interscript-maps 2.0.5

data/maps/un-tam-Taml-Latn-1972.imp

@@ -0,0 +1,173 @@
+metadata {
+  authority_id: un
+  id: 1972
+  language: iso-639-2:tam
+  source_script: Gujr
+  destination_script: Taml
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES --Tamil Romanization Version 4.0
+  url: https://www.eki.ee/wgrs/rom1_ta.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, Sri Lanka or in international cartographic products.
+
+    Tamil 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 on the whole reversible.
+
+  notes:
+
+    - |
+      ஜி Variation: டி ṭi.
+    - |
+      ஜீ Variation: டீ ṭī.
+    - |
+      ஜு Variations: கு ku, ஙு ṅu, சு chu, ஞு ñu, டு ṭu, ணு ṇu, து tu, நு nu, பு pu, மு mu, யு yu, ரு ru, லு lu, etc.
+    - |
+      ஜூ Variations: கூ kū, ஙூ ṅū, சூ chū, ஞூ ñū, டூ ṭū, ணூ ṇū, தூ tū, நூ nū, பூ pū, மூ mū, etc.
+    - |
+      ஃ Absent in the original table.
+    - |
+      ் Pronunciation without a vowel: க் k.
+    - |
+      ஜ, ஶ, ஸ, ன Characters borrowed from the Grantha script.
+    - |
+      ஸ Special syllable character: ஸ்ரீ srī.
+}
+
+tests {
+  test "அழிந்து போன நகரத்தில் , தொலைந்து போன நான்", "al̮intu poṉa nakarattil , tŏlaintu poṉa nāṉ"
+  test "முதன் முதலாக - மை ஃபர்ஸ்ட் சோலோ ட்ராவல்", "mutaṉ mutalāka - mai ḥparsṭ cholo ṭrāval"
+  test "வாழ்க்கையில் அவன் போன முதல் சோலோ டிரிப் அது தான்.", "vāl̮kkaiyil avaṉ poṉa mutal cholo ṭirip atu tāṉ."
+  test "ஸ்கூல் ப்ரெண்ட் கார்த்திக் வீட்டுக்கு போய்ட்டு", "skūl prĕṇṭ kārttik vīṭṭukku poyṭṭu"
+  test "நாசா வெளியிட்ட வெடிக்கும் நட்சத்திரத்தின் வீடியோ", "nāchā vĕḷiyiṭṭa vĕṭikkum naṭchattirattiṉ vīṭiyo"
+  test "டார்பிடோவை ஏவ உதவும் சூப்பர்சானிக் ஏவுகணையான ஸ்மார்ட் சோதனை வெற்றி", "ṭārpiṭovai eva utavum chūpparchāṉik evukaṇaiyāṉa smārṭ chotaṉai vĕṟṟi"
+  test "இந்த ஆண்டு மருத்துவத்துக்கான நோபல் பரிசு பெறுபவர்களின் பெயர்கள் அறிவிப்பு", "inta āṇṭu maruttuvattukkāṉa nopal parichu pĕṟupavarkaḷiṉ pĕyarkaḷ aṟivippu"
+  test "மல்லையா விவகாரம்: பிரிட்டன் அரசின் நடவடிக்கைகள் தங்களுக்கு தெரியவில்லை - மத்திய அரசு தகவல்", "mallaiyā vivakāram: piriṭṭaṉ arachiṉ naṭavaṭikkaikaḷ taṅkaḷukku tĕriyavillai - mattiya arachu takaval"
+  test "ஆலோசனைக்குப் பிறகு தேனியில் இருந்து சென்னை புறப்பட்டார் துணை முதலமைச்சர் பன்னீர்செல்வம்", "ālochaṉaikkup piṟaku teṉiyil iruntu chĕṉṉai puṟappaṭṭār tuṇai mutalamaichchar paṉṉīrchĕlvam"
+  test "இன்று தான் பேரன் பிறந்தநாள் முடிந்து ஃப்ரீ ஆகி இருக்கிறேன்", "iṉṟu tāṉ peraṉ piṟantanāḷ muṭintu ḥprī āki irukkiṟeṉ"
+}
+
+aliases {
+  def_alias taml_chars_1, any("\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u25cc\u0bcd")
+}
+
+stage {
+
+  # RULES
+  sub "க", "k", after: taml_chars_1
+  sub "ங", "ṅ", after: taml_chars_1
+  sub "ச", "ch", after: taml_chars_1
+  sub "ஞ", "ñ", after: taml_chars_1
+  sub "ட", "ṭ", after: taml_chars_1
+  sub "ண", "ṇ", after: taml_chars_1
+  sub "த", "t", after: taml_chars_1
+  sub "ந", "n", after: taml_chars_1
+  sub "ப", "p", after: taml_chars_1
+  sub "ம", "m", after: taml_chars_1
+  sub "ய", "y", after: taml_chars_1
+  sub "ர", "r", after: taml_chars_1
+  sub "ல", "l", after: taml_chars_1
+  sub "வ", "v", after: taml_chars_1
+  sub "ழ", "l̮", after: taml_chars_1
+  sub "ள", "ḷ", after: taml_chars_1
+  sub "ற", "ṟ", after: taml_chars_1
+  sub "ன", "ṉ", after: taml_chars_1
+  sub "ஜ", "j", after: taml_chars_1
+  sub "ஶ", "sh", after: taml_chars_1
+  sub "ஷ", "ṣh", after: taml_chars_1
+  sub "ஸ", "s", after: taml_chars_1
+  sub "ஹ", "h", after: taml_chars_1
+
+
+
+  # CHARACTERS
+  parallel {
+    sub "அ", "a"
+    sub "ஆ", "ā"
+    sub "ா", "ā"
+
+    sub "இ", "i"
+    sub "ி", "i"
+
+    sub "ஈ", "ī"
+    sub "ீ", "ī"
+
+    sub "உ", "u"
+    sub "ு", "u"
+
+    sub "ஊ", "ū"
+    sub "ூ", "ū"
+
+    sub "ெ", "ĕ"
+    sub "எ", "ĕ"
+
+    sub "ே", "e"
+    sub "ஏ", "e"
+
+    sub "ஐ", "ai"
+    sub "ை", "ai"
+
+    sub "ஒ", "ŏ"
+    sub "ொ", "ŏ"
+
+    sub "ோ", "o"
+    sub "ஓ", "o"
+
+    sub "ஔ", "au"
+    sub "ௌ", "au"
+
+    sub "ஃ", "ḥ"
+    sub "்", ""
+
+    sub "க", "ka"
+    sub "ங", "ṅa"
+    sub "ச", "cha"
+    sub "ஞ", "ña"
+    sub "ட", "ṭa"
+    sub "ண", "ṇa"
+    sub "த", "ta"
+    sub "ந", "na"
+    sub "ப", "pa"
+    sub "ம", "ma"
+    sub "ய", "ya"
+    sub "ர", "ra"
+    sub "ல", "la"
+    sub "வ", "va"
+    sub "ழ", "l̮a"
+    sub "ள", "ḷa"
+    sub "ற", "ṟa"
+    sub "ன", "ṉa"
+    sub "ஜ", "ja"
+    sub "ஶ", "sha"
+    sub "ஷ", "ṣha"
+    sub "ஸ", "sa"
+    sub "ஹ", "ha"
+    sub "க்ஷ", "kṣha"
+    sub "ற்ற", "ṟṟa"
+    sub "ன்ற", "ṉṟa"
+
+    # Digits
+    sub "௧", "1"
+    sub "௨", "2"
+    sub "௩", "3"
+    sub "௪", "4"
+    sub "௫", "5"
+    sub "௬", "6"
+    sub "௭", "7"
+    sub "௮", "8"
+    sub "௯", "9"
+    sub "௦", "0"
+    sub "௰", "10"
+    sub "௱", "100"
+    sub "௲", "1000"
+
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+  }
+
+  compose
+}

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

@@ -0,0 +1,229 @@
+metadata {
+  authority_id: un
+  id: 1972
+  language: iso-639-2:tel
+  source_script: Telu
+  destination_script: Latn
+  name: REPORT ON THE CURRENT STATUS OF UNITED NATIONS ROMANIZATION SYSTEMS FOR GEOGRAPHICAL NAMES -- Telugu Romanization, 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:
+
+    - |
+      Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+      vowels following a consonant can be found in grammars; no distinction between the two is
+      made in transliteration.
+    - |
+      The vowel a is implicit after all consonants and consonant clusters and is supplied in
+      transliteration, with the following exceptions:
+      a) when another vowel is indicated by its appropriate sign; and
+      b) when the absence of any vowel is indicated by the superscript sign ( ౬ ) called valapalagilaka.
+    - |
+      Exception: Sunna is transliterated by:
+      a) ṅ before gutturals,
+      b) ñ before palatals,
+      c) ṇ before cerebrals,
+      d) n before dentals, and
+      e) m before labials.
+    - |
+      Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
+      Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+      transliterated m
+}
+
+tests {
+  test "తమిళనాడు", "tamiḷanāḍu"
+  test "తంటికొండ ఘటన: ఆగని మృత్యుఘోష", "taṃṭikŏṃḍa ghaṭana: āgani mṛtyughoṣha"
+  test "మళ్లీ వివాదం: అమితాబ్‌పై కేసు", "maḷlī vivādaṃ: amitābpai kesu"
+  test "వరద సాయం పేరుతో వైట్ కాలర్ దోపిడీ", "varada sāyaṃ peruto vaiṭ kālar dopiḍī"
+  test "రెండో విడత జీఎస్టీ పరిహారం", "rĕṃḍo viḍata jīĕsṭī parihāraṃ"
+  test "నితీష్‌ కుమార్‌ అధ్యాయం ముగిసినట్లేనా?!", "nitīṣh kumār adhyāyaṃ mugisinaṭlenā?!"
+  test "వారిపై జీవితాంతం నిషేధం విధించండి!", "vāripai jīvitāṃtaṃ niṣhedhaṃ vidhiṃchaṃḍi!"
+  test "మరో లాక్‌డౌన్‌ వల్ల అన్నీ అనర్థాలే!", "maro lākḍaun valla annī anarthāle!"
+  test "జెసిండా మరో సంచలనం", "jĕsiṃḍā maro saṃchalanaṃ"
+  test "స్వీయ నిర్బంధంలోకి డబ్ల్యూహెచ్‌ఓ డైరెక్టర్‌", "svīya nirbaṃdhaṃloki ḍablyūhĕcho ḍairĕkṭar"
+  test "కరోనాపై యుద్ధంలో సమిధలు", "karonāpai yuddhaṃlo samidhalu"
+  test "అమెరికా ఎన్నికలు: ‘పెద్దన్న’ ఎవరో?!", "amĕrikā ĕnnikalu: ‘pĕddanna’ ĕvaro?!"
+  test "౪౬౨౬౯", "46269"
+  test "రంగపూర్", "raṃgapūr"
+  # subscript consonant characters
+  test "ట్ట", "ṭṭa"
+  test "ప్ప", "ppa"
+  test "చ్చ", "chcha"
+}
+
+aliases {
+  def_alias telu_chars_1, any("\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c\u0c4d")
+}
+
+stage {
+
+  # RULES
+  sub "క", "k", after: telu_chars_1
+  sub "ఖ", "kh", after: telu_chars_1
+  sub "గ", "g", after: telu_chars_1
+  sub "ఘ", "gh", after: telu_chars_1
+  sub "ఙ", "ṅ", after: telu_chars_1
+  sub "చ", "ch", after: telu_chars_1
+  sub "ఛ", "chh", after: telu_chars_1
+  sub "జ", "j", after: telu_chars_1
+  sub "ఝ", "jh", after: telu_chars_1
+  sub "ఞ", "ñ", after: telu_chars_1
+  sub "ట", "ṭ", after: telu_chars_1
+  sub "ఠ", "ṭh", after: telu_chars_1
+  sub "డ", "ḍ", after: telu_chars_1
+  sub "ఢ", "ḍh", after: telu_chars_1
+  sub "ణ", "ṇ", after: telu_chars_1
+  sub "త", "t", after: telu_chars_1
+  sub "థ", "th", after: telu_chars_1
+  sub "ద", "d", after: telu_chars_1
+  sub "ధ", "dh", after: telu_chars_1
+  sub "న", "n", after: telu_chars_1
+  sub "ప", "p", after: telu_chars_1
+  sub "ఫ", "ph", after: telu_chars_1
+  sub "బ", "b", after: telu_chars_1
+  sub "భ", "bh", after: telu_chars_1
+  sub "మ", "m", after: telu_chars_1
+  sub "య", "y", after: telu_chars_1
+  sub "ర", "r", after: telu_chars_1
+  sub "ఱ", "r", after: telu_chars_1
+  sub "ల", "l", after: telu_chars_1
+  sub "వ", "v", after: telu_chars_1
+  sub "శ", "sh", after: telu_chars_1
+  sub "ష", "ṣh", after: telu_chars_1
+  sub "స", "s", after: telu_chars_1
+  sub "హ", "h", after: telu_chars_1
+  sub "ళ", "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" # Variations: చి chi, ని ni, యి yi, లి li, etc.
+    sub "ీ", "ī"
+    sub "ు", "u" # Variations: జు ju, పు pu, వు vu, etc.
+    sub "ూ", "ū"
+    sub "ృ", "ṛ"
+    sub "ె", "ĕ"
+    sub "ే", "e"
+    sub "ై", "ai"
+    sub "ొ", "ŏ" # Variations: మొ mŏ, యొ yŏ.
+    sub "ో", "o" # Variations: మో mo, యో yo.
+    sub "ౌ", "au"
+    sub "ঁ", "ṁ"
+    sub "ఁ", "m̐" # Signified historic nasal sound, now obsolete.
+    sub "ః", "ḥ"
+    sub "ం", "ṃ"
+    sub "\u0c4d", "" # End-of-syllable mark (i.e., a consonant without a vowel): రంగపూర్ Raṁgapūr.
+
+    # 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" #Variant: ఱ.
+    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", "" # Used for joining
+    sub "ౕ\t", ""
+    sub "ౖ\t", ""
+    sub "्", ""
+    sub "़", ""
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+
+    # 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.imp

@@ -0,0 +1,58 @@
+metadata {
+  authority_id: un
+  id: 1998
+  language: iso-639-2: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
+  # page 320
+  creation_date: 1998
+
+  notes:
+    - 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
+  test "ОЛЕКСАНДР ЯН", "OLEKSANDR ÂN"
+  test "ТРАНСЛІТЕРАЦІЇ", "TRANSLÌTERACÌÌ"
+  test "ПЕРЕВІРКА", "PEREVÌRKA"
+  test "ВСІ МАТЕРІАЛИ РОЗМІЩЕНІ НА УМОВАХ ЛІЦЕНЗІЇ", "VSÌ MATERÌALI ROZMÌŠČENÌ NA UMOVAH LÌCENZÌÌ"
+  test "ВВЕДІТЬ ПРІЗВИЩЕ ТА ІМ'Я УКРАЇНСЬКИМИ ЛІТЕРАМИ", "VVEDÌT´ PRÌZVIŠČE TA ÌM'Â UKRAÌNS´KIMI LÌTERAMI"
+  test "ДОДАТКОВА ІНФОРМАЦІЯ", "DODATKOVA ÌNFORMACÌÂ"
+  test "ДІЯЛЬНІСТЬ", "DÌÂL´NÌST´"
+  test "ЮЛІЯ", "ÛLÌÂ"
+  test "ЗГОРАНИ", "ZGORANI"
+  test "ЙОРКШИР-ТЕР'ЄР", "JORKŠIR-TER'ÊR"
+  test "ПАПА ПАЧУКА", "PAPA PAČUKA"
+  test "ЄНАКІЄВЕ", "ÊNAKÌÊVE"
+  test "УКРАЇНА", "UKRAÌNA"
+  test "КИЇВ", "KIÌV"
+}
+
+dependency "gost-rus-Cyrl-Latn-16876-71-1983", as: cyrllatn
+
+stage {
+
+  run map.cyrllatn.stage.main
+
+  # CHARACTERS
+  parallel {
+    sub "\u0401", none # Ё
+    sub "\u0404", "Ê" # Є => Ê
+    sub "\u0406", "Ì" # І => Ì
+    sub "\u0407", "Ì" # Ї => Ì
+    sub "\u042B", none # Ы
+    sub "\u042D", none # Э
+
+    sub "\u0451", none # ё
+    sub "\u0454", "ê" # є => ê
+    sub "\u0456", "ı̀" # і => ì
+    sub "\u0457", "ı̀" # ї => ì
+    sub "\u044B", none # ы
+    sub "\u044D", none # э
+  }
+
+  compose
+}