interscript 0.1.0 → 0.1.5

data/maps/ses-ara-arab-latn-1930.yaml

@@ -0,0 +1,275 @@
+---
+authority_id: ungegn
+id: 1930
+language: ara
+source_script: Arab
+destination_script: Latn
+name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System
+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.
+notes:
+  - |
+    The Survey of Egypt System (SES) of romanization has the following correspondences with
+    the UN system:
+    á = a #  ـَى fatha followed by ى which is ا not ي
+    ā = â (a) # ـَا fatha followed by alef // آ
+    -ah (ة- = (a # ة ta' marboota at the end of a sentence
+    aw = ô (au) # ـَوْ
+    ay = ei (ai) # ـَيْ
+    ḏ = ḍ # ض
+    dh = dh (z) # ذ
+    d͟h = ẓ (d) # ظ
+    ẖ = ḥ # ح
+    ī = î
+    j = g (j)
+    q = q (k)
+    s = s (c)
+    s̱ = ṣ
+    ṯ = ṭ
+    th = th (t)
+    ū = û
+    ‘ = ‛
+  - |
+    The variants in parentheses are used depending on pronunciation and tradition. Not all the
+    variations have been given above. The article is always written el- (El-Kafr el-Qadîm, Sharm
+    el-Sheikh).
+tests:
+
+  # Examples taken from:
+  # https://unstats.un.org/unsd/geoinfo/geonames/
+
+  - source: شَرم الشَيْخ
+    expected: sharm el-sheikh
+
+  - source: الكَفر القَدِيم
+    expected: el-kafr el-qadîm
+map:
+  inherit: "un-ara-Arab-Latn-2017"
+  characters:
+
+
+    # special pointed letters
+    '\u0639\u064e' : '‛a'  # عَ
+    '\u0639\u0650' : '‛i'  # عِ
+    '\u0639\u064f' : '‛û'  # عُ
+    # handle MacOS regex difference
+    '\u0639\u064f\u0648' : '‛û'  # عُو damma followed by و
+    '\u0650\u064a' : 'î' # ـِي kasra followed by ي
+    '\u0650\u064a\u0651\u064e' : 'îy' # ـِيَّ
+    '\u064f\u0648' : 'û'  # ـُو damma followed by و
+    '\u064e\u0627' :   # ـَا fatha followed by ا
+      - 'â'
+      - 'a'
+    '\u064e\u0649' : 'a'  # ـَى fatha followed by ى which is ا not ي
+    '\u064e\u0648\u0652' :  # ـَوْ
+      - 'ô'
+      - 'au'
+    '\u064e\u064a\u0652' :   # ـَيْ
+      - 'ei'
+      - 'ai'
+    '\u0622' :   # آ
+      - 'â'
+      - 'a'
+
+    # ta' marboota
+    '\u0629$' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{2})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{3})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{4})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{5})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{6})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{7})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{8})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{9})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{10})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{11})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{12})\u0629' : 'a'
+    '(?<=\b\u0627\u0644[\u0600-\u06ff]{13})\u0629' : 'a'
+
+
+    # Sun letters
+    '\b\u0627\u0644\u062a' : 'el-t'  # الت
+    '\b\u0627\u0644\u062b' :  # الث
+      - 'el-th'
+      - 'el-t'
+    '\b\u0627\u0644\u062f' : 'el-d' # الد
+    '\b\u0627\u0644\u0630' :  # الذ
+      - 'el-dh'
+      - 'el-z'
+    '\b\u0627\u0644\u0631' : 'el-r' # الر
+    '\b\u0627\u0644\u0632' : 'el-z'  # الز
+    '\b\u0627\u0644\u0633' : # الس
+      - 'el-s'
+      - 'el-c'
+    '\b\u0627\u0644\u0634' : 'el-sh' # الش
+    '\b\u0627\u0644\u0635' : 'el-ṣ'  # الص
+    '\b\u0627\u0644\u0636' : 'el-ḍ'  # الض
+    '\b\u0627\u0644\u0637' : 'el-ṭ'  # الط
+    '\b\u0627\u0644\u0638' :  # الظ
+      - 'el-ẓ'
+      - 'el-d'
+    '\b\u0627\u0644\u0644' : 'el-l'  # الل
+    '\b\u0627\u0644\u0646' : 'el-n'  # الن
+
+
+    # shadda
+    '\u062b\u0651' :  # ث
+      - 'thth'
+      - 'tt'
+    '\u062c\u0651' :  # ج
+      - 'gg'
+      - 'jj'
+    '\u062d\u0651' : 'ḥḥ'  # ح
+    '\u062e\u0651' : 'khkh'  # خ
+
+    '\u0633\u0651' :  # س
+      - 'ss'
+      - 'cc'
+    '\u0635\u0651' : 'ṣṣ'  # ص
+    '\u0636\u0651' : 'ḍḍ'  # ض
+    '\u0637\u0651' : 'ṭṭ'  # ط
+    '\u0638\u0651' :  # ظ
+      - 'ẓẓ'
+      - 'dd'
+    '\u0642\u0651' :  # ق
+      - 'qq'
+      - 'kk'
+
+    '\b\u0627\u0644' : 'el-'  # ال
+
+    # normal letters
+    '\u062c' : # ج
+      - 'g'
+      - 'j'
+    '\ufe9f' :  # ﺟ
+      - 'g'
+      - 'j'
+    '\ufea0' :  # ﺠ
+      - 'g'
+      - 'j'
+    '\ufe9e' :  # ﺞ
+      - 'g'
+      - 'j'
+
+    '\u062d' : 'ḥ' # ح
+    '\ufea3' : 'ḥ' # ﺣ
+    '\ufea4' : 'ḥ' # ﺤ
+    '\ufea2' : 'ḥ' # ﺢ
+
+    '\u062e' : 'kh'  # خ
+    '\ufea7' : 'kh'  # ﺧ
+    '\ufea8' : 'kh'  # ﺨ
+    '\ufea6' : 'kh'  # ﺦ
+
+    '\u0630' : # ذ
+      - 'dh'
+      - 'z'
+    '\ufeac' :  # ﺬ
+      - 'dh'
+      - 'z'
+
+
+    '\u0633' :  # س
+      - 's'
+      - 'c'
+    '\ufeb3' :  # ﺳ
+      - 's'
+      - 'c'
+    '\ufeb4' :  # ﺴ
+      - 's'
+      - 'c'
+    '\ufeb2' :  # ﺲ
+      - 's'
+      - 'c'
+
+    '\u0635' : 'ṣ'  # ص
+    '\ufebb' : 'ṣ'  # ﺻ
+    '\ufebc' : 'ṣ'  # ﺼ
+    '\ufeba' : 'ṣ'  # ﺺ
+
+    '\u0636' : 'ḍ'  # ض
+    '\ufebf' : 'ḍ'  # ﺿ
+    '\ufec0' : 'ḍ'  # ﻀ
+    '\ufebe' : 'ḍ'  # ﺾ
+
+    '\u0637' : 'ṭ'  # ط
+    '\ufec3' : 'ṭ'  # ﻃ
+    '\ufec4' : 'ṭ'  # ﻄ
+    '\ufec2' : 'ṭ'  # ﻂ
+
+    '\u0639' : '‛'  # ع
+    '\ufecb' : '‛'  # ﻋ
+    '\ufecc' : '‛'  # ﻌ
+    '\ufeca' : '‛'  # ﻊ
+
+    '\u0638' :  # ظ
+      - 'ẓ'
+      - 'd'
+    '\ufec7' :  # ظ
+      - 'ẓ'
+      - 'd'
+    '\ufec8' :  # ظ
+      - 'ẓ'
+      - 'd'
+    '\ufec6' :  # ظ
+      - 'ẓ'
+      - 'd'
+
+    '\u0642' :  # ق
+      - 'q'
+      - 'k'
+    '\ufed7' :  # ﻗ
+      - 'q'
+      - 'k'
+    '\ufed8' :  # ﻘ
+      - 'q'
+      - 'k'
+    '\ufed6' :  # ﻖ
+      - 'q'
+      - 'k'

data/maps/stategeocadastre-ukr-Cyrl-Latn-1993.yaml

@@ -0,0 +1,222 @@
+---
+authority_id: stategeocadastre
+id: 1993
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: PROVISIONAL RULES OF REPRODUCING LETTERS OF THE UKRAINIAN ALPHABET WITH LATIN (ENGLISH) CHARACTERS
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/17th-gegn-docs/17th_gegn_WP73.pdf
+creation_date: 1993
+description: |
+  These Rules are intended for Romanized transliteration of Ukrainian
+  geographic names in international cartographic editions.
+
+  Geographic names of Russia, Byelorussia, Bulgaria and other states
+  using the Cyrillic alphabet are transliterated according to rules
+  accepted in those states.
+
+  These Rules come into effect from the moment of their approval by
+  the Main Administration of Geodesy, Cartography and Cadastre and
+  will be effective until the introduction of a State standard of
+  Ukraine regulating the Romanized transliteration of the Ukrainian
+  alphabet.
+
+notes:
+  - No apostrophe (’) is used in transliteration, the combination "ьо" is transliterated as "io"
+  - Use of capitals in Latin version of Ukrainian geographic names correspond to the Ukrainian spelling
+  - Generics geographical terms standing before or after a name in full or abbreviated form are transliterated
+  - Romanized versions of complex and compound Ukrainian toponyms (one word, hyphenated or separate words) will follow the Ukrainian spelling
+  - In indexes of Romanized geographical names entries must be arranged in the order of the Latin (English) alphabet
+  - Geographic names of Russia, Byelorussia, Bulgaria and other states using the Cyrillic alphabet are transliterated according to rules accepted in those states.
+  - "Ed: There seems to be a mistake in the source document. 'ц' should be replaced with ts instead 'tz'."
+
+tests:
+  - source: Кам’янка # note[1]
+    expected: Kamianka
+  - source: Сьомаки # note[1]
+    expected: Siomaky
+  - source: Усть-Чорна # note[2]
+    expected: Ust’-Chorna
+  - source: Чорне море # note[2]
+    expected: Chorne more
+  - source: оз. Сиваш # note[3]
+    expected: oz. Syvash
+  - source: Кримський канал # note[3]
+    expected: Kryms’kyi kanal # ! Example had typo in original document "Krums’kyi kanal"
+  - source: Гола Пристань
+    expected: Hola Prystan’
+  - source: Корсунь Шевченківський
+    expected: Korsun’ Shevchenkivs’kyi
+  - source: Верхньодніпровськ
+    expected: Verkhniodniprovs’k
+  - source: Варва
+    expected: Varva
+  - source: Броди
+    expected: Brody
+  - source: Верховина
+    expected: Verkhovyna
+  - source: Глухів
+    expected: Hlukhiv
+  - source: Великий
+    expected: Velykyi
+  - source: Ґрунь(гора)
+    expected: Grun’(hora)
+  - source: Димер
+    expected: Dymer
+  - source: Срібне
+    expected: Sribne
+  - source: Євпаторія
+    expected: Yevpatoriia
+  - source: Єнакієве
+    expected: Yenakiieve
+  - source: Жолква
+    expected: Zholkva
+  - source: Затока
+    expected: Zatoka
+  - source: Житомир
+    expected: Zhytomyr
+  - source: Інгул
+    expected: Inhul
+  - source: Зміїв
+    expected: Zmiïv
+  - source: Йосипівка
+    expected: Yosypivka
+  - source: Стрий
+    expected: Stryi
+  - source: Калуш
+    expected: Kalush
+  - source: Лубни
+    expected: Lubny
+  - source: Миколаїв
+    expected: Mykolaïv
+  - source: Ніжин
+    expected: Nizhyn
+  - source: Острог
+    expected: Ostroh
+  - source: Печеніги
+    expected: Pechenihy
+  - source: Рівне
+    expected: Rivne
+  - source: Сарата
+    expected: Sarata
+  - source: Тячів
+    expected: Tiachiv
+  - source: Узин
+    expected: Uzyn
+  - source: Форос
+    expected: Foros
+  - source: Харків
+    expected: Kharkiv
+  - source: Цюрупінськ
+    expected: Tsiurupins’k
+  - source: Черемош
+    expected: Cheremosh
+  - source: Шацьк
+    expected: Shats’k
+  - source: Щорс
+    expected: Shchors
+  - source: Хмельницький
+    expected: Khmel’nyts’kyi # ! Example had typo in original document "Khmel’nyts’ky"
+  - source: Юрівка
+    expected: Yurivka
+  - source: Любеч
+    expected: Liubech
+  - source: Ялта
+    expected: Yalta
+  - source: Ясіня
+    expected: Yasinia
+
+
+map:
+  rules:
+    - 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\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
+    # note[1]
+    - pattern: \b\u2019\b # remove ’
+      result: ""
+    - pattern: \u042c\u041e
+      result: "IO"
+    - pattern: \u044c\u043e
+      result: "io"
+
+  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\u0308"  # 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 note[7]
+    "\u0427": "Ch"       # Ч
+    "\u0428": "Sh"       # Ш
+    "\u0429": "Shch"     # Щ
+    "\u042c": "\u2019"   # Ь
+    "\u042e": "Iu"       # Ю
+    "\u042f": "Ia"       # Я
+    "\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 note[7]
+    "\u0447": "ch"       # ч
+    "\u0448": "sh"       # ш
+    "\u0449": "shch"     # щ
+    "\u044e": "iu"       # ю
+    "\u044f": "ia"       # я
+    "\u044c": "\u2019"   # ь