interscript 0.1.0 → 0.1.5

data/maps/ua-ukr-Cyrl-Latn-1996.yaml

@@ -0,0 +1,193 @@
+---
+authority_id: ua
+id: 1996
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: Government of Ukraine Ukrainian System (1996)
+url: http://transliteration.eki.ee/pdf/Ukrainian.pdf
+creation_date: 1996
+description: Romanization table for Ukrainian. The current national system of romanization.
+
+notes:
+  - gh is used in the romanization of зг zgh.
+  - In initial position є -> ye, ї -> yi, й -> y, ю -> yu, я -> ya.
+
+tests:
+  - source: Алушта
+    expected: Alushta
+  - source: Борщагівка
+    expected: Borschahivka
+  - source: Вишгород
+    expected: Vyshhorod
+  - source: Гадяч
+    expected: Hadiach
+  - source: Згорани
+    expected: Zghorany
+  - source: Ґалаґан
+    expected: Galagan
+  - source: Дон
+    expected: Don
+  - source: Рівне
+    expected: Rivne
+  - source: Єнакієве
+    expected: Yenakiieve
+  - source: Наєнко
+    expected: Naienko
+  - source: Житомир
+    expected: Zhytomyr
+  - source: Запоріжжя
+    expected: Zaporizhzhia
+  - source: Закарпаття
+    expected: Zakarpattia
+  - source: Медвин
+    expected: Medvyn
+  - source: Іршава
+    expected: Irshava
+  - source: Їжакевич
+    expected: Yizhakevych
+  - source: Кадіївка
+    expected: Kadiivka
+  - source: Йосипівка
+    expected: Yosypivka
+  - source: Київ
+    expected: Kyiv
+  - source: Лебедин
+    expected: Lebedyn
+  - source: Миколаїв
+    expected: Mykolaiv
+  - source: Ніжин
+    expected: Nizhyn
+  - source: Одеса
+    expected: Odesa
+  - source: Полтава
+    expected: Poltava
+  - source: Ромни
+    expected: Romny
+  - source: Суми
+    expected: Sumy
+  - source: Тетерів
+    expected: Teteriv
+  - source: Ужгород
+    expected: Uzhhorod
+  - source: Фастів
+    expected: Fastiv
+  - source: Харків
+    expected: Kharkiv
+  - source: Біла Церква
+    expected: Bila Tserkva
+  - source: Чернівці
+    expected: Chernivtsi
+  - source: Шостка
+    expected: Shostka
+  - source: Гоща
+    expected: Hoscha
+  - source: Русь
+    expected: Rus’
+  - source: Юрій
+    expected: Yurii
+  - source: Крюківка
+    expected: Kriukivka
+  - source: Яготин
+    expected: Yahotyn
+  - source: Ічня
+    expected: Ichnia
+  - source: Знам’янка
+    expected: Znam”ianka
+
+map:
+  rules:
+    - pattern: (?<=[Зз])\u0413 # Г after З or з
+      result: Gh
+    - pattern: (?<=[Зз])\u0433 # г after З or з
+      result: gh
+    - pattern: (?<!\b\u2019)\b\u0404 # Є in initial position -> Ye
+      result: Ye
+    - pattern: (?<!\b\u2019)\b\u0454 # є in initial position -> ye
+      result: ye
+    - pattern: (?<!\b\u2019)\b\u0407 # Ї in initial position -> Yi
+      result: Yi
+    - pattern: (?<!\b\u2019)\b\u0457 # ї in initial position -> yi
+      result: yi
+    - pattern: (?<!\b\u2019)\b\u0419 # Й in initial position -> Y
+      result: "Y"
+    - pattern: (?<!\b\u2019)\b\u0419 # й in initial position -> y
+      result: "y"
+    - pattern: (?<!\b\u2019)\b\u042e # Ю in initial position -> Yu
+      result: Yu
+    - pattern: (?<!\b\u2019)\b\u044e # ю in initial position -> yu
+      result: yu
+    - pattern: (?<!\b\u2019)\b\u042f # Я in initial position -> Ya
+      result: Ya
+    - pattern: (?<!\b\u2019)\b\u044f # я in initial position -> ya
+      result: ya
+    - pattern: \b\u2019\b # ’ in the middle of a word -> ”
+      result: "\u201d"
+
+  characters:
+    "\u0410": "A"       # А
+    "\u0411": "B"       # Б
+    "\u0412": "V"       # В
+    "\u0413": "H"       # Г
+    "\u0490": "G"       # Ґ
+    "\u0414": "D"       # Д
+    "\u0415": "E"       # Е
+    "\u0404": "Ie"      # Є
+    "\u0416": "Zh"      # Ж
+    "\u0417": "Z"       # З
+    "\u0418": "Y"       # И
+    "\u0406": "I"       # І
+    "\u0407": "I"       # Ї
+    "\u0419": "I"       # Й
+    "\u041a": "K"       # К
+    "\u041b": "L"       # Л
+    "\u041c": "M"       # М
+    "\u041d": "N"       # Н
+    "\u041e": "O"       # О
+    "\u041f": "P"       # П
+    "\u0420": "R"       # Р
+    "\u0421": "S"       # С
+    "\u0422": "T"       # Т
+    "\u0423": "U"       # У
+    "\u0424": "F"       # Ф
+    "\u0425": "Kh"      # Х
+    "\u0426": "Ts"      # Ц
+    "\u0427": "Ch"      # Ч
+    "\u0428": "Sh"      # Ш
+    "\u0429": "Sch"     # Щ
+    "\u042e": "Iu"      # Ю
+    "\u042f": "Ia"      # Я
+    "\u042c": "\u2019"  # Ь -> ’
+    "\u0430": "a"       # а
+    "\u0431": "b"       # б
+    "\u0432": "v"       # в
+    "\u0433": "h"       # г
+    "\u0491": "g"       # ґ
+    "\u0434": "d"       # д
+    "\u0435": "e"       # е
+    "\u0454": "ie"      # є
+    "\u0436": "zh"      # ж
+    "\u0437": "z"       # з
+    "\u0438": "y"       # и
+    "\u0456": "i"       # і
+    "\u0457": "i"       # ї
+    "\u0439": "i"       # й
+    "\u043a": "k"       # к
+    "\u043b": "l"       # л
+    "\u043c": "m"       # м
+    "\u043d": "n"       # н
+    "\u043e": "o"       # о
+    "\u043f": "p"       # п
+    "\u0440": "r"       # р
+    "\u0441": "s"       # с
+    "\u0442": "t"       # т
+    "\u0443": "u"       # у
+    "\u0444": "f"       # ф
+    "\u0445": "kh"      # х
+    "\u0446": "ts"      # ц
+    "\u0447": "ch"      # ч
+    "\u0448": "sh"      # ш
+    "\u0449": "sch"     # щ
+    "\u044e": "iu"      # ю
+    "\u044f": "ia"      # я
+    "\u044c": "\u2019"  # Ь -> ’

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

@@ -0,0 +1,127 @@
+---
+authority_id: ungegn
+id: 1971
+language: ara
+source_script: Arab
+destination_script: Latn
+name: 1971 "Beirut system"
+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
+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.
+notes:
+  - |
+    ث is t͟h (th with sub marcon)
+    خ is k͟h (kh with sub marcon)
+    ذ is d͟h (dh with sub marcon)
+    ش is s͟h (sh with sub marcon)
+    ظ is z͟h (zh with sub marcon)
+    غ is g͟h (gh witg sub marcon)
+    The previous UN 1972 System had the following differences:
+    the character (ظ) was romanized as z̧ instead of d͟h;
+    the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |
+
+tests:
+
+  # Examples taken from:
+  # https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/2nd-uncsgn-docs/E_Conf61_4_Add1_e.pdf
+  # page 31 (38 digital)
+
+  - source: خَيبَر
+    expected: k͟haybar
+
+  - source: ظَهران
+    expected: z͟hahrān
+
+  - source: القُدس
+    expected: al quds
+
+map:
+  inherit: "un-ara-Arab-Latn-2017"
+  characters:
+
+    # sun letters
+    '\b\u0627\u0644\u062b' : 'at͟h t͟h'  # الث
+    '\b\u0627\u0644\u0630' : 'ad͟h d͟h'  # الذ
+    '\b\u0627\u0644\u0634' : 'as͟h s͟h' # الش
+    '\b\u0627\u0644\u0638' : 'az͟h z͟h' # الظ
+
+    # shadda
+    '\u062e\u0651' : 'k͟hk͟h'  # خ
+    '\u0630\u0651' : 'd͟hd͟h'  # ذ
+    '\u0634\u0651' : 's͟h'  # ش
+    '\u0638\u0651' : 'z͟hz͟h'  # ظ
+    '\u063a\u0651' : 'g͟hg͟h'  # غ
+
+    '\u062b' : 't͟h'  # ث
+    '\ufe9b' : 't͟h'  # ﺛ
+    '\ufe9c' : 't͟h'  # ﺜ
+    '\ufe9a' : 't͟h'  # ﺚ
+
+    '\u062e' : 'k͟h'  # خ
+    '\ufea7' : 'k͟h'  # ﺧ
+    '\ufea8' : 'k͟h'  # ﺨ
+    '\ufea6' : 'k͟h'  # ﺦ
+
+    '\u063a' : 'g͟h'  # غ
+    '\ufecf' : 'g͟h'  # ﻏ
+    '\ufed0' : 'g͟h'  # ﻐ
+    '\ufece' : 'g͟h'  # ﻎ
+
+    '\u0630' : 'd͟h'  # ذ
+    '\ufeac' : 'd͟h'  # ﺬ
+
+    '\u0634' : 's͟h'  # ش
+    '\ufeb7' : 's͟h'  # ﺷ
+    '\ufeb8' : 's͟h'  # ﺸ
+    '\ufeb6' : 's͟h'  # ﺶ
+
+    '\u0638' : 'z͟h'  # ظ
+    '\ufec7' : 'z͟h'  # ﻇ
+    '\ufec8' : 'z͟h'  # ﻈ
+    '\ufec6' : 'z͟h'  # ﻆ
+

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

@@ -0,0 +1,152 @@
+---
+authority_id: ungegn
+id: 1972
+language: ara
+source_script: Arab
+destination_script: Latn
+name: ROMANIZATION OF ARABIC -- UNGEGN 1972 System
+url: http://www.eki.ee/wgrs/obs_rom_vers/rom1_ar_v4_0.pdf
+creation_date: 1972
+confirmation date: 2018-06
+description: |
+  The United Nations recommended romanization
+  system was approved 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 report1
+  . In the UN resolution it was specifically
+  pointed out that the system was recommended "for
+  the romanization of the geographical names within
+  those Arabic-speaking countries where this system
+  is officially acknowledged". It cannot be
+  definitely ascertained which of the
+  Arabicspeaking countries have adopted this system
+  officially, especially since 2007 when there are
+  efforts by the Arabic Division to promote a
+  modification of the UN system (ADEGN
+  romanization, see the section on other
+  romanization systems below), with varying
+  success2 . Judging by the use of names in
+  international cartographic products which rely
+  mostly on national sources it appears that the UN
+  system or its modification is more or less
+  current in Iraq, Kuwait, Libya, Saudi Arabia3 ,
+  United Arab Emirates and Yemen, there and in some
+  other countries the system is often used without
+  diacritical marks. For the geographical names of
+  the Syrian Arab Republic international maps
+  favour the UN system while the local usage seems
+  to prefer a French-oriented romanization. Also in
+  Egypt and Sudan there exist local romanization
+  schemes or practices side by side with the UN
+  system. 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. Resolution 7 of the Seventh UN
+  Conference on the Standardization of Geographical
+  Names (1998) recommended that "the League of Arab
+  States should, through its specialized
+  structures, continue its efforts to organize a
+  conference with a view to considering the
+  difficulties encountered in applying the amended
+  Beirut system of 1972 for the romanization of
+  Arabic script, and submit, as soon as possible, a
+  solution to the United Nations Group of Experts
+  on Geographical Names". At the Eighth UN
+  Conference on the Standardization of Geographical
+  Names (2002), the Arabic Division of the UN Group
+  of Experts announced that it had finalised
+  proposed modifications to the UN recommended
+  romanization system. These proposals would be
+  submitted to the League of Arab States for
+  approval. 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 proper pointing. One
+  must also take into account dialectal and
+  idiosyncratic deviations. The romanization is
+  generally reversible though there are some
+  ambiguous letter sequences (dh, kh, sh, th) which
+  may also point to combinations of Arabic
+  characters in addition to the respective single
+  characters.
+notes:
+  - |
+    The previous UN 1972 System had the following differences:
+    the character (ظ) was romanized as z̧ instead of d͟h;
+    ح, ص, ض the cedilla (¸) was used instead of sub-macron (_) in all characters with sub-macrons.  - |
+    When the definite article al precedes a word beginning with one of the "sun letters" (t,
+    th, d, dh, r, z, s, sh, ş, ḑ, ţ, z, l, n ̧ ) the l of the definite article is assimilated with the first
+    consonant of the word: ash-Sh الشارقة āriqah.
+
+
+tests:
+
+  # Examples taken from:
+  # https://unstats.un.org/unsd/geoinfo/geonames/
+
+  - source: مِصر
+    expected: mişr
+
+  - source: قَطَر
+    expected: qaţar
+
+  - source: الجُمهُورِيَّة العِراقِيَّة
+    expected: al jumhūrīyah al ‘irāqīyah
+
+  - source: جُمهُورِيَّة مِصر العَرَبِيَّة
+    expected: jumhūrīyat mişr al ‘arabīyah
+
+  - source: الرِيَاض
+    expected: ar riyāḑ
+
+  - source: الشارِقة
+    expected: ash shāriqah
+
+map:
+  inherit: "un-ara-Arab-Latn-2017"
+  characters:
+
+    '\b\u0627\u0644\u0635' : 'aş ş'  # الص
+    '\b\u0627\u0644\u0636' : 'aḑ ḑ'  # الض
+    '\b\u0627\u0644\u0637' : 'aţ ţ'  # الط
+
+    '\u062d\u0651' : 'ḩḩ'  # ح
+    '\u0635\u0651' : 'şş'  # ص
+    '\u0636\u0651' : 'ḑḑ'  # ض
+    '\u0637\u0651' : 'ţţ'  # ط
+    '\u0638\u0651' : 'z̧z̧'  # ظ
+
+    '\u062d' : 'ḩ' # ح
+    '\ufea3' : 'ḩ' # ﺣ
+    '\ufea4' : 'ḩ' # ﺤ
+    '\ufea2' : 'ḩ' # ﺢ
+
+    '\u0635' : 'ş'  # ص
+    '\ufebb' : 'ş'  # ﺻ
+    '\ufebc' : 'ş'  # ﺼ
+    '\ufeba' : 'ş'  # ﺺ
+
+    '\u0636' : 'ḑ'  # ض
+    '\ufebf' : 'ḑ'  # ﺿ
+    '\ufec0' : 'ḑ'  # ﻀ
+    '\ufebe' : 'ḑ'  # ﺾ
+
+    '\u0637' : 'ţ'  # ط
+    '\ufec3' : 'ţ'  # ﻃ
+    '\ufec4' : 'ţ'  # ﻄ
+    '\ufec2' : 'ţ'  # ﻂ
+
+    '\u0638' : 'z̧'  # ظ
+    '\ufec7' : 'z̧'  # ﻇ
+    '\ufec8' : 'z̧'  # ﻈ
+    '\ufec6' : 'z̧'  # ﻆ
+