, Column 5, and ELOT 743:1982, column 5.

data/maps/un-ell-Grek-Latn-1987-tl.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: UNGEGN Greek v4.0
+  name: Romanization of Greek -- UNGEGN 4.0 (transliteration)
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |

data/maps/un-ell-Grek-Latn-1987-ts.imp

@@ -1,10 +1,10 @@
 metadata {
   authority_id: un
-  id: 1987-tl
+  id: 1987-ts
   language: iso-639-2:ell
   source_script: Grek
   destination_script: Latn
-  name: UNGEGN Greek v4.0
+  name: Romanization of Greek -- UNGEGN 4.0 (transcription)
   url: http://www.eki.ee/wgrs/rom1_el.htm
   creation_date: 1987
   description: |

data/maps/un-guj-Gujr-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:guj
   source_script: Gujr
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Gujarati Romanization Version 4.0
+  name: Romanization of Gujarati -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_gu.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-hin-Deva-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Hindi Romanization, 1972
+  name: Romanization of Hindi -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_hi.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-kan-Kana-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:kan
   source_script: Kana
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Kannada Romanization, 1972
+  name: Romanization of Kannada -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_kn.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mal-Mlym-Latn-1972.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:mal
   source_script: Mlym
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Malayalam Romanization Version 4.0
+  name: Romanization of Malayalam -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_ml.htm
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mar-Deva-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:hin
   source_script: Deva
   destination_script: Latn
-  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Marathi Romanization, 1972
+  name: Romanization of Marathi -- UNGEGN 4.0
   url: https://www.eki.ee/wgrs/rom1_mr.pdf
   creation_date: 1972
   confirmation_date: 2016

data/maps/un-mkd-Cyrl-Latn-1977.imp

@@ -0,0 +1,119 @@
+metadata {
+  authority_id: id
+  id: 1977
+  language: iso-639-2:mkd
+  source_script: Cyrl
+  destination_script: Latn
+  name: Romanization of Macedonian geographical names (1977)
+  url: https://www.eki.ee/wgrs/v2_2/rom1_mk.htm
+  creation_date: 1977
+  description: |
+    The United Nations recommended system was approved in 1977 (III/11), based on the romanization of the Serbo-Croatian and Macedonian Cyrillic alphabets that had long been employed in official gazetteers and maps of Yugoslavia. The table was published as an annex to the resolution (Third United Nations Conference on the Standardization of Geographical Names. Athens, 17 August - 7 September 1977. Vol. I. Report of the Conference, pp. 29, 31).
+    The system is used in The former Yugoslav Republic of Macedonia (see e.g. Report of The former Yugoslav Republic of Macedonia. Seventh United Nations Conference on the Standardization of Geographical Names. New York, 13-22 January 1998. Document E/CONF.91/CRP.23) and in international cartographic products.
+    The Cyrillic alphabet is used. The romanization table is unambiguous and can be applied automatically. The system is on the whole reversible with the exception of the characters ѓ and ќ. These are romanized as g and k, respectively, before е and и. But also г and к are occasionally used before е and и, so, for example, the name Makedonija is reconstituted as Македонија, not Маќедонија in the Cyrillic source script.
+}
+
+tests {
+  test "Маќедонија", "Makedonija"
+  test "Општина Ердут", "Opština Erdut"
+  test "Општина Двор", "Opština Dvor"
+  test "ЛУЃЕ луѓе", "LUGE luge"
+  test "ЅВЕЗДА ѕвезда Ѕвезда", "DZVEZDA dzvezda Dzvezda"
+  test "ЌАРУВАЊЕ ќарување", "ĆARUVANJE ćaruvanje"
+}
+
+dependency "posix", import: true
+
+stage {
+  sub "Ѓ", "G", after: any("ЕИеи")
+  sub "ѓ", "g", after: any("ЕИеи")
+  sub "Ќ", "K", after: any("ЕИеи")
+  sub "ќ", "k", after: any("ЕИеи")
+
+  # CHARACTERS
+  parallel {
+    sub "А", "A"
+    sub "Б", "B"
+    sub "В", "V"
+    sub "Г", "G"
+    sub "Д", "D"
+    sub "Ѓ", "Đ" # Đ
+    sub "Е", "E"
+    sub "Ж", "Ž" # Ž
+    sub "З", "Z"
+    sub "Ѕ", "Dz"
+    sub "И", "I"
+    sub "Ј", "J"
+    sub "К", "K"
+    sub "Л", "L"
+    sub "Љ", "Lj"
+    sub "М", "M"
+    sub "Н", "N"
+    sub "Њ", "Nj"
+    sub "О", "O"
+    sub "П", "P"
+    sub "Р", "R"
+    sub "С", "S"
+    sub "Т", "T"
+    sub "Ќ", "Ć" # Ć
+    sub "У", "U"
+    sub "Ф", "F"
+    sub "Х", "H"
+    sub "Ц", "C"
+    sub "Ч", "Č" # Č
+    sub "Џ", "Dž" # Dž
+    sub "Ш", "Š" # Š
+    sub "а", "a"
+    sub "б", "b"
+    sub "в", "v"
+    sub "г", "g"
+    sub "д", "d"
+    sub "ѓ", "đ" # đ
+    sub "е", "e"
+    sub "ж", "ž" # ž
+    sub "з", "z"
+    sub "ѕ", "dz"
+    sub "и", "i"
+    sub "ј", "j"
+    sub "к", "k"
+    sub "л", "l"
+    sub "љ", "lj"
+    sub "м", "m"
+    sub "н", "n"
+    sub "њ", "nj"
+    sub "о", "o"
+    sub "п", "p"
+    sub "р", "r"
+    sub "с", "s"
+    sub "т", "t"
+    sub "ќ", "ć" # ć
+    sub "у", "u"
+    sub "ф", "f"
+    sub "х", "h"
+    sub "ц", "c"
+    sub "ч", "č" # č
+    sub "џ", "dž" # dž
+    sub "ш", "š" # š
+  }
+
+  # POSTRULES
+  # rewritten by hand to work properly
+  # DZ
+  sub capture(maybe(upper)) + "Dz" + capture(upper), ref(1) + "DZ" + ref(2)
+  sub capture(upper) + "Dz" +  capture(maybe(upper)), ref(1) + "DZ" + ref(2)
+
+  #LJ
+  sub capture(upper) + "Lj" + capture(maybe(upper)), ref(1) + "LJ" + ref(2)
+  sub capture(maybe(upper)) + "Lj" + capture(upper), ref(1) + "LJ" + ref(2)
+
+  #NJ
+  sub capture(upper) + "Nj" + capture(maybe(upper)), ref(1) + "NJ" + ref(2)
+  sub capture(maybe(upper)) + "Nj" + capture(upper), ref(1) + "NJ" + ref(2)
+
+  #DŽ
+  sub capture(upper) + "Dž" + capture(maybe(upper)), ref(1) + "DŽ" + ref(2)
+  sub capture(maybe(upper)) + "Dž" + capture(upper), ref(1) + "DŽ" + ref(2)
+
+  compose
+}
+