interscript 0.1.1 → 0.1.6

data/maps/un-mon-Mong-Latn-2013.yaml

@@ -0,0 +1,99 @@
+---
+authority_id: un
+id: 2013
+language: mon
+source_script: Mong
+destination_script: Latn
+name: Mongolian Romanization in China, Version 4.0
+url: http://www.eki.ee/wgrs/rom1_mnc.htm
+creation_date: 2013-09
+description: |
+  The United Nations resolution III/8 in 1977 recognized the Scheme for
+  a Chinese Phonetic Alphabet (Pinyin) as China’s official Roman alphabet
+  scheme and recommended the alphabet as the international system for the
+  romanization of Chinese geographical names. In China Mongolian
+  geographical names are transcribed directly from the Mongolian script
+  into Pinyin. The scheme was published in Toponymic Guidelines for Map
+  and Other Editors: China, 19821.
+
+  The system is used in China and in international cartographic
+  products.
+
+  Mongolian uses a vertical script. Transcription of Mongolian names is
+  made from their proper pronunciation based on the written form of the
+  Mongolian language and Qahar vernacular, with Zhenglan as its
+  representative pronunciation. Due to the complex nature of the script
+  the romanization scheme is not reversible, e.g. the name of the city
+  Hohhot is written ᠬᠥᠬᠡᠬᠣᠲᠠ but may be transliterated as kökeqota.
+
+notes:
+  - The long and short Mongolian vowels are not distinguished in the
+    spelling for general use, but in recording the pronunciation of
+    place-names, the long vowel is represented by duplication.
+  - Where two Roman equivalents are given, the second (in brackets) is
+    used for recording the pronunciation of place-names while the first
+    form is for general use.
+  - In the table only word-initial character variants are shown.
+    Depending on the position in the word many variants of the characters
+    are used as well as some ligatures. These features are not covered here.
+  - For technical reasons the characters of the Mongolian script are
+    turned 90˚ anti-clockwise.
+
+tests:
+  - source: "ᠬᠥᠬᠡᠬᠣᠲᠠ"
+    expected: "kökeqota"
+map:
+  rules:
+    - pattern: \u182c(\u1821|\u1825|\u1826)
+      result: "k\\1"
+    - pattern: \u182d(\u1821|\u1825|\u1826)
+      result: "g\\1"
+
+  characters:
+    "ᠠ": "a"
+    "ᠪ": "b"
+    "ᠼ": "c"
+    "ᠲ": "d"
+    "ᠳ": "d"
+    "ᠡ": "e"
+    "ᠹ": "f"
+    "ᠭ": "ġ"
+    "ᠺ": "g"
+    "ᠬ": "q"
+    "ᠾ": "h"
+    "ᠢ": "i"
+    "ᠵ": "j"
+    "ᠺ": "k"
+    "ᠯ": "l"
+    "ᠮ": "m"
+    "ᠨ": "n"
+    "ᠥ": "ö"
+    "ᠫ": "p"
+    "ᠴ": "q"
+    "ᠷ": "r"
+    "ᠰ": "s"
+    "ᠲ": "t"
+    "ᠦ": "u"
+    "ᠸ": "w"
+    "ᠱ": "x"
+    "ᠶ": "y"
+    "ᠽ": "z"
+    "ᠣ": "o"
+      # - "o" # General use
+      # - "ô" # For place names
+    "ᠤ": "u"
+      # - "u" # General use
+      # - "û" # For place names
+
+
+    # @TODO Exceptional
+    #
+    # This is failing the whole test suite, but as far as I understood
+    # from the comment, this city name is exceptional, so we are temporarliy
+    # adding it as execeptional rules for now.
+    #
+    # But, we will need some natives attension to help us out here, and maybe
+    # come up with some basic rules for this exceptional pattern.
+    #
+
+    "ᠬᠥᠬᠡᠬᠣᠲᠠ": "kökeqota"

data/maps/un-nep-Deva-Latn-1972.yaml

@@ -0,0 +1,163 @@
+---
+authority_id: ungegn
+id: 1972
+language: nep
+source_script: Deva
+destination_script: Latn
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Nepali Romanization, 1972
+url: https://www.eki.ee/wgrs/v3_0/rom1_ne.pdf
+creation_date: 1972
+confirmation_date: 2010
+description: |
+  The United Nations recommended system was approved in 1972 (II/11), based on a report
+  prepared by D. N. Sharma. The note on the system was published in volume II of the
+  conference report.
+
+  There is no evidence of the use of the system either in Nepal or in international cartographic
+  products. The resolution IV/17 (1982) recommended association, inter alia, with Nepal in
+  carrying out further studies on the system. In Nepal a system of romanization is employed by
+  the Nepal Survey Department (NSD). This system has been applied to names appearing on
+  national mapping, and it is also used in the Geographic Information Infrastructure Programme
+  (NGIIP).
+
+  Nepali (Nepālī) uses the alphasyllabic script Devanāgarī.
+
+notes:
+
+  - In normal spelling ṙ and ṙh are not marked, instead dotless ड ḍa, ढ ḍha are used to denote these sounds.
+  - |
+    Ligatures may be formed with r as the first component: ~ह rha.
+
+tests:
+  - source: "लेखन"
+    expected: "laekhana"
+  - source: "मुद्रा"
+    expected: "maudaaraā"
+  - source: "प्रशंसा"
+    expected: "paarashaṁsaā"
+  - source: "अंक"
+    expected: "aṁka"
+  - source: "नेकपाले स्थगित स्थायी कमिटीको बैठक भदौ गते बोलाउने भएको"
+    expected: "naekapaālae saathagaita saathaāyaī kamaiṭaīkao baaiṭhaka bhadaau gatae baolaāunae bhaekao"
+  - source: "न घर रह्यो, न परिवार"
+    expected: "na ghara rahaayao, na paraivaāra"
+  - source: "ढोरपाटनमा भुजीखोला बाढीपहिरोले अभिभावक गुमाएका बालबालिकाको बिचल्ली"
+    expected: "ḍhaorapaāṭanamaā bhaujaīkhaolaā baāḍhaīpahairaolae abhaibhaāvaka gaumaāekaā baālabaālaikaākao baichalaalaī"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "sausaamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  - source: "संविधान जारी भएसँगै सार्वजनिक प्रशासनमा नयाँ उत्साह आउने अपेक्षा थियो"
+    expected: "saṁvaidhaāna jaāraī bhaesam̐gaai saāraavajanaika paarashaāsanamaā nayaām̐ utaasaāha āunae apaekaaṣhaā thaiyao"
+  - source: "देशमा कोरोना संक्रमित र मृतकको संख्या हरेक दिन बढ्दो छ"
+    expected: "daeshamaā kaoraonaā saṁkaaramaita ra maṛtakakao saṁkhaayaā haraeka daina baḍhaadao chha"
+  - source: "गाउँपालिकाका अध्यक्ष टिका गुरुङका अनुसार विष्णुदासलाई राजुले सुत्नका लागि बेलुका साथी लगेका थिए"
+    expected: "gaāum̐paālaikaākaā adhaayakaaṣha ṭaikaā gaurauṅakaā anausaāra vaiṣhaaṇaudaāsalaāī raājaulae sautaanakaā laāgai baelaukaā saāthaī lagaekaā thaie"
+  - source: "यो आयोजना गाउँपालिकाको केन्द्र तेल्लोकमा पर्छ"
+    expected: "yao āyaojanaā gaāum̐paālaikaākao kaenaadaara taelaalaokamaā paraachha"
+  - source: "सुस्मिताका काका हेमबहादुर र काकीलाई पनि पहिरोले बगायो"
+    expected: "sausaamaitaākaā kaākaā haemabahaādaura ra kaākaīlaāī panai pahairaolae bagaāyao"
+  - source: "चैत पहिलो साता घर आएका उनी लकडाउन भएपछि यतै रोकिए"
+    expected: "chaaita pahailao saātaā ghara āekaā unaī lakaḍaāuna bhaepachhai yataai raokaie"
+  - source: "काम गर्न जानेको हकमा रोजगारदाता कम्पनीको पत्रसँगै वडा र जिल्ला प्रशासनको सिफारिस अनिवार्य गरिएको छ"
+    expected: "kaāma garaana jaānaekao hakamaā raojagaāradaātaā kamaapanaīkao pataarasam̐gaai vaḍaā ra jailaalaā paarashaāsanakao saiphaāraisa anaivaāraaya garaiekao chha"
+
+map:
+
+  characters:
+
+    # Vowels and Diphthongs
+    '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'
+
+    # Medials # Needed for connecting constants
+
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛ"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+
+    # 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' # or wa [Note#3]
+
+    # Sibilants
+    'श': 'sha'
+    'ष': 'ṣha'
+    'स': 'sa'
+
+    # Dotted variants
+    'क़': qa
+    'ख़': ḳha
+    'ग़': ga
+    'ज़': za
+    'ड़': ṙa
+    'ढ़': ṙha
+    'फ़': fa
+
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Anusvāra
+    'ं': 'ṁ'
+
+    # Anunāsika
+    'ँ': 'm̐'
+
+    # halanta
+    '्': 'a'

data/maps/un-rus-Cyrl-Latn-1987.yaml

@@ -0,0 +1,166 @@
+---
+authority_id: ungegn
+id: 1987
+language: rus
+source_script: Cyrl
+destination_script: Latn
+name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Russian Romanization system
+url: http://www.eki.ee/wgrs/rom1_ru.htm
+creation_date: 1987
+confirmation_date: 2016
+description: |
+  The United Nations recommended system was approved in 1987 (V/18),
+  based on the official system of the Main Administration of Geodesy and
+  Cartography of the former Soviet Union, also known as the GOST 1983
+  system (GOST 16876-71). The table was published as an annex to the
+  resolution.
+
+  The system is used in the Russian Federation and increasingly in
+  international cartographic products.
+
+  Russian uses the Cyrillic script which is alphabetic. The
+  romanization table is unambiguous and can be applied automatically. The
+  system is reversible, although rarely there can be ambiguities.
+
+notes:
+  - "Cursive forms of some characters might be formed differently: Аа Бб
+    Вв Гг Дд Ее Ёё Жж Зз Ии Йй Кк Лл Мм Нн Оо Пп Рр Сс Тт Уу Фф Хх Цц Чч Шш
+    Щщ Ъъ Ыы Ьь Ээ Юю Яя."
+
+  - Fifth United Nations Conference on the Standardization of
+    Geographical Names. Montreal, 18–31 August 1987. Vol. I. Report of the
+    Conference, pp. 40–41.
+
+tests:
+  - source: Aнaпa
+    expected: Anapa
+
+  - source: Бaбушкин
+    expected: Babuškin
+
+  - source: Вaвилово
+    expected: Vavilovo
+
+  - source: Гaгaрин
+    expected: Gagarin
+
+  - source: Дудинкa
+    expected: Dudinka
+
+  - source: Елисeeвкa
+    expected: Eliseevka
+
+  - source: Ёлкино
+    expected: "\u00CBlkino"
+
+  - source: Псëл
+    expected: Psël
+
+  - source: Жужa
+    expected: Žuža
+
+  - source: Звëздный
+    expected: Zvëzdnyj
+
+  - source: Идрицa
+    expected: Idrica
+
+  - source: Зaрaйск
+    expected: Zarajsk
+
+  - source: Кокaнд
+    expected: Kokand
+
+  - source: Лaлвaр
+    expected: Lalvar
+
+  - source: Мaймaк
+    expected: Majmak
+
+  - source: Нeжин
+    expected: Nežin
+
+  - source: Обoдoвкa
+    expected: Obodovka
+
+  - source: Пaп
+    expected: Pap
+
+  - source: Рeбрихa
+    expected: Rebriha
+
+  - source: Сaсoвo
+    expected: Sasovo
+
+  - source: Тaттa
+    expected: Tatta
+
+  - source: Уржум
+    expected: Uržum
+
+  - source: Фoфaнoвo
+    expected: Fofanovo
+
+  - source: Хoхломa
+    expected: Hohloma
+
+  - source: Цвeткoвo
+    expected: Cvetkovo
+
+  - source: Чeчeльник
+    expected: Čečel’nik
+
+  - source: Шишкинo
+    expected: Šiškino
+
+  - source: Щукинo
+    expected: Ščukino
+
+  - source: Пoдъячeвo
+    expected: Pod”jačevo
+
+  - source: Ыныкчaнский
+    expected: Ynykčanskij
+
+  - source: Пaрaньгa
+    expected: Paran’ga
+
+  - source: Кaзaнь
+    expected: Kazan’
+
+  - source: Щучьe
+    expected: Ščuč’e
+
+  - source: Элистa
+    expected: Èlista
+
+  - source: Юринo
+    expected: Jurino
+
+  - source: Юхнoв
+    expected: Juhnov
+
+  - source: Юрюзaнь
+    expected: Jurjuzan’
+
+  - source: Ямaл
+    expected: Jamal
+
+  - source: Язъявaн
+    expected: Jaz”javan
+
+  - source: Яя
+    expected: Jaja
+
+  - source: Вязьмa
+    expected: Vjaz’ma
+
+
+map:
+  inherit: gost-rus-Cyrl-Latn-16876-71-1983
+
+  characters:
+    '\u042A' : '”'  # Ъ
+    '\u042C' : '’'  # Ь
+    '\u044A' : '”'  # ъ
+    '\u044C' : '’'  # ь

data/maps/un-ukr-Cyrl-Latn-1998.yaml

@@ -0,0 +1,30 @@
+---
+authority_id: un
+id: 1998
+language: ukr
+source_script: Cyrl
+destination_script: Latn
+name: ROMANIZATION SYSTEM FOR BELARUSIAN, RUSSIAN AND UKRAINIAN CYRILLIC
+url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
+creation_date: 1998
+
+tests:
+
+map:
+  inherit: gost-rus-Cyrl-Latn-16876-71-1983
+
+  characters:
+    '\u0490' : '?'  # Ґ
+    '\u0491' : '?'  # ґ
+
+    '\u0404' : "Je" # Є
+    '\u0454' : "je" # є
+
+    '\u0406' : 'I'  # І
+    '\u0456' : 'i'  # і
+
+    '\u0407' : 'I'  # Ї
+    '\u0457' : 'i'  # ї
+
+    '\u2019' : '?'
+    "'" : '?'