interscript-maps 2.4.3 → 2.5.0

data/maps/un-tel-Telu-Latn-1972.isc

@@ -0,0 +1,361 @@
+system "UN:tel-Telu:Latn:1972" {
+
+metadata {
+  authority_id un
+  id 1972
+  language iso-639-2:tel
+  source_script Telu
+  destination_script Latn
+  name Romanization of Telugu -- UNGEGN 4.0 (1972)
+  url https://www.eki.ee/wgrs/rom1_te.htm
+  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.
+
+    Telugu uses an alphasyllabic script 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. The system is
+    mostly reversible but there may exist some ambiguities in the romanization of vowels (independent vs. abbreviated characters)
+    and consonants (combinations with subscript consonants vs. character sequences).
+  }
+
+  notes {
+
+    note "      Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for\n      vowels following a consonant can be found in grammars; no distinction between the two is\n      made in transliteration."
+    note "      The vowel a is implicit after all consonants and consonant clusters and is supplied in\n      transliteration, with the following exceptions:\n      a) when another vowel is indicated by its appropriate sign; and\n      b) when the absence of any vowel is indicated by the superscript sign ( ౬ ) called valapalagilaka."
+    note "      Exception: Sunna is transliterated by:\n      a) ṅ before gutturals,\n      b) ñ before palatals,\n      c) ṇ before cerebrals,\n      d) n before dentals, and\n      e) m before labials."
+    note "      Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.\n      Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is\n      transliterated m"
+  }
+}
+
+tests {
+   "తమిళనాడు" ->  "tamiḷanāḍu"
+   "తంటికొండ ఘటన: ఆగని మృత్యుఘోష" ->  "taṃṭikŏṃḍa ghaṭana: āgani mṛtyughoṣha"
+   "మళ్లీ వివాదం: అమితాబ్‌పై కేసు" ->  "maḷlī vivādaṃ: amitābpai kesu"
+   "వరద సాయం పేరుతో వైట్ కాలర్ దోపిడీ" ->  "varada sāyaṃ peruto vaiṭ kālar dopiḍī"
+   "రెండో విడత జీఎస్టీ పరిహారం" ->  "rĕṃḍo viḍata jīĕsṭī parihāraṃ"
+   "నితీష్‌ కుమార్‌ అధ్యాయం ముగిసినట్లేనా?!" ->  "nitīṣh kumār adhyāyaṃ mugisinaṭlenā?!"
+   "వారిపై జీవితాంతం నిషేధం విధించండి!" ->  "vāripai jīvitāṃtaṃ niṣhedhaṃ vidhiṃchaṃḍi!"
+   "మరో లాక్‌డౌన్‌ వల్ల అన్నీ అనర్థాలే!" ->  "maro lākḍaun valla annī anarthāle!"
+   "జెసిండా మరో సంచలనం" ->  "jĕsiṃḍā maro saṃchalanaṃ"
+   "స్వీయ నిర్బంధంలోకి డబ్ల్యూహెచ్‌ఓ డైరెక్టర్‌" ->  "svīya nirbaṃdhaṃloki ḍablyūhĕcho ḍairĕkṭar"
+   "కరోనాపై యుద్ధంలో సమిధలు" ->  "karonāpai yuddhaṃlo samidhalu"
+   "అమెరికా ఎన్నికలు: ‘పెద్దన్న’ ఎవరో?!" ->  "amĕrikā ĕnnikalu: ‘pĕddanna’ ĕvaro?!"
+   "౪౬౨౬౯" ->  "46269"
+   "రంగపూర్" ->  "raṃgapūr"
+  # subscript consonant characters
+   "ట్ట" ->  "ṭṭa"
+   "ప్ప" ->  "ppa"
+   "చ్చ" ->  "chcha"
+
+  # Note: UN card expects this to start with an uppercase letter, but that would break other tests
+   "ఆంధ్ర ప్రదేశ్" ->  "āṃdhra pradesh"
+   "హైదరాబాదు" ->  "haidarābādu"
+}
+
+aliases {
+  telu_chars_1 = any("\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d")
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from "క"
+    to "k"
+    after telu_chars_1
+  }
+  sub {
+    from "ఖ"
+    to "kh"
+    after telu_chars_1
+  }
+  sub {
+    from "గ"
+    to "g"
+    after telu_chars_1
+  }
+  sub {
+    from "ఘ"
+    to "gh"
+    after telu_chars_1
+  }
+  sub {
+    from "ఙ"
+    to "ṅ"
+    after telu_chars_1
+  }
+  sub {
+    from "చ"
+    to "ch"
+    after telu_chars_1
+  }
+  sub {
+    from "ఛ"
+    to "chh"
+    after telu_chars_1
+  }
+  sub {
+    from "జ"
+    to "j"
+    after telu_chars_1
+  }
+  sub {
+    from "ఝ"
+    to "jh"
+    after telu_chars_1
+  }
+  sub {
+    from "ఞ"
+    to "ñ"
+    after telu_chars_1
+  }
+  sub {
+    from "ట"
+    to "ṭ"
+    after telu_chars_1
+  }
+  sub {
+    from "ఠ"
+    to "ṭh"
+    after telu_chars_1
+  }
+  sub {
+    from "డ"
+    to "ḍ"
+    after telu_chars_1
+  }
+  sub {
+    from "ఢ"
+    to "ḍh"
+    after telu_chars_1
+  }
+  sub {
+    from "ణ"
+    to "ṇ"
+    after telu_chars_1
+  }
+  sub {
+    from "త"
+    to "t"
+    after telu_chars_1
+  }
+  sub {
+    from "థ"
+    to "th"
+    after telu_chars_1
+  }
+  sub {
+    from "ద"
+    to "d"
+    after telu_chars_1
+  }
+  sub {
+    from "ధ"
+    to "dh"
+    after telu_chars_1
+  }
+  sub {
+    from "న"
+    to "n"
+    after telu_chars_1
+  }
+  sub {
+    from "ప"
+    to "p"
+    after telu_chars_1
+  }
+  sub {
+    from "ఫ"
+    to "ph"
+    after telu_chars_1
+  }
+  sub {
+    from "బ"
+    to "b"
+    after telu_chars_1
+  }
+  sub {
+    from "భ"
+    to "bh"
+    after telu_chars_1
+  }
+  sub {
+    from "మ"
+    to "m"
+    after telu_chars_1
+  }
+  sub {
+    from "య"
+    to "y"
+    after telu_chars_1
+  }
+  sub {
+    from "ర"
+    to "r"
+    after telu_chars_1
+  }
+  sub {
+    from "ఱ"
+    to "r"
+    after telu_chars_1
+  }
+  sub {
+    from "ల"
+    to "l"
+    after telu_chars_1
+  }
+  sub {
+    from "వ"
+    to "v"
+    after telu_chars_1
+  }
+  sub {
+    from "శ"
+    to "sh"
+    after telu_chars_1
+  }
+  sub {
+    from "ష"
+    to "ṣh"
+    after telu_chars_1
+  }
+  sub {
+    from "స"
+    to "s"
+    after telu_chars_1
+  }
+  sub {
+    from "హ"
+    to "h"
+    after telu_chars_1
+  }
+  sub {
+    from "ళ"
+    to "ḷ"
+    after telu_chars_1
+  }
+
+
+  # CHARACTERS
+  parallel {
+
+    # I. Independent vowel characters
+
+    sub "అ" "a"
+    sub "ఆ" "ā"
+    sub "ఇ" "i"
+    sub "ఈ" "ī"
+    sub "ఉ" "u"
+    sub "ఊ" "ū"
+    sub "ఋ" "ṛ"
+    sub "ౠ" "ṝ"
+    sub "ఎ" "ĕ"
+    sub "ఏ" "e"
+    sub "ఐ" "ai"
+    sub "ఒ" "ŏ"
+    sub "ఓ" "o"
+    sub "ఔ" "au"
+
+    # II. Abbreviated vowel characters and other symbols
+
+    sub "ా" "ā"
+    sub "ి" "i"
+    sub "ీ" "ī"
+    sub "ు" "u"
+    sub "ూ" "ū"
+    sub "ృ" "ṛ"
+    sub "ె" "ĕ"
+    sub "ే" "e"
+    sub "ై" "ai"
+    sub "ొ" "ŏ"
+    sub "ో" "o"
+    sub "ౌ" "au"
+    sub "ঁ" "ṁ"
+    sub "ఁ" "m̐"
+    sub "ః" "ḥ"
+    sub "ం" "ṃ"
+    sub "\u0c4d" ""
+
+    # III. Consonant characters
+
+    # Gutturals
+    sub "క" "ka"
+    sub "ఖ" "kha"
+    sub "గ" "ga"
+    sub "ఘ" "gha"
+    sub "ఙ" "ṅa"
+
+    # Palatals
+    sub "చ" "cha"
+    sub "ఛ" "chha"
+    sub "జ" "ja"
+    sub "ఝ" "jha"
+    sub "ఞ" "ña"
+
+    # Cerebrals
+    sub "ట" "ṭa"
+    sub "ఠ" "ṭha"
+    sub "డ" "ḍa"
+    sub "ఢ" "ḍha"
+    sub "ణ" "ṇa"
+
+    # Dentals
+    sub "త" "ta"
+    sub "థ" "tha"
+    sub "ద" "da"
+    sub "ధ" "dha"
+    sub "న" "na"
+
+    # Labials
+    sub "ప" "pa"
+    sub "ఫ" "pha"
+    sub "బ" "ba"
+    sub "భ" "bha"
+    sub "మ" "ma"
+
+    # Semivowels
+    sub "య" "ya"
+    sub "ర" "ra"
+    sub "ఱ" "ra"
+    sub "ల" "la"
+    sub "వ" "va"
+
+    # Sibilants
+    sub "శ" "sha"
+    sub "ష" "ṣha"
+    sub "స" "sa"
+
+    # Aspirate
+    sub "హ" "ha"
+    sub "ళ" "ḷa"
+
+    sub "\u09CD" ""
+    sub "ౕ\t" ""
+    sub "ౖ\t" ""
+    sub "्" ""
+    sub "़" ""
+    sub "‍" ""
+    sub "‌" ""
+
+    # numbers
+
+    sub "౦" "0"
+    sub "౧" "1"
+    sub "౨" "2"
+    sub "౩" "3"
+    sub "౪" "4"
+    sub "౫" "5"
+    sub "౬" "6"
+    sub "౭" "7"
+    sub "౮" "8"
+    sub "౯" "9"
+  }
+
+  compose
+}
+}

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

@@ -0,0 +1,66 @@
+system "UN:ukr-Cyrl:Latn:1998" {
+
+metadata {
+  authority_id un
+  id 1998
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Belarusian, Russian And Ukrainian Cyrillic (1998)
+  url https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
+  # page 320
+  creation_date 1998
+
+  notes {
+    note "Ge (ґ) was officially banned in the Soviet Ukraine from 1933 to 1990; https://en.wikipedia.org/wiki/Ukrainian_alphabet#ref_2b"
+  }
+}
+
+tests {
+  # generated manually
+   "ОЛЕКСАНДР ЯН" ->  "OLEKSANDR ÂN"
+   "ТРАНСЛІТЕРАЦІЇ" ->  "TRANSLÌTERACÌÌ"
+   "ПЕРЕВІРКА" ->  "PEREVÌRKA"
+   "ВСІ МАТЕРІАЛИ РОЗМІЩЕНІ НА УМОВАХ ЛІЦЕНЗІЇ" ->  "VSÌ MATERÌALI ROZMÌŠČENÌ NA UMOVAH LÌCENZÌÌ"
+   "ВВЕДІТЬ ПРІЗВИЩЕ ТА ІМ'Я УКРАЇНСЬКИМИ ЛІТЕРАМИ" ->  "VVEDÌT´ PRÌZVIŠČE TA ÌM'Â UKRAÌNS´KIMI LÌTERAMI"
+   "ДОДАТКОВА ІНФОРМАЦІЯ" ->  "DODATKOVA ÌNFORMACÌÂ"
+   "ДІЯЛЬНІСТЬ" ->  "DÌÂL´NÌST´"
+   "ЮЛІЯ" ->  "ÛLÌÂ"
+   "ЗГОРАНИ" ->  "ZGORANI"
+   "ЙОРКШИР-ТЕР'ЄР" ->  "JORKŠIR-TER'ÊR"
+   "ПАПА ПАЧУКА" ->  "PAPA PAČUKA"
+   "ЄНАКІЄВЕ" ->  "ÊNAKÌÊVE"
+   "УКРАЇНА" ->  "UKRAÌNA"
+   "КИЇВ" ->  "KIÌV"
+
+  # UN card tests
+   "Україна" ->  "Ukraı̀na"
+   "Київ" ->  "Kiı̀v"
+}
+
+dependency "gost-rus-Cyrl-Latn-16876-71-1983" as cyrllatn
+
+stage main {
+
+  run  map.cyrllatn.stage.main
+
+  # CHARACTERS
+  parallel {
+    sub "\u0401" none
+    sub "\u0404" "Ê"
+    sub "\u0406" "Ì"
+    sub "\u0407" "Ì"
+    sub "\u042B" none
+    sub "\u042D" none
+
+    sub "\u0451" none
+    sub "\u0454" "ê"
+    sub "\u0456" "ı̀"
+    sub "\u0457" "ı̀"
+    sub "\u044B" none
+    sub "\u044D" none
+  }
+
+  compose
+}
+}

data/maps/un-ukr-Cyrl-Latn-2012.isc

@@ -0,0 +1,98 @@
+system "UN:ukr-Cyrl:Latn:2012" {
+
+metadata {
+  authority_id un
+  id 2012
+  language iso-639-2:ukr
+  source_script Cyrl
+  destination_script Latn
+  name Romanization of Belarusian, Russian And Ukrainian Cyrillic (2012)
+  url http://www.eki.ee/wgrs/rom1_uk.htm
+  creation_date 2010
+}
+
+tests {
+   "Алушта" ->  "Alushta"
+   "Андрій" ->  "Andrii"
+   "Борщагівка" ->  "Borshchahivka"
+   "Борисенко" ->  "Borysenko"
+   "Вінниця" ->  "Vinnytsia"
+   "Володимир" ->  "Volodymyr"
+   "Гадяч" ->  "Hadiach"
+   "Богдан" ->  "Bohdan"
+   "Згурський" ->  "Zghurskyi"
+   "Ґалаґан" ->  "Galagan"
+   "Ґорґани" ->  "Gorgany"
+   "Донецьк" ->  "Donetsk"
+   "Дмитро" ->  "Dmytro"
+   "Рівне" ->  "Rivne"
+   "Олег" ->  "Oleh"
+   "Есмань" ->  "Esman"
+   "Єнакієве" ->  "Yenakiieve"
+   "Гаєвич" ->  "Haievych"
+   "Короп'є" ->  "Koropie"
+   "Житомир" ->  "Zhytomyr"
+   "Жанна" ->  "Zhanna"
+   "Жежелів" ->  "Zhezheliv"
+   "Закарпаття" ->  "Zakarpattia"
+   "Казимирчук" ->  "Kazymyrchuk"
+   "Медвин" ->  "Medvyn"
+   "Михайленко" ->  "Mykhailenko"
+   "Іванків" ->  "Ivankiv"
+   "Іващенко" ->  "Ivashchenko"
+   "Їжакевич" ->  "Yizhakevych"
+   "Кадиївка" ->  "Kadyivka"
+   "Мар'їне" ->  "Marine"
+   "Йосипівка" ->  "Yosypivka"
+   "Стрий" ->  "Stryi"
+   "Олексій" ->  "Oleksii"
+   "Київ" ->  "Kyiv"
+   "Коваленко" ->  "Kovalenko"
+   "Лебедин" ->  "Lebedyn"
+   "Леонід" ->  "Leonid"
+   "Миколаїв" ->  "Mykolaiv"
+   "Маринич" ->  "Marynych"
+   "Ніжин" ->  "Nizhyn"
+   "Наталія" ->  "Nataliia"
+   "Одеса" ->  "Odesa"
+   "Онищенко" ->  "Onyshchenko"
+   "Полтава" ->  "Poltava"
+   "Петро" ->  "Petro"
+   "Решетилівка" ->  "Reshetylivka"
+   "Рибчинський" ->  "Rybchynskyi"
+   "Суми" ->  "Sumy"
+   "Соломія" ->  "Solomiia"
+   "Тернопіль" ->  "Ternopil"
+   "Троць" ->  "Trots"
+   "Ужгород" ->  "Uzhhorod"
+   "Уляна" ->  "Uliana"
+   "Фастів" ->  "Fastiv"
+   "Філіпчук" ->  "Filipchuk"
+   "Харків" ->  "Kharkiv"
+   "Христина" ->  "Khrystyna"
+   "Біла Церква" ->  "Bila Tserkva"
+   "Стеценко" ->  "Stetsenko"
+   "Чернівці" ->  "Chernivtsi"
+   "Шевченко" ->  "Shevchenko"
+   "Шостка" ->  "Shostka"
+   "Кишеньки" ->  "Kyshenky"
+   "Щербухи" ->  "Shcherbukhy"
+   "Гоща" ->  "Hoshcha"
+   "Гаращенко" ->  "Harashchenko"
+   "Яготин" ->  "Yahotyn"
+   "Ярошенко" ->  "Yaroshenko"
+   "Костянтин" ->  "Kostiantyn"
+   "Знам'янка" ->  "Znamianka"
+   "Феодосія" ->  "Feodosiia"
+   "Згорани" ->  "Zghorany"
+   "Розгон" ->  "Rozghon"
+}
+
+dependency "ua-ukr-Cyrl-Latn-2010" as cyrllatn
+
+stage main {
+
+  run  map.cyrllatn.stage.main
+
+}
+}