interscript-maps 2.1.0 → 2.3.1a

data/maps/odni-uzb-Cyrl-Latn-2015.imp

@@ -4,9 +4,7 @@ metadata {
   language: iso-639-2:uzb
   source_script: Cyrl
   destination_script: Latn
-  name: Office of the Director Of National Intelligence Uzbek Personal Names 2015, ICS-630-01 Annex V
-
-  # url:
+  name: ICS-630-01 Romanization of Uzbek Personal Names (2015)
   source: ICS-630-01 Annex V
   creation_date: 2015
   confirmation_date: 2015

data/maps/ses-ara-Arab-Latn-1930.imp

@@ -1,58 +1,15 @@
 metadata {
-  authority_id: ungegn
+  authority_id: ses
   id: 1930
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  name: Survey of Egypt Romanization
   url: http://www.eki.ee/wgrs/rom1_ar.pdf
   creation_date: 1930
   confirmation_date: 2018-06
   description: |
-    The current United Nations recommended romanization
-    system was approved in 2017 (resolution XI/3), based on
-    the system adopted by Arabic experts at the conference
-    held in Beirut in 2007, the Unified Arabic
-    Transliteration System, taking into account the
-    practical amendments and corrections carried out and
-    agreed upon by the representatives of the Arabic-
-    speaking countries at the Fourth Arab Conference on
-    Geographical Names, held in Beirut in 2008, and some
-    clarifications and amendments agreed in Riyadh in 20171.
-    Previously, the United Nations had approved a
-    romanization system in 1972 (resolution II/8), based on the
-    system adopted by Arabic experts at the conference
-    held at Beirut in 1971 with the practical amendments carried out
-    and agreed upon by the representatives of the Arabic-speaking
-    countries at their conference. The table was published in volume
-    II of the conference report.
-    In UN resolution XI/3 it is specifically stated that the
-    system was recommended for the “romanization of the
-    geographical names within those Arabic-speaking countries
-    where this system is officially adopted”. There is
-    evidence of its partial implementation in Jordan, Oman and
-    Saudi Arabia. The UNGEGN Working Group on Romanization
-    Systems intends to continue monitoring the UN system’s
-    implementation across Arabic-speaking countries.
-    In some countries there exist local romanization schemes
-    or practices. The geographical names of Algeria, Djibouti,
-    Mauritania, Morocco and Tunisia are generally rendered in
-    the traditional manner which conforms to the principles of
-    the French orthography.
-    The previous UN-approved system is still found in
-    considerable international usage.
-    Arabic is written from right to left. The Arabic script
-    usually omits vowel points and diacritical marks from
-    writing which makes it difficult to obtain uniform results
-    in the romanization of Arabic. It is essential to identify
-    correctly the words which appear in any particular name
-    and to know the standard Arabic-script spelling including
-    the relevant vowels. One must also take into account
-    dialectal and idiosyncratic deviations. The romanization
-    is generally reversible though there may be some ambiguous
-    letter sequences (dh, kh, sh, th) which may also point to
-    combinations of Arabic characters in addition to the
-    respective single characters.
+    The Survey of Egypt System (SES) of Romanization.
   notes:
     - |
       The Survey of Egypt System (SES) of romanization has the following correspondences with
@@ -129,20 +86,20 @@ stage {
 
 
     # Sun letters
-    sub boundary + "\u0627\u0644\u062a", "el-t" # الت
-    sub boundary + "\u0627\u0644\u062b", any(["el-th", "el-t"]) # الث
-    sub boundary + "\u0627\u0644\u062f", "el-d" # الد
-    sub boundary + "\u0627\u0644\u0630", any(["el-dh", "el-z"]) # الذ
-    sub boundary + "\u0627\u0644\u0631", "el-r" # الر
-    sub boundary + "\u0627\u0644\u0632", "el-z" # الز
-    sub boundary + "\u0627\u0644\u0633", any(["el-s", "el-c"]) # الس
-    sub boundary + "\u0627\u0644\u0634", "el-sh" # الش
-    sub boundary + "\u0627\u0644\u0635", "el-ṣ" # الص
-    sub boundary + "\u0627\u0644\u0636", "el-ḍ" # الض
-    sub boundary + "\u0627\u0644\u0637", "el-ṭ" # الط
-    sub boundary + "\u0627\u0644\u0638", any(["el-ẓ", "el-d"]) # الظ
-    sub boundary + "\u0627\u0644\u0644", "el-l" # الل
-    sub boundary + "\u0627\u0644\u0646", "el-n" # الن
+    sub boundary + "\u0627\u0644\u062a" + maybe("\u0651"), "el-t" # الت
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), any(["el-th", "el-t"]) # الث
+    sub boundary + "\u0627\u0644\u062f" + maybe("\u0651"), "el-d" # الد
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), any(["el-dh", "el-z"]) # الذ
+    sub boundary + "\u0627\u0644\u0631" + maybe("\u0651"), "el-r" # الر
+    sub boundary + "\u0627\u0644\u0632" + maybe("\u0651"), "el-z" # الز
+    sub boundary + "\u0627\u0644\u0633" + maybe("\u0651"), any(["el-s", "el-c"]) # الس
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "el-sh" # الش
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "el-ṣ" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "el-ḍ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "el-ṭ" # الط
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), any(["el-ẓ", "el-d"]) # الظ
+    sub boundary + "\u0627\u0644\u0644" + maybe("\u0651"), "el-l" # الل
+    sub boundary + "\u0627\u0644\u0646" + maybe("\u0651"), "el-n" # الن
 
 
     # shadda

data/maps/un-amh-Ethi-Latn-2016.imp

@@ -4,7 +4,7 @@ metadata {
   language: iso-639-2:amh
   source_script: Ethi
   destination_script: Latn
-  name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
+  name: Romanization of Amharic -- UNGEGN (2016)
   url: http://www.eki.ee/wgrs/rom1_am.pdf
   creation_date: 1967
   confirmation_date: 2016-03

data/maps/un-ara-Arab-Latn-1971.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1971
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: 1971 "Beirut system"
+  name: Romanization of Arabic -- Beirut system (1971)
   url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
   creation_date: 1971
   confirmation_date: 2018-06
@@ -85,10 +85,10 @@ stage {
   parallel {
 
     # sun letters
-    sub boundary + "\u0627\u0644\u062b", "at͟h t͟h" # الث
-    sub boundary + "\u0627\u0644\u0630", "ad͟h d͟h" # الذ
-    sub boundary + "\u0627\u0644\u0634", "as͟h s͟h" # الش
-    sub boundary + "\u0627\u0644\u0638", "az͟h z͟h" # الظ
+    sub boundary + "\u0627\u0644\u062b" + maybe("\u0651"), "at͟h t͟h" # الث
+    sub boundary + "\u0627\u0644\u0630" + maybe("\u0651"), "ad͟h d͟h" # الذ
+    sub boundary + "\u0627\u0644\u0634" + maybe("\u0651"), "as͟h s͟h" # الش
+    sub boundary + "\u0627\u0644\u0638" + maybe("\u0651"), "az͟h z͟h" # الظ
 
     # shadda
     sub "\u062e\u0651", "k͟hk͟h" # خ

data/maps/un-ara-Arab-Latn-1972.imp

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 1972
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 1972 System
+  name: Romanization of Arabic -- UNGEGN (1972)
   url: http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
   creation_date: 1972
   confirmation_date: 2018-06
@@ -107,9 +107,9 @@ stage {
   # CHARACTERS
   parallel {
 
-    sub boundary + "\u0627\u0644\u0635", "aş ş" # الص
-    sub boundary + "\u0627\u0644\u0636", "aḑ ḑ" # الض
-    sub boundary + "\u0627\u0644\u0637", "aţ ţ" # الط
+    sub boundary + "\u0627\u0644\u0635" + maybe("\u0651"), "aş ş" # الص
+    sub boundary + "\u0627\u0644\u0636" + maybe("\u0651"), "aḑ ḑ" # الض
+    sub boundary + "\u0627\u0644\u0637" + maybe("\u0651"), "aţ ţ" # الط
 
     sub "\u062d\u0651", "ḩḩ" # ح
     sub "\u0635\u0651", "şş" # ص

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

@@ -1,10 +1,10 @@
 metadata {
-  authority_id: ungegn
+  authority_id: un
   id: 2017
   language: iso-639-2:ara
   source_script: Arab
   destination_script: Latn
-  name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+  name: Romanization of Arabic -- Unified Arabic Transliteration System (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)
+}
+