interscript 0.1.6 → 0.1.7

data/maps/ua-ukr-Cyrl-Latn-2010.yaml

@@ -0,0 +1,192 @@
+---
+authority_id: ua
+id: 2010
+language: iso-639-2:ukr
+source_script: Cyrl
+destination_script: Latn
+name: The Cabinet of Ministers of Ukraine adopted Resolution No 55 "On Normalization of Transliteration of the Ukrainian Alphabet by Means of the Latin Alphabet"
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/26th-gegn-docs/WP/WP21_Roma_system_Ukraine%20_engl._.pdf
+creation_date: 2010
+
+description: |
+  The Cabinet of Ministers of Ukraine adopted Resolution No 55 "On
+  Normalization of Transliteration of the Ukrainian Alphabet by Means of the
+  Latin Alphabet" on January 27, 2010. The Resolution approved The Table of
+  transliteration of the Ukrainian Alphabet by Means of the Latin Alphabet.
+  As a result of the adoption of this Resolution Ukrainian proper names
+  (geographical names, names and surnames,) are rendered by means of the Latin
+  alphabet in accordance with unified rules of transliteration in official documents,
+  in cartographic editions, on signs of populated places, streets, metro stations,
+  stops, etc. 
+
+notes:
+  - Combination of letters "зг" is transliterated as "zgh" as opposed to "zh" – the equivalent of the Ukrainian letter "ж". 
+  - Soft sign and the apostrophe are not reproduced in Latin.
+  - Transliteration of first and last names of individuals and geograpical names is carried out by way of letter-for-letter representation in Latin.
+
+tests:
+  - source: Алушта
+    expected: Alushta
+  - source: Андрій
+    expected: Andrii
+  - source: Борщагівка
+    expected: Borshchahivka
+  - source: Борисенко
+    expected: Borysenko
+  - source: Вінниця
+    expected: Vinnytsia
+  - source: Володимир
+    expected: Volodymyr
+  - source: Гадяч
+    expected: Hadiach
+  - source: Богдан
+    expected: Bohdan
+  - source: Згурський
+    expected: Zghurskyi
+  - source: Ґалаґан
+    expected: Galagan
+  - source: Ґорґани
+    expected: Gorgany
+  - source: Донецьк
+    expected: Donetsk
+  - source: Дмитро
+    expected: Dmytro
+  - source: Рівне
+    expected: Rivne
+  - source: Олег
+    expected: Oleh
+  - source: Есмань
+    expected: Esman
+  - source: Єнакієве
+    expected: Yenakiieve
+  - source: Гаєвич
+    expected: Haievych
+  - source: Короп'є
+    expected: Koropie
+  - source: Житомир
+    expected: Zhytomyr
+  - source: Жанна
+    expected: Zhanna
+  - source: Жежелів
+    expected: Zhezheliv
+  - source: Закарпаття
+    expected: Zakarpattia
+  - source: Казимирчук
+    expected: Kazymyrchuk
+  - source: Медвин
+    expected: Medvyn
+  - source: Михайленко
+    expected: Mykhailenko
+  - source: Іванків
+    expected: Ivankiv
+  - source: Іващенко
+    expected: Ivashchenko
+  - source: Їжакевич
+    expected: Yizhakevych
+  - source: Кадиївка
+    expected: Kadyivka
+  - source: Мар'їне
+    expected: Marine
+  - source: Йосипівка
+    expected: Yosypivka
+  - source: Стрий
+    expected: Stryi
+  - source: Олексій
+    expected: Oleksii
+  - source: Київ
+    expected: Kyiv
+  - source: Коваленко
+    expected: Kovalenko 
+  - source: Лебедин
+    expected: Lebedyn
+  - source: Леонід
+    expected: Leonid
+  - source: Миколаїв
+    expected: Mykolaiv
+  - source: Маринич
+    expected: Marynych
+  - source: Ніжин
+    expected: Nizhyn
+  - source: Наталія
+    expected: Nataliia
+  - source: Одеса
+    expected: Odesa
+  - source: Онищенко
+    expected: Onyshchenko
+  - source: Полтава
+    expected: Poltava
+  - source: Петро
+    expected: Petro
+  - source: Решетилівка
+    expected: Reshetylivka
+  - source: Рибчинський
+    expected: Rybchynskyi
+  - source: Суми
+    expected: Sumy
+  - source: Соломія
+    expected: Solomiia
+  - source: Тернопіль
+    expected: Ternopil
+  - source: Троць
+    expected: Trots
+  - source: Ужгород
+    expected: Uzhhorod
+  - source: Уляна
+    expected: Uliana
+  - source: Фастів
+    expected: Fastiv
+  - source: Філіпчук
+    expected: Filipchuk
+  - source: Харків
+    expected: Kharkiv
+  - source: Христина
+    expected: Khrystyna
+  - source: Біла Церква
+    expected: Bila Tserkva
+  - source: Стеценко
+    expected: Stetsenko
+  - source: Чернівці
+    expected: Chernivtsi
+  - source: Шевченко
+    expected: Shevchenko
+  - source: Шостка
+    expected: Shostka
+  - source: Кишеньки
+    expected: Kyshenky
+  - source: Щербухи
+    expected: Shcherbukhy
+  - source: Гоща
+    expected: Hoshcha
+  - source: Гаращенко
+    expected: Harashchenko
+  - source: Яготин
+    expected: Yahotyn
+  - source: Ярошенко
+    expected: Yaroshenko
+  - source: Костянтин
+    expected: Kostiantyn
+  - source: Знам'янка
+    expected: Znamianka
+  - source: Феодосія
+    expected: Feodosiia
+  - source: Згорани
+    expected: Zghorany
+  - source: Розгон
+    expected: Rozghon
+
+map:
+  inherit: ua-ukr-Cyrl-Latn-1996
+
+  rules:
+    - pattern: \u0027
+      result: ""
+    - pattern: \u2019
+      result: ""
+
+  characters:
+    "\u0429": 'Shch' # Щ
+    "\u0449": 'shch' # щ
+    "\u044c": ''     # Ь ->
+    "\u042c": ''     # ь ->
+    "\u0027": ''     # ' ->
+    "\u2019": ''     # ’ ->

data/maps/{ungegn-amh-Ethi-Latn-2016.yaml → un-amh-Ethi-Latn-2016.yaml}

@@ -1,7 +1,7 @@
 ---
-authority_id: ungegn
+authority_id: un
 id: 2016
-language: amh
+language: iso-639-2:amh
 source_script: Ethi
 destination_script: Latn
 name: ROMANIZATION OF AMHARIC -- UNGEGN 2016 System
@@ -9,42 +9,68 @@ url: http://www.eki.ee/wgrs/rom1_am.pdf
 creation_date: 1967
 confirmation date: 2016-03
 description: |
-    The United Nations recommended romanization system was approved in 1967 (resolution I/17), based on the Amharic to English Transliteration System (2nd revised edition, August 1962) by the Imperial Ethiopian Mapping and Geography Institute. The table has been published in volume II of the conference report (see Ref. in Notes section).
-
-    The UN-approved system is not being used in Ethiopia, instead a simple version without diacritical marks is used. In international cartographic products mostly the BGN/PCGN 1967 system is used which differs from the former mainly by using diacritical marks differently. Often the same spellings are used without any diacritical marks.
-
-    Amharic uses the Ethiopic syllabic script whereby each syllable denotes a combination of a consonant and a vowel. It has 34 basic characters, each character having several different forms, usually called orders, according to the vowel with which the basic character is combined. The system is mainly reversible with the exception of some syllables of the 1st order which are pronounced in the same manner as the syllables of the 4th order, and some consonants.
+  The United Nations recommended romanization system was approved in 1967
+  (resolution I/17), based on the Amharic to English Transliteration System
+  (2nd revised edition, August 1962) by the Imperial Ethiopian Mapping and
+  Geography Institute. The table has been published in volume II of the
+  conference report (see Ref. in Notes section).
+
+  The UN-approved system is not being used in Ethiopia, instead a simple
+  version without diacritical marks is used. In international cartographic
+  products mostly the BGN/PCGN 1967 system is used which differs from the
+  former mainly by using diacritical marks differently. Often the same
+  spellings are used without any diacritical marks.
+
+  Amharic uses the Ethiopic syllabic script whereby each syllable denotes a
+  combination of a consonant and a vowel. It has 34 basic characters, each
+  character having several different forms, usually called orders, according to
+  the vowel with which the basic character is combined. The system is mainly
+  reversible with the exception of some syllables of the 1st order which are
+  pronounced in the same manner as the syllables of the 4th order, and some
+  consonants.
 
 notes:
-  - (A) The vowel of the sixth order (i̠) is eliminated in spelling except when the actual pronunciation requires it (e.g. not Me̠ni̠gi̠si̠ti̠ but Me̠ngi̠st).
+  - (A) The vowel of the sixth order (i̠) is eliminated in spelling except when
+    the actual pronunciation requires it (e.g. not Me̠ni̠gi̠si̠ti̠ but Me̠ngi̠st).
 
   - (B) Sounds identical to fourth-order form.
 
-  - (C) Row 34 and most combinations with W and Y are not present in the original table. These Amharic syllable characters have been taken from the BGN/PCGN 1967 table, preserving however the indication of vowels as it is done elsewhere in the table.
+  - (C) Row 34 and most combinations with W and Y are not present in the
+    original table. These Amharic syllable characters have been taken from the
+    BGN/PCGN 1967 table, preserving however the indication of vowels as it is
+    done elsewhere in the table.
 
   - |
-      Other systems of romanization.
-      The BGN/PCGN 1967 System is practically very close to the system above, except for the diacritical marks used with vowels:
+    Other systems of romanization.
+    The BGN/PCGN 1967 System is practically very close to the system above,
+    except for the diacritical marks used with vowels:
 
-                  UN  BGN/PCGN
-      1st order	e̠	 e
-      1st order	a	ā (ሀ hā, ሐ hā, ኀ hā, አ ā, ’ā, ዐ ‘ā)
-      3rd order	i	ī
-      5th order	e   ē
-      6th order	i̠	 i
+    UN  BGN/PCGN
+    1st order	e̠	 e
+    1st order	a	ā (ሀ hā, ሐ hā, ኀ hā, አ ā, ’ā, ዐ ‘ā)
+    3rd order	i	ī
+    5th order	e   ē
+    6th order	i̠	 i
 
-      Other differences:
+    Other differences:
 
-      1. The vowel characters in row 16 should be romanized in the BGN/PCGN System ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o in all other positions.
+    1. The vowel characters in row 16 should be romanized in the BGN/PCGN
+    System ā, u, ī, a, ē, i, and o initially and ’ā, ’u, ’ī, ’a, ’ē, ’i, and ’o
+    in all other positions.
 
-      2. The characters in row 20 should be romanized in the BGN/PCGN System ‘ā, ‘u, ‘ī, ‘a, ‘ē, ‘ or ‘i, and ‘o.
+    2. The characters in row 20 should be romanized in the BGN/PCGN System ‘ā,
+    ‘u, ‘ī, ‘a, ‘ē, ‘ or ‘i, and ‘o.
 
-      3. The syllables gwe̠, hwe̠, kwe̠, k’we̠ of the UN system are treated as variations of the syllables go, ho, ko, k’o in the BGN/PCGN system.
+    3. The syllables gwe̠, hwe̠, kwe̠, k’we̠ of the UN system are treated as
+    variations of the syllables go, ho, ko, k’o in the BGN/PCGN system.
 
-      4. For documentation purposes the following consonants may be romanized with diacritical marks in the BGN/PCGN system: ḥ (row 3), š (row 5), ḫ (row 13), ẖ (row 18), t͟s’ (row 31).
+    4. For documentation purposes the following consonants may be romanized
+    with diacritical marks in the BGN/PCGN system: ḥ (row 3), š (row 5), ḫ (row
+    13), ẖ (row 18), t͟s’ (row 31).
 
-
-  - (Ref.) Second United Nations Conference on the Standardization of Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp. 165–168 (Table 2).
+  - (Ref.) Second United Nations Conference on the Standardization of
+    Geographical Names. London, 10–31 May 1972. Vol. II. Technical papers, pp.
+    165–168 (Table 2).
 
 tests:
   - source: የዜግነት ክብር በ ኢትዮጵያችን ጸንቶ
@@ -573,3 +599,4 @@ map:
       - 'vi̠'
       - 'v'
     '\u126E' : 'vo'  # ቮ
+

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

@@ -1,7 +1,7 @@
 ---
 authority_id: ungegn
 id: 1971
-language: ara
+language: iso-639-2:ara
 source_script: Arab
 destination_script: Latn
 name: 1971 "Beirut system"

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

@@ -1,7 +1,7 @@
 ---
 authority_id: ungegn
 id: 1972
-language: ara
+language: iso-639-2:ara
 source_script: Arab
 destination_script: Latn
 name: ROMANIZATION OF ARABIC -- UNGEGN 1972 System

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

@@ -1,7 +1,7 @@
 ---
 authority_id: ungegn
 id: 2017
-language: ara
+language: iso-639-2:ara
 source_script: Arab
 destination_script: Latn
 name: ROMANIZATION OF ARABIC -- UNGEGN 2017 System

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

@@ -1,7 +1,7 @@
 ---
 authority_id: un
 id: 2007
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: National System of Geographic Names Transmission into Roman Alphabet in Belarus

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

@@ -1,7 +1,7 @@
 ---
 authority_id: un
 id: 2016
-language: ben
+language: iso-639-2:ben
 source_script: Beng
 destination_script: Latn
 name: Bengali Romanization, Version 4.0

data/maps/{un-ell-Grek-Latn-phonetic-1987.yaml → un-ell-Grek-Latn-1987-phonetic.yaml}

@@ -1,7 +1,7 @@
 ---
 authority_id: un
-id: 1987
-language: ell
+id: 1987-phonetic
+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.

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

@@ -1,7 +1,7 @@
 ---
 authority_id: un
-id: 1987
-language: ell
+id: 1987-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: UNGEGN Greek v4.0

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

@@ -1,12 +1,12 @@
 ---
 authority_id: un
-id: 2016
-language: ell
+id: 1987-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: UNGEGN Greek v4.0
 url: http://www.eki.ee/wgrs/rom1_el.htm
-creation_date: 2016
+creation_date: 1987
 description: |
   UNGEGN Romanization table for Greek
 

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

@@ -0,0 +1,222 @@
+---
+authority_id: ungegn
+id: 2016
+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
+url: https://www.eki.ee/wgrs/rom1_hi.pdf
+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. It was stated in 1987 that the appropriate resolution had not been implemented in
+  India and the Hunterian system was still in use in large-scale mapping
+
+  Hindi uses the alphasyllabic script Devanāgarī 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 (only three are given). The system is mostly
+  reversible but there may exist some ambiguities in the romanization of vowels (independent
+  vs. abbreviated characters) and consonants
+
+notes:
+  - |
+    It is recommended that the vowel अ (a) should always be romanized except when it ends a
+    name. If a name ends with a consonant, the consonant should carry a sub-macron. Such
+    cases, however, will be very rare. For example, कानपुर Kānapur (not Kānapura), जगत्
+    Jagaṯ.
+  - |
+    If each letter of a digraph or any two parts of a trigraph has a distinct independent sound
+    then it should be indicated by a hyphen, thus d-h.
+
+tests:
+  - source: "परिपक्क"
+    expected: "paraipakka"
+  - source: "जगत्"
+    expected: "jagat"
+  - source: "संख्या"
+    expected: "saṁkhyaā"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "gaṁbhaīra maraījaoṁ kae maāmalae maeṁ bhaārata daūsarae naṁbara para"
+  - source: "कोरोना अपडेट्स"
+    expected: "kaoraonaā apaḍaeṭsa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "saīḍaīsaī chaīpha kaā bayaāna ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gaūgala plae sṭaora para paeṭaīema kaī vaāpasaī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhaārata maeṁ gaaiṁbalaiṁga kaī ijaājata nahaīṁ"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "kaoraonaā vaaiksaīna mauddae para ghairae raāṣhṭrapatai; jao baāiḍaena baolae- maujhae aura daesha kao vaaijñaānaikaoṁ para bharaosaā haai, ḍaonaālḍa ṭrampa para nahaīṁ"
+  - source: "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं"
+    expected: "gaūgala kaī kaārravaāī para paeṭaīema nae kahaā thaā kai aipa kao asthaāyaī taaura para plae-sṭaora sae haṭaāyaā gayaā haai, āpakae paaisae saurakṣhaita haaiṁ"
+map:
+
+  characters:
+
+    # I. Independent vowel characters
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛ'
+    'ॠ': 'ṝ'
+    'ऌ': 'l̤'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # II. Abbreviated vowel characters
+
+    'ा': "ā"    # का
+    'ॉ': "ā̆ "   #  additional mark: कॉ
+    'ि': "i"    # कि i
+    'ी': "ī"    # की
+    'ु': "u"    # कु
+    'ू': "ū"    # कू
+    'ृ': "ṛ"    # कृ
+    'े': "e"    # के
+    'ै': "ai"   # कै
+    'ो': "o"    # को
+    'ौ': "au"   # कौ
+
+
+    # Consonants (see Note 1)
+
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'cha'
+    'छ': 'chha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    'ढ': 'ḍha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'sha'
+    'ष': 'ṣha'
+    'स': 'sa'
+
+    # Dotted variants
+    'क़': 'qa'
+    'ख़': 'ḳha'
+    'ग़': 'ġa'
+    'ज़': 'za'
+    'ड़': 'ṙa'
+    'ढ़': 'ṙha'
+    'फ़': 'fa'
+
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Anusvāra
+    'ं': 'ṁ'
+
+    # Anunāsika
+    'ँ': 'm̐'
+
+    # halanta
+    '्': ''
+
+    # bisharga
+    'ः' : 'ḥ'
+
+    #V. Ligatures(To cover all Ligatures at unicode)
+    #  Implemnting Pronunciation without a vowel: क् k.
+
+    # Gutturals
+    'क्': 'k'
+    'ख्': 'kh'
+    'ग्': 'g'
+    'घ्': 'gh'
+    'ङ्': 'ṅ'
+
+    # Palatals
+    'च्': 'ch'
+    'छ्': 'chh'
+    'ज्': 'j'
+    'झ्': 'jh'
+    'ञ्': 'ñ'
+
+    # Cerebrals
+    'ट्': 'ṭ'
+    'ठ्': 'ṭh'
+    'ड्': 'ḍ'
+    'ढ्': 'ḍh'
+    'ण्': 'ṇ'
+
+    # Dentals
+    'त्': 't'
+    'थ्': 'th'
+    'द्': 'd'
+    'ध्': 'dh'
+    'न्': 'n'
+
+    # Labials
+    'प्': 'p'
+    'फ्': 'ph'
+    'ब्': 'b'
+    'भ्': 'bh'
+    'म्': 'm'
+
+    # Semivowels
+    'य्': 'y'
+    'र्': 'r'
+    'ल्': 'l'
+    'व्': 'v'
+
+    # Sibilants
+    'श्': 'sh'
+    'ष्': 'ṣh'
+    'स्': 's'
+
+    # Dotted variants
+    'क़्': 'q'
+    'ख़्': 'ḳh'
+    'ग़्': 'ġ'
+    'ज़्': 'z'
+    'ड़्': 'ṙ'
+    'ढ़्': 'ṙh'
+    'फ़्': 'f'