interscript-maps 2.4.2 → 2.5.0

data/maps/un-mal-Mlym-Latn-1972.imp

@@ -1,215 +0,0 @@
-metadata {
-  authority_id: un
-  id: 1972
-  language: iso-639-2:mal
-  source_script: Mlym
-  destination_script: Latn
-  name: Romanization of Malayalam -- UNGEGN 4.0
-  url: https://www.eki.ee/wgrs/rom1_ml.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.
-
-    Malayalam (Malayāḷam) 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 but now
-    outdated because since the 1970's a new orthography has been introduced and the use of many character
-    combinations and ligatures has been simplified. Nevertheless the user of the romanization table would have to
-    recognize many ligatures not given in the original table. The system is mostly reversible but there exist some
-    ambiguities in the romanization of vowels (independent vs. abbreviated characters) and
-    consonants (ligatures vs. character sequences), particularly in the case of older orthography.
-
-
-  notes:
-    - |
-      ടു For traditional script forms ഖു khu, മു mu, etc., exceptionally കു ku (ക്കു kku, ങ്കു ṅku), ഗു gu, ഛു chhu, ജു ju, ണു ṇu, തു tu, നു nu (ന്നു nnu), ഭു bhu, രു ru, ശു shu, ഹു hu
-    - |
-      ടൂ For traditional script forms ഖൂ khū, മൂ mū, etc., exceptionally കൂ kū, ഗൂ gū, ഛൂ chhū, ജൂ jū, ണൂ ṇū, തൂ tū, നൂ nū, ഭൂ bhū, രൂ rū, ശൂ shū, ഹൂ hū
-    - |
-      ടൃ Traditionally written in conjunction with the consonant character: കൃ kṛ .
-    - |
-      ടൗ In the older spelling: ൌ.
-    - |
-      ട്‌  Indicates absence of the inherent short [a] vowel, e.g. ക്‌ k , സ്‌ s. Special, co-called chillu-forms of consonants with that symbol: ണ്‍ ṇ, ന്‍ n, ര്‍ r, ല്‍ l, ള്‍ ḷ.
-    - |
-      റ  Special ligature: റ്റ ṭ̈.
-}
-
-tests {
-  test "ചൈനയ്ക്കെതിരെ ലഡാക്കിൽ സദാസജ്ജം; യുഎസിൽനിന്ന് ൭൨,൫൦൦ സിഗ്–൧൬ റൈഫിൾ", "chainaykkĕtirĕ laḍākkil sadāsajjaṃ; yuĕsilninn 72,500 sig–16 ṟaiphiḷ"
-  test "സർഗഭൂമിക’യ്ക്കില്ല; ലളിതച്ചേച്ചി അങ്ങനെ പറഞ്ഞിട്ടുണ്ടാവില്ല: ആർഎൽവി രാമകൃഷ്ണൻ", "sargabhūmika’ykkilla; laḷitachchechchi aṅṅanĕ paṟaññiṭṭuṇṭāvilla: ārĕlvi rāmakṛṣhṇan"
-  test "സ്വർണക്കടത്ത്‌: ഫൈസൽ ഫരീദും റബിന്‍സും ദുബായിൽ അറസ്റ്റിലായെന്ന്‌ എന്‍ഐഎ", "svarṇakkaṭatt: phaisal pharīduṃ ṟabinsuṃ dubāyil aṟasṟṟilāyĕnn ĕnaiĕ"
-  test "വരുമോ ചൈനയുടെ വാക്സീൻ?; ആഗോള ഉപയോഗത്തിന് ഡബ്ല്യുഎച്ച്ഒയുമായി ചർച്ച", "varumo chainayuṭĕ vāksīn?; āgoḷa upayogattin ḍablyuĕchchŏyumāyi charchcha"
-  test "കുട്ടികളുടെ മാനസിക പിരിമുറുക്കം മാറ്റാൻ പരിശീലനം; ക്ലാസുമായി പോക്സോ പ്രതി", "kuṭṭikaḷuṭĕ mānasika pirimuṟukkaṃ māṟṟān parishīlanaṃ; klāsumāyi pokso prati"
-  test "ആദ്യം അമിത് ഷാ, ഇപ്പോൾ മോദി; ബിജെപിയെ പുണരാൻ ജഗൻ; ആന്ധ്രയിലെ കരുനീക്കങ്ങൾ", "ādyaṃ amit ṣhā, ippoḷ modi; bijĕpiyĕ puṇarān jagan; āndhrayilĕ karunīkkaṅṅaḷ"
-  test "ലഹരിമരുന്ന് കേസ്: ബിനീഷ് കോടിയേരിയെ ഇഡി 6 മണിക്കൂർ ചോദ്യം ചെയ്തു", "laharimarunn kes: binīṣh koṭiyeriyĕ iḍi 6 maṇikkūr chodyaṃ chĕytu"
-  test "ഈന്തപ്പഴം വിതരണം ചെയ്തത് ശിവശങ്കര്‍ പറഞ്ഞതു പ്രകാരം: ടി.വി അനുപമയുടെ മൊഴി", "īntappaḻaṃ vitaraṇaṃ chĕytat shivashaṅkar paṟaññatu prakāraṃ: ṭi.vi anupamayuṭĕ mŏḻi"
-  test "൫൦൦൦ മണിക്കൂർ കാത്തിരിക്കാൻ തയാറെന്ന് രാഹുൽ: ഒടുവിൽ വഴങ്ങി ഹരിയാന", "5000 maṇikkūr kāttirikkān tayāṟĕnn rāhul: ŏṭuvil vaḻaṅṅi hariyāna"
-  test "കാരണം ഷോര്‍ട്ട്‌സര്‍ക്യൂട്ടല്ല; കത്തിയത് ഫയല്‍ മാത്രം, സാനിറ്റൈസര്‍ ഉള്‍പ്പെടെ കത്തിയില്ല", "kāraṇaṃ ṣhorṭṭsarkyūṭṭalla; kattiyat phayal mātraṃ, sāniṟṟaisar uḷppĕṭĕ kattiyilla"
-  test "വിമൺ സയൻറിസ്റ്റ്സ് സ്കീം", "vimaṇ sayanṟisṟṟs skīṃ"
-}
-
-aliases {
-  def_alias mlym_chars_1, any("\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d43\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0d4d")
-}
-
-stage {
-
-  # RULES
-  sub "ക", "k", after: mlym_chars_1
-  sub "ഖ", "kh", after: mlym_chars_1
-  sub "ഗ", "g", after: mlym_chars_1
-  sub "ഘ", "gh", after: mlym_chars_1
-  sub "ങ", "ṅ", after: mlym_chars_1
-  sub "ച", "ch", after: mlym_chars_1
-  sub "ഛ", "chh", after: mlym_chars_1
-  sub "ജ", "j", after: mlym_chars_1
-  sub "ഝ", "jh", after: mlym_chars_1
-  sub "ഞ", "ñ", after: mlym_chars_1
-  sub "ട", "ṭ", after: mlym_chars_1
-  sub "ഠ", "ṭh", after: mlym_chars_1
-  sub "ഡ", "ḍ", after: mlym_chars_1
-  sub "ഢ", "ḍh", after: mlym_chars_1
-  sub "ണ", "ṇ", after: mlym_chars_1
-  sub "ത", "t", after: mlym_chars_1
-  sub "ഥ", "th", after: mlym_chars_1
-  sub "ദ", "d", after: mlym_chars_1
-  sub "ധ", "dh", after: mlym_chars_1
-  sub "ന", "n", after: mlym_chars_1
-  sub "പ", "p", after: mlym_chars_1
-  sub "ഫ", "ph", after: mlym_chars_1
-  sub "ബ", "b", after: mlym_chars_1
-  sub "ഭ", "bh", after: mlym_chars_1
-  sub "മ", "m", after: mlym_chars_1
-  sub "യ", "y", after: mlym_chars_1
-  sub "ര", "r", after: mlym_chars_1
-  sub "ല", "l", after: mlym_chars_1
-  sub "വ", "v", after: mlym_chars_1
-  sub "ശ", "sh", after: mlym_chars_1
-  sub "ഷ", "ṣh", after: mlym_chars_1
-  sub "സ", "s", after: mlym_chars_1
-  sub "ഹ", "h", after: mlym_chars_1
-  sub "ള", "ḷ", after: mlym_chars_1
-  sub "ഴ", "ḻ", after: mlym_chars_1
-  sub "റ", "ṟ", after: mlym_chars_1
-  sub "ക്ഷ", "kṣh", after: mlym_chars_1
-
-
-  # CHARACTERS
-  parallel {
-    # I. Independent vowel characters
-    sub "അ", "a"
-    sub "ആ", "ā"
-    sub "ഇ", "i"
-    sub "ഈ", "ī"
-    sub "ഉ", "u"
-    sub "ഊ", "ū"
-    sub "ഋ", "ṛ"
-    sub "എ", "ĕ"
-    sub "ഏ", "e"
-    sub "ഐ", "ai"
-    sub "ഒ", "ŏ"
-    sub "ഓ", "o"
-    sub "ഔ", "au"
-
-    # II. Abbreviated vowel characters
-    sub "ാ", "ā"
-    sub "ി", "i"
-    sub "ീ", "ī"
-    sub "ു", "u"
-    sub "ൂ", "ū"
-    sub "ൃ", "ṛ"
-    sub "െ", "ĕ"
-    sub "േ", "e"
-    sub "ൈ", "ai"
-    sub "ൊ", "ŏ"
-    sub "ോ", "o"
-    sub "ൌ", "au"
-
-    #III. Other symbols
-    sub "ഃ", "ḥ"
-    sub "ം", "ṃ"
-    sub "്", ""
-
-    #IV. Consonant characters
-    sub "ക", "ka"
-    sub "ഖ", "kha"
-    sub "ഗ", "ga"
-    sub "ഘ", "gha"
-    sub "ങ", "ṅa"
-    sub "ച", "cha"
-    sub "ഛ", "chha"
-    sub "ജ", "ja"
-    sub "ഝ", "jha"
-    sub "ഞ", "ña"
-    sub "ട", "ṭa"
-    sub "ഠ", "ṭha"
-    sub "ഡ", "ḍa"
-    sub "ഢ", "ḍha"
-    sub "ണ", "ṇa"
-    sub "ത", "ta"
-    sub "ഥ", "tha"
-    sub "ദ", "da"
-    sub "ധ", "dha"
-    sub "ന", "na"
-    sub "പ", "pa"
-    sub "ഫ", "pha"
-    sub "ബ", "ba"
-    sub "ഭ", "bha"
-    sub "മ", "ma"
-    sub "യ", "ya"
-    sub "ര", "ra"
-    sub "ല", "la"
-    sub "വ", "va"
-    sub "ശ", "sha"
-    sub "ഷ", "ṣha"
-    sub "സ", "sa"
-    sub "ഹ", "ha"
-    sub "ക്ഷ", "kṣha"
-    sub "ള", "ḷa"
-    sub "ഴ", "ḻa"
-    sub "റ", "ṟa"
-    sub "റ്റ", "ṭ̈"
-
-
-    sub "्", ""
-    sub "़", ""
-    sub "ൗ", ""
-    sub "‍", "" # no need for zero with joiner
-    sub "‌", "" # no need for zero with non joiner
-
-
-    # numbers
-    sub "൦", "0"
-    sub "൧", "1"
-    sub "൨", "2"
-    sub "൩", "3"
-    sub "൪", "4"
-    sub "൫", "5"
-    sub "൬", "6"
-    sub "൭", "7"
-    sub "൮", "8"
-    sub "൯", "9"
-    sub "൰", "10"
-    sub "൱", "100"
-    sub "൲", "1000"
-
-
-    # chillu-forms of consonants note 5
-    sub "ൿ", "k"
-    sub "ൺ", "ṇ"
-    sub "ൻ", "n"
-    sub "ൽ", "l"
-    sub "ൾ", "ḷ"
-    sub "ർ", "r"
-    sub "സ്", "s"
-  }
-
-
-  compose
-}

data/maps/un-mar-Deva-Latn-2016.imp

@@ -1,96 +0,0 @@
-metadata {
-  authority_id: un
-  id: 2016
-  language: iso-639-2:mar
-  source_script: Deva
-  destination_script: Latn
-  name: Romanization of Marathi -- UNGEGN 4.0
-  url: https://www.eki.ee/wgrs/rom1_mr.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.
-
-    Marathi (Marāṭhī) uses the alphasyllabic script Devanāgarī.
-
-  notes:
-    - |
-       Additional characters (absent in Hindi):
-       ळ ḷa
-       ऍ ă (abbreviated: कॅ kă)
-
-    - |
-      Ligatures may be formed with r as the first component: 'ऱ्य': 'rya' 'ऱ्ह': 'rha'
-    - |
-      Typical are ligatures ending in h: न्ह nh, म्ह mh, ल्ह lh, व्ह vh.
-    - |
-      The following independent characters are sometimes used: अि i, अी ī, अु u, अू ū, अे e, अै ai.
-
-    ######################################## Additional Note ############################################################
-    #    It is recommended that the vowel अ (a) should always be romanized except when it ends a                        #
-    #    name. In the scheme we are not yet able to detect a name. Analysing language pattern and the example           #
-    #    we found that actually when a word ends with a consonant it should be transliterated without the vowel in it.  #
-    #    so we are applying this rule as if a word ends with a consonant, in this case we are removing the ending 'a'.  #
-    #####################################################################################################################
-}
-
-tests {
-  test "महाराष्ट्र", "mahārāṣhṭr"
-  test "मुंबई", "muṁbaī"
-  test "परिपक्क", "paripakk"
-  test "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद", "ṭhāṇe - jilhyāt budhavārī ek hajār rugṇāṁchī vāḍh, tar jaṇāṁchyā mṛtyūchī noṁd"
-  test "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक", "ekatā kapūr punhā aḍakalī vādāt, vebasīrijamadhalyā 'tyā' sīnamuḷae jamāvāchī gharāvar dagaḍaphek"
-  test "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं", "jāṇūn ghyā, bīemasīchyā adhikāryāṁnī kaṁganā rāṇautachyā ôphisamadhale nakkī kāy- kāy toḍalaṁ"
-  test "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश", "kaṁganā muṁbaīt dākhal hoṇyāpūrvī 'mātoshrī'varūn pharmān suṭale; pravaktyāṁnā sakt ādesh"
-  test "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय", "marāṭhā ārakṣhaṇās tātpuratī sthagitī; sarvochch nyāyālayāchā nirṇay"
-  test "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात", "bhāratāchyā tinhī lashīṁchā pahilā ṭappā yashasvī, vāchā kadhī yeṇār bājārāt"
-  test "रुग्णवाढीमुळे खाटांची चणचण", "rugṇavāḍhīmuḷae khāṭāṁchī chaṇachaṇ"
-  test "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद", "pīem svanidhī karj yojanelā muṁbaītūn alp pratisād"
-  test "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती", "sāṁtākrūjh-cheṁbūr liṁk roḍavarīl unnat mārgālā sthagitī"
-  test "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार", "saṁpādak arṇab gosvāmī yāṁchyāvirūddh khaḍak polis ṭhāṇyāt takrār"
-  test "करणाऱ्या मुलांना अनुक्रमे प्ले ग्रूप", "karaṇāryā mulāṁnā anukrame ple grūp"
-  test "राज्यातील शाळा दिवाळीपर्यंत बंद, मंत्र्यांच्या बैठकीत निर्णय, शिक्षकांची जबाबदारी वाढली", "rājyātīl shāḷaā divāḷaīparyaṁt baṁd, maṁtryāṁchyā baiṭhakīt nirṇay, shikṣhakāṁchī jabābadārī vāḍhalī"
-}
-
-
-dependency "un-hin-Deva-Latn-2016", as: devalatn
-
-
-stage {
-
-  run map.devalatn.stage.main
-
-  # RULES
-  # note[3]
-  sub some("\U") + "0939", "h", before: "", after: boundary
-
-
-  # CHARACTERS
-  parallel {
-
-    # Note 1
-    sub "ळ", "ḷa"
-    sub "ऍ", "ă"
-
-    # Note 2
-    sub "ऱ", "r" # used for making Ligatures  'ऱ्य': 'rya'  'ऱ्ह': 'rha'
-
-    # Note 4
-    sub "अि", "i"
-    sub "अी", "ī"
-    sub "अु", "u"
-    sub "अू", "ū"
-    sub "अे", "e"
-    sub "अै", "ai"
-
-    sub "ॲ", "ê"
-    sub "ऑ", "ô"
-  }
-  compose
-}
-

data/maps/un-mkd-Cyrl-Latn-1977.imp

@@ -1,119 +0,0 @@
-metadata {
-  authority_id: un
-  id: 1977
-  language: iso-639-2:mkd
-  source_script: Cyrl
-  destination_script: Latn
-  name: Romanization of Macedonian geographical names (1977)
-  url: https://www.eki.ee/wgrs/v2_2/rom1_mk.htm
-  creation_date: 1977
-  description: |
-    The United Nations recommended system was approved in 1977 (III/11), based on the romanization of the Serbo-Croatian and Macedonian Cyrillic alphabets that had long been employed in official gazetteers and maps of Yugoslavia. The table was published as an annex to the resolution (Third United Nations Conference on the Standardization of Geographical Names. Athens, 17 August - 7 September 1977. Vol. I. Report of the Conference, pp. 29, 31).
-    The system is used in The former Yugoslav Republic of Macedonia (see e.g. Report of The former Yugoslav Republic of Macedonia. Seventh United Nations Conference on the Standardization of Geographical Names. New York, 13-22 January 1998. Document E/CONF.91/CRP.23) and in international cartographic products.
-    The Cyrillic alphabet is used. The romanization table is unambiguous and can be applied automatically. The system is on the whole reversible with the exception of the characters ѓ and ќ. These are romanized as g and k, respectively, before е and и. But also г and к are occasionally used before е and и, so, for example, the name Makedonija is reconstituted as Македонија, not Маќедонија in the Cyrillic source script.
-}
-
-tests {
-  test "Маќедонија", "Makedonija"
-  test "Општина Ердут", "Opština Erdut"
-  test "Општина Двор", "Opština Dvor"
-  test "ЛУЃЕ луѓе", "LUGE luge"
-  test "ЅВЕЗДА ѕвезда Ѕвезда", "DZVEZDA dzvezda Dzvezda"
-  test "ЌАРУВАЊЕ ќарување", "ĆARUVANJE ćaruvanje"
-}
-
-dependency "posix", import: true
-
-stage {
-  sub "Ѓ", "G", after: any("ЕИеи")
-  sub "ѓ", "g", after: any("ЕИеи")
-  sub "Ќ", "K", after: any("ЕИеи")
-  sub "ќ", "k", after: any("ЕИеи")
-
-  # CHARACTERS
-  parallel {
-    sub "А", "A"
-    sub "Б", "B"
-    sub "В", "V"
-    sub "Г", "G"
-    sub "Д", "D"
-    sub "Ѓ", "Đ" # Đ
-    sub "Е", "E"
-    sub "Ж", "Ž" # Ž
-    sub "З", "Z"
-    sub "Ѕ", "Dz"
-    sub "И", "I"
-    sub "Ј", "J"
-    sub "К", "K"
-    sub "Л", "L"
-    sub "Љ", "Lj"
-    sub "М", "M"
-    sub "Н", "N"
-    sub "Њ", "Nj"
-    sub "О", "O"
-    sub "П", "P"
-    sub "Р", "R"
-    sub "С", "S"
-    sub "Т", "T"
-    sub "Ќ", "Ć" # Ć
-    sub "У", "U"
-    sub "Ф", "F"
-    sub "Х", "H"
-    sub "Ц", "C"
-    sub "Ч", "Č" # Č
-    sub "Џ", "Dž" # Dž
-    sub "Ш", "Š" # Š
-    sub "а", "a"
-    sub "б", "b"
-    sub "в", "v"
-    sub "г", "g"
-    sub "д", "d"
-    sub "ѓ", "đ" # đ
-    sub "е", "e"
-    sub "ж", "ž" # ž
-    sub "з", "z"
-    sub "ѕ", "dz"
-    sub "и", "i"
-    sub "ј", "j"
-    sub "к", "k"
-    sub "л", "l"
-    sub "љ", "lj"
-    sub "м", "m"
-    sub "н", "n"
-    sub "њ", "nj"
-    sub "о", "o"
-    sub "п", "p"
-    sub "р", "r"
-    sub "с", "s"
-    sub "т", "t"
-    sub "ќ", "ć" # ć
-    sub "у", "u"
-    sub "ф", "f"
-    sub "х", "h"
-    sub "ц", "c"
-    sub "ч", "č" # č
-    sub "џ", "dž" # dž
-    sub "ш", "š" # š
-  }
-
-  # POSTRULES
-  # rewritten by hand to work properly
-  # DZ
-  sub capture(maybe(upper)) + "Dz" + capture(upper), ref(1) + "DZ" + ref(2)
-  sub capture(upper) + "Dz" +  capture(maybe(upper)), ref(1) + "DZ" + ref(2)
-
-  #LJ
-  sub capture(upper) + "Lj" + capture(maybe(upper)), ref(1) + "LJ" + ref(2)
-  sub capture(maybe(upper)) + "Lj" + capture(upper), ref(1) + "LJ" + ref(2)
-
-  #NJ
-  sub capture(upper) + "Nj" + capture(maybe(upper)), ref(1) + "NJ" + ref(2)
-  sub capture(maybe(upper)) + "Nj" + capture(upper), ref(1) + "NJ" + ref(2)
-
-  #DŽ
-  sub capture(upper) + "Dž" + capture(maybe(upper)), ref(1) + "DŽ" + ref(2)
-  sub capture(maybe(upper)) + "Dž" + capture(upper), ref(1) + "DŽ" + ref(2)
-
-  compose
-}
-

data/maps/un-mon-Mong-Latn-general-2013.imp

@@ -1,170 +0,0 @@
-metadata {
-  authority_id: un
-  id: general-2013
-  language: iso-639-2:mon
-  source_script: Mong
-  destination_script: Latn
-  name: Romanization of Mongolian in China -- UNGEGN 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, 1982.
-
-    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.
-
-  implementation_notes:
-    - A separated final form of vowels a or e is common, and can appear at the end
-      of a word, word stem, or suffix. This form requires a final-shaped preceding
-      consonant and an inter-word gap in between. The vowels themselves appear as ᠎ᠠ,
-      and with consonants as ‍ᠬ᠎ᠠ q‑a, ‍ᠷ᠎ᠠ r‑a/r‑e, etc. This gap can be transliterated
-      with a hyphen. In digital typesetting, these forms are triggered by inserting
-      a U+180E ᠎ MONGOLIAN VOWEL SEPARATOR (HTML ᠎ · MVS) between the consonant
-      and vowel.
-    - All case suffixes, as well as any plural suffixes consisting of one or two
-      syllables are likewise separated by a preceding and hyphen-transliterated gap.
-      In digital typesetting, this gap is represented by a U+202F   NARROW NO-BREAK SPACE
-      (HTML   · NNBSP). A maximum of two case suffixes can be added to a stem.
-      Single-letter vowel suffixes appear with the final-shaped forms of a/e, i, or u/ü,
-      as in ᠭᠠᠵᠠᠷ ᠠ γaǰar‑a 'to the country' and ᠡᠳᠦᠷ ᠡ edür‑e 'on the day', or ᠤᠯᠤᠰ ᠢ ulus‑i
-      'the state' etc. Multi-letter suffixes most often start with an initial- (consonants),
-      medial- (vowels), or variant-shaped form.
-}
-
-tests {
-  test "ᠣᠷᠳᠣᠰ ᠬᠣᠲᠠ", "ordos hota" # Ордос хот
-  test "ᠪᠠᠶᠠᠨᠨᠠᠭᠤᠷ ᠬᠣᠲᠠ", "bayannagur hota" # Баяннуур хот
-  test "ᠤᠯᠠᠭᠠᠨᠬᠣᠲᠠ", "ulaganhota" # Улаан хот
-  test "ᠬᠣᠣᠯᠢᠠ ᠭᠣᠤᠯ ᠬᠣᠲᠠ", "hoolia goul hota" # Хоолингол хот
-  test "ᠡᠷᠢᠶᠡᠨ ᠬᠣᠲᠠ", "eriyen hota" #  Эрээн хот
-  test "ᠷᠠᠰᠢᠶᠠᠨ ᠬᠣᠲᠠ", "rasiyan hota" # Рашаан хот
-  test "ᠪᠠᠭᠠᠷᠢᠨ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ", "bagarin baragun hosigu" # Баарин баруун хошуу
-  test "ᠪᠠᠭᠠᠷᠢᠨ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ", "bagarin jegun hosigu" # Баарин зүүн хошуу
-  test "ᠲᠦᠩᠯᠢᠶᠣᠤ ᠬᠣᠲᠠ", "tungliyou hota" # Байшинт хот
-  test "ᠰᠢᠯᠢ ᠶᠢᠨ ᠬᠣᠲᠠ", "sili-yin hota" # Шилийн хот
-  test "ᠬᠣᠷᠢᠨ ᠭᠡᠷ ᠰᠢᠶᠠᠨ", "horin ger siyan" # Horinger County
-  test "ᠤᠳᠠ ᠲᠣᠭᠣᠷᠢᠭ", "uda togorig" # Уда тойрог
-  test "ᠦᠬᠠᠢ ᠬᠣᠲᠠ", "uhai hota" # Үхай хот
-  test "ᠬᠠᠶᠢᠨᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "hayinan togorig" # Hainan District
-  test "ᠬᠠᠶᠢᠷᠤᠪ ᠤᠨ ᠲᠣᠬᠣᠢ ᠲᠣᠭᠣᠷᠢᠭ", "hayirub-un tohoi togorig" # Haibowan District
-  test "ᠤᠯᠠᠭᠠᠨᠴᠠᠪ ᠬᠣᠲᠠ", "ulaganqab hota" # Улаанцав хот
-  test "ᠵᠢᠨᠢᠩ ᠲᠣᠭᠣᠷᠢᠭ", "jining togorig" # Жинин тойрог
-  test "ᠹᠸᠩᠵᠸᠡ ᠬᠣᠲᠠ", "fwngjwe hota" # Фенжень хот
-  test "ᠵᠦᠸᠧᠽᠢ ᠰᠢᠶᠠᠨ", "juwezi siyan" # Zhuozi County
-  test "ᠬᠤᠸᠠᠳᠧ ᠰᠢᠶᠠᠨ", "huwade siyan" # Huade County
-  test "ᠱᠠᠩᠳᠤ ᠰᠢᠶᠠᠨ", "xangdu siyan" # Шанду шянь
-  test "ᠰᠢᠩᠾᠧ ᠰᠢᠶᠠᠨ", "singhe siyan" # Шинхэ шянь
-  test "ᠯᠢᠶᠠᠩᠴᠠᠩ ᠰᠢᠶᠠᠨ", "liyangqang siyan" # Liangcheng County
-  test "ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ", "qahar baragun garun emunedu hosigu" # Цахар баруун гарын өмнөд хошуу
-  test "ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ", "qahar baragun garun dumdadu hosigu" # Цахар баруун гарын дундад хошуу
-  test "ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ", "qahar baragun garun hoyitu hosigu" # Цахар баруун гарын хойд хошуу
-  test "ᠳᠥᠷᠪᠡᠳ ᠬᠣᠰᠢᠭᠤ", "dorbed hosigu" # Дөрвөд хошуу
-  test "ᠪᠤᠭᠤᠲᠤ ᠬᠣᠲᠠ", "bugutu hota" # Бугaт хот
-  test "ᠬᠥᠨᠳᠡᠯᠡᠨ ᠲᠣᠭᠣᠷᠢᠭ", "hondelen togorig" # Hondlon District
-  test "ᠳᠦᠩᠾᠧ ᠲᠣᠭᠣᠷᠢᠭ", "dunghe togorig" # Donghe District
-  test "ᠴᠢᠩᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "qingxan togorig" # Qingshan District
-  test "ᠰᠢᠭᠤᠶᠢᠲᠤ ᠲᠣᠭᠣᠷᠢᠭ", "siguyitu togorig" # Шигуай тойрог
-  test "ᠵᠢᠦ ᠶᠤᠸᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "jiu yuwan togorig" # Jiuyuan District
-  test "ᠭᠦᠶᠠᠩ ᠰᠢᠶᠠᠨ", "guyang siyan" # Guyang County
-  test "ᠲᠦᠮᠡᠳ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ", "tumed jegun hosigu" # Түмэд Зүүн хошуу
-  test "ᠲᠦᠮᠡᠳ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ", "tumed baragun hosigu" # Түмэд Баруун хошуу
-  test "ᠳᠠᠷᠬᠠᠨ ᠮᠤᠤᠮᠢᠩᠭ᠋ᠠᠨ ᠬᠣᠯᠪᠣᠭᠠᠲᠤ ᠬᠣᠰᠢᠭᠤ", "darhan muumingg᠋an holbogatu hosigu" # Darhan Muminggan United Banner
-  test "ᠬᠡᠰᠢᠭᠲᠡᠨ ᠬᠣᠰᠢᠭᠤ", "hesigten hosigu" # Hexigten Banner
-  test "ᠰᠢᠨ᠎ᠡ ᠪᠠᠷᠭᠤ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ", "sin-e bargu jegun hosigu" # New Barag Left Banner
-  test "ᠰᠢᠨ᠎ᠡ ᠪᠠᠷᠭᠤ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ", "sin-e bargu baragun hosigu" # New Barag Right Banner
-  test "ᠣᠲᠣᠭ ᠬᠣᠰᠢᠭᠤ", "otog hosigu" # Otog Banner
-  test "ᠳ᠋ᠦᠩᠱᠧᠩ ᠲᠣᠭᠣᠷᠢᠭ", "d᠋ungxeng togorig" # Dongsheng District
-  test "ᠳᠠᠯᠠᠳ ᠬᠣᠰᠢᠭᠤ", "dalad hosigu" # Dalad Banner
-  test "ᠵᠡᠭᠦᠨᠭᠠᠷ ᠬᠣᠰᠢᠭᠤ", "jegungar hosigu" # Jungar Banner
-  test "ᠣᠲᠣᠭ ᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ", "otog-un emunedu hosigu" # Otog Front Banner
-  test "ᠬᠠᠩᠭᠢᠨ ᠬᠣᠰᠢᠭᠤ", "hanggin hosigu" # Hanggin Banner
-  test "ᠦᠦᠰᠢᠨ ᠬᠣᠰᠢᠭᠤ", "uusin hosigu" # Uxin Banner
-  test "ᠡᠵᠢᠨ ᠬᠣᠷᠣᠭ᠎ᠠ ᠬᠣᠰᠢᠭᠤ", "ejin horog-a hosigu" # Эзэн Хороо хошуу
-  test "ᠵᠠᠯᠠᠨ ᠠᠢ᠌ᠯ ᠬᠣᠲᠠ", "jalan ai᠌l hota" # Жалан-Айл хот
-  test "ᠶᠠᠭᠰᠢ ᠬᠣᠲᠠ", "yagsi hota" # Ягши хот
-  test "ᠮᠠᠨᠵᠤᠤᠷ ᠬᠣᠲᠠ", "manjuur hota" # Манжуур хот
-  test "ᠬᠠᠶᠢᠯᠠᠷ ᠲᠣᠭᠣᠷᠢᠭ", "hayilar togorig" # Хайлаар тойрог
-  test "ᠬᠣᠷᠴᠢᠨ ᠲᠣᠭᠣᠷᠢᠭ", "horqin togorig" # Horqin District
-  test "ᠺᠠᠶᠢᠯᠦ ᠰᠢᠶᠠᠨ", "kayilu siyan" # Kailu County
-  test "ᠬᠦᠷᠢᠶ᠎ᠡ ᠬᠣᠰᠢᠭᠤ", "huriy-e hosigu" # Hure Banner
-  test "ᠨᠠᠢᠮᠠᠨ ᠬᠣᠰᠢᠭᠤ", "naiman hosigu" # Naiman Banner
-  test "ᠵᠠᠷᠤᠳ ᠬᠣᠰᠢᠭᠤ", "jarud hosigu" # Jarud Banner
-  test "ᠬᠣᠷᠴᠢᠨ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ", "horqin baragun garun dumdadu hosigu" # Хорчин Баруун Гарын Дундад Хошуу
-  test "ᠬᠣᠷᠴᠢᠨ ᠵᠡᠭᠦᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ", "horqin jegun garun dumdadu hosigu" # Horqin Left Middle Banner
-  test "ᠬᠣᠷᠴᠢᠨ ᠵᠡᠭᠦᠨ ᠭᠠᠷᠤᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ", "horqin jegun garun hoyitu hosigu" # Horqin Left Rear Banner
-  test "ᠤᠯᠠᠭᠠᠨᠬᠠᠳᠠ ᠬᠣᠲᠠ", "ulaganhada hota" # Улаанхад хот
-  test "ᠰᠡᠷᠡᠴᠢ", "sereqi" # Salaqi
-  test "ᠭᠡᠭᠡᠨ ᠭᠣᠤᠯ ᠬᠣᠲᠠ", "gegen goul hota" # Гэгээнгол хот
-  test "ᠠᠯᠠᠱᠠ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ", "alaxa jegun hosigu" # Alxa Left Banner
-  test "ᠠᠯᠠᠱᠠ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ", "alaxa baragun hosigu" # Alxa Right Banner
-  test "ᠡᠵᠡᠨ᠎ᠡ ᠬᠣᠰᠢᠭᠤ", "ejen-e hosigu" # Ejin Banner
-  test "ᠬᠥᠪᠡᠭᠡᠲᠦ ᠰᠢᠷ᠎ᠠ ᠬᠣᠰᠢᠭᠤ", "hobegetu sir-a hosigu" # Хөвөөт Шар хошуу
-  test "ᠦᠶᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ", "uyuwan siyan" # Үюань шянь
-  test "ᠦᠴᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ", "uquwan siyan" # Wuchuan County
-  test "ᠲᠦᠴᠢᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ", "tuqiuwan siyan" # Тучуань шянь
-  test "ᠨᠢᠩᠴᠧᠩ ᠰᠢᠶᠠᠨ", "ningqeng siyan" # Ningcheng County
-  test "ᠯᠢᠨᠰᠢ ᠰᠢᠶᠠᠨ", "linsi siyan" # Linxi County
-  test "ᠯᠢᠨᠾᠧ ᠲᠣᠭᠣᠷᠢᠭ", "linhe togorig" # Linhe
-  test "ᠬᠠᠷᠠᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ", "haraqin hosigu" # Harqin Banner
-  test "ᠳ᠋ᠧᠩᠺᠧᠦ ᠰᠢᠶᠠᠨ", "d᠋engkeu siyan" # Dengkou County
-  test "ᠠᠤᠬᠠᠨ ᠬᠣᠰᠢᠭᠤ", "auhan hosigu" # Aohan Banner
-  test "ᠴᠢᠩ ᠱᠦᠢ ᠾᠧ ᠰᠢᠶᠠᠨ", "qing xui he siyan" # Qingshuihe County
-  test "ᠬᠣᠳᠣᠩ ᠠᠷᠠᠳ ᠤᠨ ᠲᠣᠭᠣᠷᠢᠭ", "hodong arad-un togorig" # Huimin District
-  test "ᠰᠠᠶᠢᠬᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "sayihan togorig" # Saihan District
-  test "ᠰᠢᠨ᠎ᠡ ᠬᠣᠲᠠ ᠲᠣᠭᠣᠷᠢᠭ", "sin-e hota togorig" # Xincheng District
-  test "ᠬᠠᠶᠢᠷᠤᠪ ᠤᠨ ᠲᠣᠬᠣᠢ ᠲᠣᠭᠣᠷᠢᠭ", "hayirub-un tohoi togorig" # Haibowan (Hairibin Tohoi) District
-  test "ᠰᠦᠩ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "sung xan togorig" # Songshan District
-  test "ᠬᠦᠩ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "hung xan togorig" # Hongshan District
-  test "ᠠᠷᠤᠨ ᠬᠣᠰᠢᠭᠤ", "arun hosigu" # Арун хошуу
-  test "ᠶᠤᠸᠠᠨ ᠪᠣᠣ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ", "yuwan boo xan togorig" # Юаньбаошань тойрог
-  test "ᠰᠢᠯᠤᠭᠤᠨ ᠬᠥᠪᠡᠭᠡᠲᠦ ᠴᠠᠭᠠᠨ ᠬᠣᠰᠢᠭᠤ", "silugun hobegetu qagan hosigu" # Шулуун Хөвөөт Цагаан хошуу
-  test "ᠰᠢᠯᠤᠭᠤᠨ ᠬᠥᠬᠡ ᠬᠣᠰᠢᠭᠤ", "silugun hohe hosigu" # Шулуун хөх хошуу
-  test "ᠤᠷᠠᠳ ᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ", "urad-un dumdadu hosigu" # Урадын Дундад Хошуу
-  test "ᠤᠷᠠᠳ ᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ", "urad-un emunedu hosigu" # Урадын Өмнөд Хошуу
-  test "ᠲᠣᠭᠲᠠᠬᠤ ᠰᠢᠶᠠᠨ", "togtahu siyan" # Тогтох шянь
-  test "ᠲᠠᠶᠢᠫᠤᠰᠧ ᠬᠣᠰᠢᠭᠤ", "tayipuse hosigu" # Тайвас хошуу
-  test "ᠰᠥᠨᠡᠳ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ", "soned jegun hosigu" # Sonid Left Banner
-  test "ᠰᠥᠨᠡᠳ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ", "soned baragun hosigu" # Sonid Right Banner
-  test "ᠣᠩᠨᠢᠭᠤᠳ ᠬᠣᠰᠢᠭᠤ", "ongnigud hosigu" # Ongniud Banner
-  test "ᠵᠠᠯᠠᠢᠳ ᠬᠣᠰᠢᠭᠤ", "jalaid hosigu" # Jalaid Banner
-  test "ᠬᠠᠩᠭᠢᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ", "hanggin hoyitu hosigu" # Hanggin Rear Banner
-  test "ᠵᠡᠭᠦᠨ ᠤᠵᠤᠮᠤᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ", "jegun ujumuqin hosigu" # East Ujimqin Banner
-  test "ᠠᠷᠤ ᠬᠣᠷᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ", "aru horqin hosigu" # Ar Horqin Banner
-  test "ᠠᠪᠠᠭ᠎ᠠ ᠬᠣᠰᠢᠭᠤ", "abag-a hosigu" # Abag Banner
-  test "ᠪᠤᠷᠢᠶᠠᠳ", "buriyad" # Буриад
-  test "ᠤᠯᠠᠭᠠᠨᠪᠠᠭᠠᠲᠤᠷ", "ulaganbagatur" # Улаанбаатар
-}
-
-dependency "sasm-mon-Mong-Latn-general-1978", as: monglatn
-
-stage {
-
-  run map.monglatn.stage.main
-
-}