interscript 0.1.6 → 0.1.7

data/maps/var-hin-Deva-Latn-hunterian-1872.yaml

@@ -0,0 +1,221 @@
+---
+authority_id: var
+id: 1872
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Hunterian system
+url: https://transliteration.eki.ee/pdf/Hindi-Marathi-Nepali.pdf
+creation_date: 1872
+description:
+  The Hunterian system is the national system of romanization in India.
+
+notes:
+
+  -  a, i and u are used in word-final position. The a in gaon and the u in pur are not accented.
+  -  ज्ञ is transliterated gy.
+  -  v is used before i.
+
+tests:
+  - source: "परिपक्क"
+    expected: "paraipakka"
+  - source: "जगत्"
+    expected: "jagat"
+  - source: "संख्या"
+    expected: "sankhyaā"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "ganbhaīra maraījaon kae maāmalae maen bhaārata daūsarae nanbara para"
+  - source: "कोरोना अपडेट्स"
+    expected: "kaoraonaā apadaetsa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "saīdaīsaī chaīpha kaā bayaāna ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gaūgala plae staora para paetaīema kaī waāpasaī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhaārata maen gaainbalainga kaī ijaājata nahaīn"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "kaoraonaā waaiksaīna mauddae para ghairae raāshtrapatai; jao baāidaena baolae- maujhae aura daesa kao waaigyānaikaon para bharaosaā haai, daonaālda trampa para nahaīn"
+  - 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 kaārrawaāi para paetaīema nae kahaā thaā kai aipa kao asthaāyaī taaura para plae-staora sae hataāyaā gayaā haai, āpakae paaisae saurakshaita haain"
+
+map:
+
+  rules:
+    # note[1]
+    - pattern: (?<=)\u0906(?=\b)
+      result: "a"
+    - pattern: (?<=)\u0908(?=\b)
+      result: "i"
+    - pattern: (?<=)\u090A(?=\b)
+      result: "u"
+
+    # note[3]
+    - pattern: \u0935(?=[इई])
+      result: "v"
+
+
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ri'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'nga'
+
+    # Palatals
+    'च': 'cha'
+    'छ': 'chha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'nya'
+
+    # Cerebrals
+    'ट': 'ta'
+    'ठ': 'tha'
+    'ड': 'da'
+    'ढ': 'dha'
+    'ण': 'na'
+
+    # 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': 'wa'
+
+    # Sibilants
+    'श': 'sa'
+    'ष': 'sha'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+
+    # Additional consonants
+    'क़': 'qa'
+    'ख़': 'kha'
+    'ग़': 'ġa'
+    'ज़': 'za'
+    'ड़': 'ṙa'
+    'ढ़': 'ṙha'
+    'फ़': 'fa'
+    'ळ': 'la'
+
+    # Anusvāra
+    'ं': 'n'
+
+    # Bisarga
+    'ः': 'h'
+
+    # Anunāsika
+    'ँ': 'm'
+
+    # Note 2
+    'ज्ञ': 'gy'
+
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ri"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+    '‍': ''# Used for joining
+
+
+    #V. Vowelless with halanta (्)
+
+    # Gutturals
+    'क्': 'k'
+    'ख्': 'kh'
+    'ग्': 'g'
+    'घ्': 'gh'
+    'ङ्': 'ng'
+
+    # Palatals
+    'च्': 'ch'
+    'छ्': 'chh'
+    'ज्': 'j'
+    'झ्': 'jh'
+    'ञ्': 'ny'
+
+    # Cerebrals
+    'ट्': 't'
+    'ठ्': 'th'
+    'ड्': 'd'
+    'ढ्': 'dh'
+    'ण्': 'n'
+
+    # 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': 'w'
+
+    # Sibilants
+    'श्': 's'
+    'ष्': 'sh'
+    'स्': 's'
+
+    # Aspirate
+    'ह्': 'h'
+
+    # Additional consonants
+    'क़्': 'q'
+    'ख़्': 'kh'
+    'ग़्': 'ġ'
+    'ज़्': 'z'
+    'ड़्': 'ṙ'
+    'ढ़्': 'ṙh'
+    'फ़्': 'f'
+    'ळ्': 'l'

data/maps/var-jpn-Hrkt-Latn-hepburn-1886.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: var
 id: hepburn-1886
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: Traditional Hepburn

data/maps/var-jpn-Hrkt-Latn-hepburn-1954.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: var
 id: hepburn-1954
-language: jpn
+language: iso-639-2:jpn
 source_script: Hrkt
 destination_script: Latn
 name: Modified Hepburn

data/maps/{nil-kor-Hang-Hang-jamo.yaml → var-kor-Hang-Hang-jamo.yaml}

@@ -1,7 +1,7 @@
 ---
 authority_id: nil
 id: jamo
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Hang
 name: Hangul to Jamo decomposition

data/maps/var-kor-Hang-Latn-mr-1939.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgn
 id: mr-1939
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: McCune-Reischauer System
@@ -310,7 +310,7 @@ map:
   character_separator: ""
   word_separator: " "
   title_case: False
-  inherit: nil-kor-Hang-Hang-jamo
+  inherit: var-kor-Hang-Hang-jamo
 
   rules:
 

data/maps/var-kor-Kore-Hang-2013.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: var
 id: 2013
-language: kor
+language: iso-639-2:kor
 source_script: Kore
 destination_script: Hang
 name: Hanja Hangul Converter 0.0.7

data/maps/var-kor-Kore-Latn-mr-1939.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgn
 id: mr-1939
-language: kor
+language: iso-639-2:kor
 source_script: Hang
 destination_script: Latn
 name: McCune-Reischauer System

data/maps/var-mar-Deva-Latn-hunterian-1872.yaml

@@ -0,0 +1,43 @@
+---
+authority_id: var
+id: 1872
+language: iso-639-2:mar
+source_script: Deva
+destination_script: Latn
+name: Marathi Hunterian system
+url: https://transliteration.eki.ee/pdf/Hindi-Marathi-Nepali.pdf
+creation_date: 1872
+description:
+  The Hunterian system is the national system of romanization in India.
+
+notes:
+
+  -  a, i and u are used in word-final position. The a in gaon and the u in pur are not accented.
+  -  ज्ञ is transliterated gy.
+  -  v is used before i.
+
+tests:
+  - source: "ठाणे - जिल्ह्यात बुधवारी एक हजार रुग्णांची वाढ, तर जणांच्या मृत्यूची नोंद"
+    expected: "thaānae - jailhyaāta baudhawaāraī eka hajaāra raugnaānchaī waādha, tara janaānchyaā marityaūchaī naonda"
+  - source: "एकता कपूर पुन्हा अडकली वादात, वेबसीरिजमधल्या 'त्या' सीनमुळे जमावाची घरावर दगडफेक"
+    expected: "ekataā kapaūra paunhaā adakalaī waādaāta, waebasaīraijamadhalyaā 'tyaā' saīnamaulae jamaāwaāchaī gharaāwara dagadaphaeka"
+  - source: "जाणून घ्या, बीएमसीच्या अधिकाऱ्यांनी कंगना राणौतच्या ऑफिसमधले नक्की काय- काय तोडलं"
+    expected: "jaānaūna ghyaā, baīemasaīchyaā adhaikaāऱ्yaānnaī kanganaā raānaautachyaā ऑphaisamadhalae nakkaī kaāya- kaāya taodalan"
+  - source: "कंगना मुंबईत दाखल होण्यापूर्वी 'मातोश्री'वरून फर्मान सुटले; प्रवक्त्यांना सक्त आदेश"
+    expected: "kanganaā maunbaīta daākhala haonyaāpaūrwaī 'maātaosraī'waraūna pharmaāna sautalae; prawaktyaānnaā sakta ādaesa"
+  - source: "मराठा आरक्षणास तात्पुरती स्थगिती; सर्वोच्च न्यायालयाचा निर्णय"
+    expected: "maraāthaā ārakshanaāsa taātpaurataī sthagaitaī; sarwaochcha nyaāyaālayaāchaā nairnaya"
+  - source: "भारताच्या तिन्ही लशींचा पहिला टप्पा यशस्वी, वाचा कधी येणार बाजारात"
+    expected: "bhaārataāchyaā tainhaī lasaīnchaā pahailaā tappaā yasaswaī, waāchaā kadhaī yaenaāra baājaāraāta"
+  - source: "रुग्णवाढीमुळे खाटांची चणचण"
+    expected: "raugnawaādhaīmaulae khaātaānchaī chanachana"
+  - source: "पीएम स्वनिधी कर्ज योजनेला मुंबईतून अल्प प्रतिसाद"
+    expected: "paīema swanaidhaī karja yaojanaelaā maunbaītaūna alpa prataisaāda"
+  - source: "सांताक्रूझ-चेंबूर लिंक रोडवरील उन्नत मार्गाला स्थगिती"
+    expected: "saāntaākraūjha-chaenbaūra lainka raodawaraīla unnata maārgaālaā sthagaitaī"
+  - source: "संपादक अर्णब गोस्वामी यांच्याविरूद्ध खडक पोलिस ठाण्यात तक्रार"
+    expected: "sanpaādaka arnaba gaoswaāmaī yaānchyaāwairaūddha khadaka paolaisa thaānyaāta takraāra"
+
+map:
+
+  inherit: 'var-hin-Deva-Latn-hunterian-1872'

data/maps/var-mon-Mong-Latn-1930.yaml

@@ -0,0 +1,102 @@
+---
+authority_id: var
+id: 1930
+language: iso-639-2:mon
+source_script: Mong
+destination_script: Latn
+name: Mongolian Latin alphabet
+url: https://en.m.wikipedia.org/wiki/Mongolian_Latin_alphabet
+creation_date:
+description: |
+  Latin alphabet was using "y" as feminine "u", with additional
+  feminine "o" ("ө") and with additional consonants "ç" for "ch", "ş"
+  for "sh" and "ƶ" for "j", it successfully served in printing books
+  and newspapers. A few of the letters (f, k, p, v) were rarely used,
+  being found only in borrowings, while q, w and x were excluded
+  altogether. Since k transcribed [h] in loans, it is unclear how loans
+  in [kʰ] were written. "j" is used for vowel combinations of the [ja]
+  type. Letter "c" is used for the sound [ts] and "k" is used for the 
+  ound [h]. The first version was inspired by the Yanalif script used
+  for the Soviet Union's Turkic languages.
+
+  The orthography of the Mongolian Latin is based on the orthography of
+  the Classical Mongolian script. It preserves short final vowels. It
+  does not drop unstressed vowels in the closing syllables when the word
+  is conjugated. The suffixes and inflections without long or i-coupled
+  vowels are made open syllables ending with a vowel, which is harmonized
+  with the stressed vowel. The rule for the vowel harmony for unstressed
+  vowels is similar to that of the Mongolian Cyrillic. It does not use
+  consonant combinations to denote new consonant sounds. For both of the
+  version, letter "b" is used both in the beginning and in the middle of
+  the word. Because it phonetically assimilates into sound [w], no
+  ambiguity is caused.
+
+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.
+
+  # Note: Provedid sample of "Latin 1931-1939" in https://en.m.wikipedia.org/wiki/Mongolian_Latin_alphabet is not actual transliteration.
+  # It's kind of buggy transliteration that mixes Cyrillic and Traditional Mongolian script into Latin based on phonetic sound.
+  # There is no expected transliteration sources found for the tests.
+
+  # Latin 1931-1939
+  # Manai ulasiin niislel koto Ulaanbaatar bol 80 000 şakam kyntei, ulasiin olon niitiin, aƶi akuin tөb gazaruud oroşison jikeeken oron bolno.
+  # Tus ulasiin dotoroos garka tyykii zuiliig bolbosruulka aƶi yildberiin gazaruudiig baiguulka ni çukala.
+
+tests:
+  - source: |
+      ᠮᠠᠨ ᠤ ᠤᠯᠤᠰ ᠤᠨ ᠨᠡᠶᠢᠰᠯᠡᠯ ᠬᠣᠲᠠ ᠤᠯᠠᠭᠠᠨᠪᠠᠭᠠᠲᠤᠷ ᠪᠣᠯ 80 000 ᠰᠢᠬᠠᠮ ᠬᠦᠮᠦᠨ ᠲᠡᠢ᠂ ᠤᠯᠤᠰ ᠤᠨ ᠣᠯᠠᠨ ᠨᠡᠶᠢᠲᠡ ᠶᠢᠨ᠂ ᠠᠵᠤ ᠠᠬᠤᠢ ᠶᠢᠨ ᠲᠥᠪ ᠭᠠᠵᠠᠷ ᠤᠳ ᠣᠷᠣᠰᠢᠭᠰᠠᠨ ᠶᠡᠬᠡᠬᠡᠨ ᠣᠷᠣᠨ ᠪᠣᠯᠤᠨ᠎ᠠ᠃
+      ᠲᠤᠰ ᠤᠯᠤᠰ ᠤᠨ ᠳᠣᠲᠣᠷ᠎ᠠ ᠠᠴᠠ ᠭᠠᠷᠬᠤ ᠲᠦᠭᠦᠬᠡᠢ ᠵᠤᠶᠢᠯ ᠢ ᠪᠣᠯᠪᠠᠰᠤᠷᠠᠭᠤᠯᠬᠤ ᠠᠵᠤ ᠦᠢᠯᠡᠳᠪᠦᠷᠢ ᠶᠢᠨ ᠭᠠᠵᠠᠷ ᠤᠳ ᠢ ᠪᠠᠶᠢᠭᠤᠯᠬᠤ ᠨᠢ ᠴᠢᠬᠤᠯᠠ᠃
+    expected: |
+      man-u ulus-un nejislel kota ulaganbagatur bol 80 000 sikam kymyn-tei, ulus-un olan nejite-jin, aƶu akui-jin tөb gaƶar-ud orosigsan jekeken oron bolun-a.
+      tus ulus-un dotor-a-aça garku tygykei ƶujil-i bolbasuragulku aƶu yiledbyri-jin gaƶar-ud-i bajigulku ni çikula.
+
+map:
+
+  characters:
+    "ᠠ": "a"      # \u1820
+    "ᠡ": "e"      # \u1821
+    "ᠢ": "i"      # \u1822
+    "ᠣ": "o"      # \u1823
+    "ᠤ": "u"      # \u1824
+    "ᠥ": "ө"     # \u1825
+    "ᠦ": "y"     # \u1826
+    "ᠨ": "n"      # \u1828
+    "ᠮ": "m"      # \u182e
+    "ᠯ": "l"      # \u182f
+    "ᠪ": "b"      # \u182a
+    "ᠫ": "p"      # \u182b
+    "ᠹ": "f"      # \u1839
+    "ᠻ": "k"      # \u183b
+    "ᠬ": "k"      # \u182c
+    "ᠭ": "g"      # \u182d
+    "ᠰ": "s"      # \u1830
+    "ᠱ": "ş"      # \u1831
+    "ᠲ": "t"      # \u1832
+    "ᠳ": "d"      # \u1833
+    "ᠴ": "c"      # \u1834
+    "ᠴ": "ç"      # \u1834
+    "ᠵ": "z"      # \u1835
+    "ᠵ": "ƶ"      # \u1835
+    "ᠶ": "j"      # \u1836
+    "ᠷ": "r"      # \u1837
+    "ᠾ": "h"     # \u183e
+    "᠁": "..."   # \u1801
+    "᠂": ","      # \u1802
+    "᠃": "."      # \u1803
+    "᠄": ":"      # \u1804
+    "\u180e": "-" # MVS
+    "\u202f": "-" # NNBSP

data/maps/var-mon-Mong-Latn-lessing.yaml

@@ -0,0 +1,272 @@
+---
+authority_id: var
+id: lessing
+language: iso-639-2:mon
+source_script: Mong
+destination_script: Latn
+name: Transliteration Systems for Uyghur-Mongolian or Vertical or Old Script
+url: https://collab.its.virginia.edu/wiki/tibetan-script/Transliteration%20Schemes%20for%20Mongolian%20Vertical%20Script.html
+creation_date:
+description: |
+  The only system for the Mongolian vertical script which is used commonly throughout
+  Mongolian studies worldwide is the Vladimirtsov-Mostaert system (V-M). The only
+  dictionary using this system is in an appendix to Antoine Mostaert’s Dictionnaire
+  ordos. Thus the Harvard Journal of Asiatic Studies specifies, “please use the written
+  Mongolian appendix to Antoine Mostaert’s Dictionnaire ordos. However, the V-M system
+  has many difficult diacriticals and non-Latin characters that constitute a significant
+  problem for editors and thus is difficult to recommend.
+
+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 rexuires 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:
+  - source: ᠬᠥᠬᠡᠬᠣᠲᠠ # Хөх хот
+    expected: køkexota
+  - source: ᠣᠷᠳᠣᠰ ᠬᠣᠲᠠ # Ордос хот
+    expected: ordos xota
+  - source: ᠪᠠᠶᠠᠨᠨᠠᠭᠤᠷ ᠬᠣᠲᠠ # Баяннуур хот
+    expected: bajannaγur xota
+  - source: ᠤᠯᠠᠭᠠᠨᠬᠣᠲᠠ # Улаан хот
+    expected: ulaγanxota
+  - source: ᠬᠣᠣᠯᠢᠠ ᠭᠣᠤᠯ ᠬᠣᠲᠠ # Хоолингол хот
+    expected: xoolia γoul xota
+  - source: ᠡᠷᠢᠶᠡᠨ ᠬᠣᠲᠠ #  Эрээн хот
+    expected: erijen xota
+  - source: ᠷᠠᠰᠢᠶᠠᠨ ᠬᠣᠲᠠ # Рашаан хот
+    expected: rasijan xota
+  - source: ᠪᠠᠭᠠᠷᠢᠨ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ # Баарин баруун хошуу
+    expected: baγarin baraγun xosiγu
+  - source: ᠪᠠᠭᠠᠷᠢᠨ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ # Баарин зүүн хошуу
+    expected: baγarin zegyn xosiγu
+  - source: ᠲᠦᠩᠯᠢᠶᠣᠤ ᠬᠣᠲᠠ # Байшинт хот
+    expected: tynglijou xota
+  - source: ᠰᠢᠯᠢ ᠶᠢᠨ ᠬᠣᠲᠠ # Шилийн хот
+    expected: sili-jin xota
+  - source: ᠬᠣᠷᠢᠨ ᠭᠡᠷ ᠰᠢᠶᠠᠨ # Horinger County
+    expected: xorin ger sijan
+  - source: ᠤᠳᠠ ᠲᠣᠭᠣᠷᠢᠭ # Уда тойрог
+    expected: uda toγoriγ
+  - source: ᠦᠬᠠᠢ ᠬᠣᠲᠠ # Үхай хот
+    expected: yxai xota
+  - source: ᠬᠠᠶᠢᠨᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Hainan District
+    expected: xainan toγoriγ
+  - source: ᠬᠠᠶᠢᠷᠤᠪ ᠤᠨ ᠲᠣᠬᠣᠢ ᠲᠣᠭᠣᠷᠢᠭ # Haibowan District
+    expected: xairub-un toxoi toγoriγ
+  - source: ᠤᠯᠠᠭᠠᠨᠴᠠᠪ ᠬᠣᠲᠠ # Улаанцав хот
+    expected: ulaγancab xota
+  - source: ᠵᠢᠨᠢᠩ ᠲᠣᠭᠣᠷᠢᠭ # Жинин тойрог
+    expected: zining toγoriγ
+  - source: ᠹᠸᠩᠵᠸᠡ ᠬᠣᠲᠠ # Фенжень хот
+    expected: fvngzve xota
+  - source: ᠱᠠᠩᠳᠤ ᠰᠢᠶᠠᠨ # Шанду шянь
+    expected: šangdu sijan
+  - source: ᠯᠢᠶᠠᠩᠴᠠᠩ ᠰᠢᠶᠠᠨ # Liangcheng County
+    expected: lijangcang sijan
+  - source: ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ # Цахар баруун гарын өмнөд хошуу
+    expected: caxar baraγun γarun emynedy xosiγu
+  - source: ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ # Цахар баруун гарын дундад хошуу
+    expected: caxar baraγun γarun dumdadu xosiγu
+  - source: ᠴᠠᠬᠠᠷ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ # Цахар баруун гарын хойд хошуу
+    expected: caxar baraγun γarun xoitu xosiγu
+  - source: ᠳᠥᠷᠪᠡᠳ ᠬᠣᠰᠢᠭᠤ # Дөрвөд хошуу
+    expected: dørbed xosiγu
+  - source: ᠪᠤᠭᠤᠲᠤ ᠬᠣᠲᠠ # Бугaт хот
+    expected: buγutu xota
+  - source: ᠬᠥᠨᠳᠡᠯᠡᠨ ᠲᠣᠭᠣᠷᠢᠭ # Hondlon District
+    expected: køndelen toγoriγ
+  - source: ᠴᠢᠩᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Qingshan District
+    expected: cingšan toγoriγ
+  - source: ᠰᠢᠭᠤᠶᠢᠲᠤ ᠲᠣᠭᠣᠷᠢᠭ # Шигуай тойрог
+    expected: siγuitu toγoriγ
+  - source: ᠵᠢᠦ ᠶᠤᠸᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Jiuyuan District
+    expected: ziy juvan toγoriγ
+  - source: ᠭᠦᠶᠠᠩ ᠰᠢᠶᠠᠨ # Guyang County
+    expected: gyjang sijan
+  - source: ᠲᠦᠮᠡᠳ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ # Түмэд Зүүн хошуу
+    expected: tymed zegyn xosiγu
+  - source: ᠲᠦᠮᠡᠳ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ # Түмэд Баруун хошуу
+    expected: tymed baraγun xosiγu
+  - source: ᠳᠠᠷᠬᠠᠨ ᠮᠤᠤᠮᠢᠩᠭ᠋ᠠᠨ ᠬᠣᠯᠪᠣᠭᠠᠲᠤ ᠬᠣᠰᠢᠭᠤ # Darhan Muminggan United Banner
+    expected: darxan muumingγ᠋an xolboγatu xosiγu
+  - source: ᠬᠡᠰᠢᠭᠲᠡᠨ ᠬᠣᠰᠢᠭᠤ # Hexigten Banner
+    expected: kesiγten xosiγu
+  - source: ᠰᠢᠨ᠎ᠡ ᠪᠠᠷᠭᠤ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ # New Barag Left Banner
+    expected: sin-e barγu zegyn xosiγu
+  - source: ᠰᠢᠨ᠎ᠡ ᠪᠠᠷᠭᠤ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ # New Barag Right Banner
+    expected: sin-e barγu baraγun xosiγu
+  - source: ᠣᠲᠣᠭ ᠬᠣᠰᠢᠭᠤ # Otog Banner
+    expected: otoγ xosiγu
+  - source: ᠳᠠᠯᠠᠳ ᠬᠣᠰᠢᠭᠤ # Dalad Banner
+    expected: dalad xosiγu
+  - source: ᠵᠡᠭᠦᠨᠭᠠᠷ ᠬᠣᠰᠢᠭᠤ # Jungar Banner
+    expected: zegynγar xosiγu
+  - source: ᠣᠲᠣᠭ ᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ # Otog Front Banner 
+    expected: otoγ-un emynedy xosiγu
+  - source: ᠬᠠᠩᠭᠢᠨ ᠬᠣᠰᠢᠭᠤ # Hanggin Banner
+    expected:	xangγin xosiγu
+  - source: ᠦᠦᠰᠢᠨ ᠬᠣᠰᠢᠭᠤ # Uxin Banner
+    expected: yysin xosiγu
+  - source: ᠡᠵᠢᠨ ᠬᠣᠷᠣᠭ᠎ᠠ ᠬᠣᠰᠢᠭᠤ # Эзэн Хороо хошуу
+    expected: ezin xoroγ-a xosiγu
+  - source: ᠵᠠᠯᠠᠨ ᠠᠢ᠌ᠯ ᠬᠣᠲᠠ # Жалан-Айл хот
+    expected: zalan ai᠌l xota
+  - source: ᠶᠠᠭᠰᠢ ᠬᠣᠲᠠ # Ягши хот
+    expected: jaγsi xota
+  - source: ᠮᠠᠨᠵᠤᠤᠷ ᠬᠣᠲᠠ # Манжуур хот
+    expected: manzuur xota
+  - source: ᠬᠠᠶᠢᠯᠠᠷ ᠲᠣᠭᠣᠷᠢᠭ # Хайлаар тойрог
+    expected: xailar toγoriγ
+  - source: ᠬᠣᠷᠴᠢᠨ ᠲᠣᠭᠣᠷᠢᠭ # Horqin District
+    expected: xorcin toγoriγ
+  - source: ᠺᠠᠶᠢᠯᠦ ᠰᠢᠶᠠᠨ # Kailu County
+    expected: kaily sijan
+  - source: ᠬᠦᠷᠢᠶ᠎ᠡ ᠬᠣᠰᠢᠭᠤ # Hure Banner
+    expected: kyrij-e xosiγu
+  - source: ᠨᠠᠢᠮᠠᠨ ᠬᠣᠰᠢᠭᠤ # Naiman Banner
+    expected: naiman xosiγu
+  - source: ᠵᠠᠷᠤᠳ ᠬᠣᠰᠢᠭᠤ # Jarud Banner
+    expected: zarud xosiγu
+  - source: ᠬᠣᠷᠴᠢᠨ ᠪᠠᠷᠠᠭᠤᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ # Хорчин Баруун Гарын Дундад Хошуу
+    expected: xorcin baraγun γarun dumdadu xosiγu
+  - source: ᠬᠣᠷᠴᠢᠨ ᠵᠡᠭᠦᠨ ᠭᠠᠷᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ # Horqin Left Middle Banner
+    expected: xorcin zegyn γarun dumdadu xosiγu
+  - source: ᠬᠣᠷᠴᠢᠨ ᠵᠡᠭᠦᠨ ᠭᠠᠷᠤᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ # Horqin Left Rear Banner
+    expected: xorcin zegyn γarun xoitu xosiγu
+  - source: ᠤᠯᠠᠭᠠᠨᠬᠠᠳᠠ ᠬᠣᠲᠠ # Улаанхад хот
+    expected: ulaγanxada xota
+  - source: ᠰᠡᠷᠡᠴᠢ # Salaqi
+    expected: sereci
+  - source: ᠭᠡᠭᠡᠨ ᠭᠣᠤᠯ ᠬᠣᠲᠠ # Гэгээнгол хот
+    expected: gegen γoul xota
+  - source: ᠠᠯᠠᠱᠠ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ # Alxa Left Banner
+    expected: alaša zegyn xosiγu
+  - source: ᠠᠯᠠᠱᠠ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ # Alxa Right Banner
+    expected: alaša baraγun xosiγu # Alaša Baraγun xosiγu
+  - source: ᠡᠵᠡᠨ᠎ᠡ ᠬᠣᠰᠢᠭᠤ # Ejin Banner
+    expected: ezen-e xosiγu
+  - source: ᠬᠥᠪᠡᠭᠡᠲᠦ ᠰᠢᠷ᠎ᠠ ᠬᠣᠰᠢᠭᠤ # Хөвөөт Шар хошуу
+    expected: købegety sir-a xosiγu
+  - source: ᠦᠶᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ # Үюань шянь
+    expected: yjuvan sijan
+  - source: ᠦᠴᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ # Wuchuan County
+    expected: ycuvan sijan
+  - source: ᠲᠦᠴᠢᠤᠸᠠᠨ ᠰᠢᠶᠠᠨ # Тучуань шянь
+    expected: tyciuvan sijan
+  - source: ᠯᠢᠨᠰᠢ ᠰᠢᠶᠠᠨ # Linxi County
+    expected: linsi sijan
+  - source: ᠬᠠᠷᠠᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ # Harqin Banner
+    expected: xaracin xosiγu
+  - source: ᠠᠤᠬᠠᠨ ᠬᠣᠰᠢᠭᠤ # Aohan Banner
+    expected: auxan xosiγu
+  - source: ᠬᠣᠳᠣᠩ ᠠᠷᠠᠳ ᠤᠨ ᠲᠣᠭᠣᠷᠢᠭ # Huimin District
+    expected: xodong arad-un toγoriγ
+  - source: ᠰᠠᠶᠢᠬᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Saihan District
+    expected: saixan toγoriγ
+  - source: ᠰᠢᠨ᠎ᠡ ᠬᠣᠲᠠ ᠲᠣᠭᠣᠷᠢᠭ # Xincheng District
+    expected: sin-e xota toγoriγ
+  - source: ᠬᠠᠶᠢᠷᠤᠪ ᠤᠨ ᠲᠣᠬᠣᠢ ᠲᠣᠭᠣᠷᠢᠭ # Haibowan (Hairibin Tohoi) District
+    expected: xairub-un toxoi toγoriγ
+  - source: ᠰᠦᠩ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Songshan District
+    expected: syng šan toγoriγ
+  - source: ᠬᠦᠩ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Hongshan District
+    expected: kyng šan toγoriγ
+  - source: ᠠᠷᠤᠨ ᠬᠣᠰᠢᠭᠤ # Арун хошуу
+    expected: arun xosiγu
+  - source: ᠶᠤᠸᠠᠨ ᠪᠣᠣ ᠱᠠᠨ ᠲᠣᠭᠣᠷᠢᠭ # Юаньбаошань тойрог
+    expected: juvan boo šan toγoriγ
+  - source: ᠰᠢᠯᠤᠭᠤᠨ ᠬᠥᠪᠡᠭᠡᠲᠦ ᠴᠠᠭᠠᠨ ᠬᠣᠰᠢᠭᠤ # Шулуун Хөвөөт Цагаан хошуу
+    expected: siluγun købegety caγan xosiγu
+  - source: ᠰᠢᠯᠤᠭᠤᠨ ᠬᠥᠬᠡ ᠬᠣᠰᠢᠭᠤ # Шулуун хөх хошуу
+    expected: siluγun køke xosiγu
+  - source: ᠤᠷᠠᠳ ᠤᠨ ᠳᠤᠮᠳᠠᠳᠤ ᠬᠣᠰᠢᠭᠤ # Урадын Дундад Хошуу
+    expected: urad-un dumdadu xosiγu
+  - source: ᠤᠷᠠᠳ ᠤᠨ ᠡᠮᠦᠨᠡᠳᠦ ᠬᠣᠰᠢᠭᠤ # Урадын Өмнөд Хошуу
+    expected: urad-un emynedy xosiγu
+  - source: ᠲᠣᠭᠲᠠᠬᠤ ᠰᠢᠶᠠᠨ # Тогтох шянь
+    expected: toγtaxu sijan
+  - source: ᠰᠥᠨᠡᠳ ᠵᠡᠭᠦᠨ ᠬᠣᠰᠢᠭᠤ # Sonid Left Banner
+    expected: søned zegyn xosiγu
+  - source: ᠰᠥᠨᠡᠳ ᠪᠠᠷᠠᠭᠤᠨ ᠬᠣᠰᠢᠭᠤ # Sonid Right Banner
+    expected: søned baraγun xosiγu
+  - source: ᠣᠩᠨᠢᠭᠤᠳ ᠬᠣᠰᠢᠭᠤ # Ongniud Banner
+    expected: ongniγud xosiγu
+  - source: ᠵᠠᠯᠠᠢᠳ ᠬᠣᠰᠢᠭᠤ # Jalaid Banner
+    expected: zalaid xosiγu
+  - source: ᠬᠠᠩᠭᠢᠨ ᠬᠣᠶᠢᠲᠤ ᠬᠣᠰᠢᠭᠤ # Hanggin Rear Banner
+    expected: xangγin xoitu xosiγu
+  - source: ᠵᠡᠭᠦᠨ ᠤᠵᠤᠮᠤᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ # East Ujimqin Banner
+    expected: zegyn uzumucin xosiγu
+  - source: ᠠᠷᠤ ᠬᠣᠷᠴᠢᠨ ᠬᠣᠰᠢᠭᠤ # Ar Horqin Banner
+    expected: aru xorcin xosiγu
+  - source: ᠠᠪᠠᠭ᠎ᠠ ᠬᠣᠰᠢᠭᠤ # Abag Banner
+    expected: abaγ-a xosiγu
+  - source: ᠪᠤᠷᠢᠶᠠᠳ
+    expected: burijad # Буриад
+  - source: ᠤᠯᠠᠭᠠᠨᠪᠠᠭᠠᠲᠤᠷ # Улаанбаатар
+    expected: ulaγanbaγatur
+  - source: ᠴᠢᠩᠭᠢᠰ ᠬᠠᠭᠠᠨ # Чингис Хаан
+    expected: cingγis xaγan
+
+map:
+  rules:
+    - pattern: \u182c(\u1821|u1822|\u1825|\u1826)
+      result: "k\\1"
+    - pattern: \u182d(\u1821|u1822|\u1825|\u1826)
+      result: "g\\1"
+    - pattern: \u1820\u1836\u1822
+      result: "ai"
+    - pattern: \u1821\u1836\u1822
+      result: "ei"
+    - pattern: \u1823\u1836\u1822
+      result: "oi"
+    - pattern: \u1824\u1836\u1822
+      result: "ui"
+
+  characters:
+    "ᠠ": "a"      # \u1820
+    "ᠡ": "e"      # \u1821
+    "ᠢ": "i"      # \u1822
+    "ᠣ": "o"      # \u1823
+    "ᠤ": "u"      # \u1824
+    "ᠥ": "ø"     # \u1825
+    "ᠦ": "y"     # \u1826
+    "ᠨ": "n"      # \u1828
+    "ᠩ": "ng"     # \u1829
+    "ᠬ": "x"      # \u182c
+    "ᠭ": "γ"      # \u182d
+    "ᠪ": "b"      # \u182a
+    "ᠫ": "p"      # \u182b
+    "ᠹ": "f"      # \u1839
+    "ᠰ": "s"      # \u1830
+    "ᠱ": "š"      # \u1831
+    "ᠲ": "t"      # \u1832
+    "ᠳ": "d"      # \u1833
+    "ᠯ": "l"      # \u182f
+    "ᠮ": "m"      # \u182e
+    "ᠴ": "c"      # \u1834
+    "ᠵ": "z"      # \u1835
+    "ᠶ": "j"      # \u1836
+    "ᠺ": "k"      # \u183a
+    "ᠷ": "r"      # \u1837
+    "ᠸ": "v"      # \u1838
+    "ᠾ": "h"     # \u183e
+    "᠁": "..."   # \u1801
+    "᠂": ","      # \u1802
+    "᠃": "."      # \u1803
+    "᠄": ":"      # \u1804
+    "\u180e": "-" # MVS
+    "\u202f": "-" # NNBSP