interscript 0.1.6 → 2.1.0a9

data/maps/alalc-hin-Deva-Latn-2020.yaml

@@ -1,159 +0,0 @@
----
-authority_id: alalc
-id: 2020
-language: hin
-source_script: Deva
-destination_script: Latn
-name: Hindi Romanization, 2020
-url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
-creation_date: 2020
-description: |
-  ALA-LC Romanization table for Hindi
-
-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 subscript sign ( ◌् ) called halanta or
-       virāma.
-
-  - |
-    Exception: Anusvāra is transliterated by:
-
-    a) ṅ before gutturals,
-    b) ñ before palatals,
-    c) ṇ before cerebrals,
-    d) n before dentals, and
-    e) m before labials.
-
-  - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
-    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
-
-  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
-
-tests:
-  - source: "हम"
-    expected: "hama"
-  - source: "मीन"
-    expected: "maīna"
-  - source: "औसत"
-    expected: "ăusata"
-  - source: "माँऽऽऽ!"
-    expected: "maān̐’’’!"
-  - source: "माँ"
-    expected: "maām̐"
-
-
-
-map:
-
-  rules:
-    # note[4]
-    - pattern: (?<=)\u0901(?=\b)
-      result: "m̐"
-
-  characters:
-
-    # I. Vowels and Diphthongs (see Note 1)
-
-    'अ': 'a'
-    'आ': 'ā'
-    'इ': 'i'
-    'ई': 'ī'
-    'उ': 'u'
-    'ऊ': 'ū'
-    'ऋ': 'ṛ'
-    'ॠ': 'ṝ'
-    'ऌ': 'ḹ'
-    'ॳ': 'ĕ'
-    'ए': 'e'
-    'ॲ': 'ê'
-    'अै': 'ai'
-    'ऐ': 'ai'
-    'ऒ': 'ŏ'
-    'ओ': 'o'
-    'ऑ': 'ô'
-    'औ': 'ău'
-
-    # II. Consonants (see Note 2)
-    # Gutturals
-    'क': 'ka'
-    'ख': 'kha'
-    'ग': 'ga'
-    'घ': 'gha'
-    'ङ': 'ṅa'
-
-    # Palatals
-    'च': 'ca'
-    'छ': 'cha'
-    'ज': 'ja'
-    'झ': 'jha'
-    'ञ': 'ña'
-
-    # Cerebrals
-    'ट': 'ṭa'
-    'ठ': 'ṭha'
-    'ड': 'ḍa'
-    'ड़': 'ṛa'
-    'ढ': 'ḍha'
-    'ढ़': 'ṛha'
-    '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': 'ba'
-
-    # Sibilants
-    'श': 'śa'
-    'ष': 'sha'
-    'स': 'sa'
-
-    # Aspirate
-    'ह': 'ha'
-
-    # Anusvāra
-    'ं': 'ṃ'
-
-    # Bisarga
-    'ः ': 'ḥ'
-
-    # Anunāsika
-    'ँ': 'n̐' # ঁ : n̐, m̐
-
-    # Abagraha
-    'ऽ': '’' # (apostrophe)
-
-    # Medials # Needed for connecting constants
-    'ा': "ā"
-    'ि': "i"
-    'ी': "ī"
-    'ु': "u"
-    'ू': "ū"
-    'ृ': "ṛi"
-    'ॄ': "rī"
-    'े': "e"
-    'ॊ': "o"
-    'ौ': "au"

data/maps/alalc-kat-Geok-Latn-1997.yaml

@@ -1,111 +0,0 @@
----
-authority_id: alalc
-id: 1997
-language: kat
-source_script: Geok
-destination_script: Latn
-name: ALA-LC Georgian System (1997)
-url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
-creation_date: 1997
-confirmation_date: 1997
-description: |
-  Values are shown for the Khutsuri alphabet.
-
-notes:
-
-tests:
-
-  - source: ႼႨႢႬႨ
-    expected: CIGNI
-
-  - source: ⴜⴈⴂⴌⴈ
-    expected: cigni
-
-  - source: ႱႭႪႭႫႭႬ
-    expected: SOLOMON
-
-  - source: ⴑⴍⴊⴍⴋⴍⴌ
-    expected: solomon
-
-  - source: ႠႡႰႠჀႠႫ
-    expected: ABRAHAM
-
-map:
-  characters:
-    '\u10a0' : 'A' # Ⴀ
-    '\u10a1' : 'B' # Ⴁ
-    '\u10a2' : 'G' # Ⴂ
-    '\u10a3' : 'D' # Ⴃ
-    '\u10a4' : 'E' # Ⴄ
-    '\u10a5' : 'V' # Ⴅ
-    '\u10a6' : 'Z' # Ⴆ
-    '\u10a7' : 'Tʻ' # Ⴇ
-    '\u10a8' : 'I' # Ⴈ
-    '\u10a9' : 'K' # Ⴉ
-    '\u10aa' : 'L' # Ⴊ
-    '\u10ab' : 'M' # Ⴋ
-    '\u10ac' : 'N' # Ⴌ
-    '\u10ad' : 'O' # Ⴍ
-    '\u10ae' : 'P' # Ⴎ
-    '\u10af' : 'Ž' # Ⴏ
-    '\u10b0' : 'R' # Ⴐ
-    '\u10b1' : 'S' # Ⴑ
-    '\u10b2' : 'T' # Ⴒ
-    '\u10b3' : 'U' # Ⴓ
-    '\u10b4' : 'Pʻ' # Ⴔ
-    '\u10b5' : 'Kʻ' # Ⴕ
-    '\u10b6' : 'Ġ' # Ⴖ
-    '\u10b7' : 'Q' # Ⴗ
-    '\u10b8' : 'Š' # Ⴘ
-    '\u10b9' : 'Čʻ' # Ⴙ
-    '\u10ba' : 'Cʻ' # Ⴚ
-    '\u10bb' : 'Ż' # Ⴛ
-    '\u10bc' : 'C' # Ⴜ
-    '\u10bd' : 'Č' # Ⴝ
-    '\u10be' : 'X' # Ⴞ
-    '\u10bf' : 'J' # Ⴟ
-    '\u10c0' : 'H' # Ⴠ
-    '\u10c1' : 'Ē' # Ⴡ
-    '\u10c2' : 'Y' # Ⴢ
-    '\u10c3' : 'W' # Ⴣ
-    '\u10c4' : 'X̣' # Ⴤ
-    '\u10c5' : 'Ō' # Ⴥ
-
-    '\u2d00' : 'a' # ⴀ
-    '\u2d01' : 'b' # ⴁ
-    '\u2d02' : 'g' # ⴂ
-    '\u2d03' : 'd' # ⴃ
-    '\u2d04' : 'e' # ⴄ
-    '\u2d05' : 'v' # ⴅ
-    '\u2d06' : 'z' # ⴆ
-    '\u2d07' : 'tʻ' # ⴇ
-    '\u2d08' : 'i' # ⴈ
-    '\u2d09' : 'k' # ⴉ
-    '\u2d0a' : 'l' # ⴊ
-    '\u2d0b' : 'm' # ⴋ
-    '\u2d0c' : 'n' # ⴌ
-    '\u2d0d' : 'o' # ⴍ
-    '\u2d0e' : 'p' # ⴎ
-    '\u2d0f' : 'ž' # ⴏ
-    '\u2d10' : 'r' # ⴐ
-    '\u2d11' : 's' # ⴑ
-    '\u2d12' : 't' # ⴒ
-    '\u2d13' : 'u' # ⴓ
-    '\u2d14' : 'pʻ' # ⴔ
-    '\u2d15' : 'kʻ' # ⴕ
-    '\u2d16' : 'ġ' # ⴖ
-    '\u2d17' : 'q' # ⴗ
-    '\u2d18' : 'š' # ⴘ
-    '\u2d19' : 'čʻ' # ⴙ
-    '\u2d1a' : 'cʻ' # ⴚ
-    '\u2d1b' : 'ż' # ⴛ
-    '\u2d1c' : 'c' # ⴜ
-    '\u2d1d' : 'č' # ⴝ
-    '\u2d1e' : 'x' # ⴞ
-    '\u2d1f' : 'j' # ⴟ
-    '\u2d20' : 'h' # ⴠ
-    '\u2d21' : 'ē' # ⴡ
-    '\u2d22' : 'y' # ⴢ
-    '\u2d23' : 'w' # ⴣ
-    '\u2d24' : 'x̣' # ⴤ
-    '\u2d25' : 'ō' # ⴥ

data/maps/alalc-kat-Geor-Latn-1997.yaml

@@ -1,146 +0,0 @@
----
-authority_id: alalc
-id: 1997
-language: kat
-source_script: Geor
-destination_script: Latn
-name: ALA-LC Georgian System (1997)
-url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
-creation_date: 1997
-confirmation_date: 1997
-description: |
-  Values are shown for the older Khutsuri and the modern Mkhedruli alphabets.
-  There are no upper case letters in Mkhedruli.
-
-notes:
-
-tests:
-
-  - source: ხაოფსე
-    expected: xaopʻse
-
-  - source: ჭლოუ
-    expected: člou
-
-  - source: ჩოხულდი
-    expected: čʻoxuldi
-
-  - source: ქვემო ლინდა
-    expected: kʻvemo linda
-
-  - source: ტამკვაჩ იგვავერა
-    expected: tamkvačʻ igvavera
-
-  - source: სვანეთი
-    expected: svanetʻi
-
-  - source: საცხვარისი
-    expected: sacʻxvarisi
-
-  - source: მუხრან-თელეთი
-    expected: muxran-tʻeletʻi
-
-  - source: მუცდი
-    expected: mucʻdi
-
-  - source: ლეჩხუმი
-    expected: lečʻxumi
-
-  - source: ვერხნაია მწარა
-    expected: verxnaia mcara
-
-  - source: ეგრისის ქედი
-    expected: egrisis kʻedi
-
-  - source: დოჩარიფშა
-    expected: dočʻaripʻša
-
-  - source: ბოლოკო
-    expected: boloko
-
-  - source: აჭანდარა
-    expected: ačandara
-
-  - source: აუალიცა
-    expected: aualicʻa
-
-  - source: აკალამრა
-    expected: akalamra
-
-  - source: ლასილი
-    expected: lasili
-
-  - source: გუბაზეული
-    expected: gubazeuli
-
-  - source: ბაყაყი
-    expected: baqaqi
-
-  - source: ძროხა
-    expected: żroxa
-
-  - source: ჰაერი
-    expected: haeri
-
-  - source: ჟოლო
-    expected: žolo
-
-  - source: ჯართი
-    expected: jartʻi
-
-  - source: ღრმაღელე
-    expected: ġrmaġele
-
-map:
-  characters:
-    '\u10d0' : 'a' # ა
-    '\u10d1' : 'b' # ბ
-    '\u10d2' : 'g' # გ
-    '\u10d3' : 'd' # დ
-    '\u10d4' : 'e' # ე
-    '\u10d5' : 'v' # ვ
-    '\u10d6' : 'z' # ზ
-
-    '\u10f1' : 'ē' # ჱ
-
-    '\u10d7' : 'tʻ' # თ
-    '\u10d8' : 'i' # ი
-    '\u10d9' : 'k' # კ
-    '\u10da' : 'l' # ლ
-    '\u10db' : 'm' # მ
-    '\u10dc' : 'n' # ნ
-
-    '\u10f2' : 'y' # ჲ
-
-    '\u10dd' : 'o' # ო
-    '\u10de' : 'p' # პ
-    '\u10df' : 'ž' # ჟ
-    '\u10e0' : 'r' # რ
-    '\u10e1' : 's' # ს
-    '\u10e2' : 't' # ტ
-
-    '\u10f3' : 'w' # ჳ
-
-    '\u10e3' : 'u' # უ
-    '\u10e4' : 'pʻ' # ფ
-    '\u10e5' : 'kʻ' # ქ
-    '\u10e6' : 'ġ' # ღ
-    '\u10e7' : 'q' # ყ
-    '\u10e8' : 'š' # შ
-    '\u10e9' : 'čʻ' # ჩ
-    '\u10ea' : 'cʻ' # ც
-    '\u10eb' : 'ż' # ძ
-    '\u10ec' : 'c' # წ
-    '\u10ed' : 'č' # ჭ
-    '\u10ee' : 'x' # ხ
-
-    '\u10f4' : 'x̣' # ჴ
-
-    '\u10ef' : 'j' # ჯ
-    '\u10f0' : 'h' # ჰ
-
-    '\u10f5' : 'ō' # ჵ
-
-    '\u10f6' : 'f' # ჶ
-    '\u10f7' : 'ĕ' # ჷ
-    '\u10f8' : 'ʻ' # ჸ

data/maps/alalc-kor-Hang-Latn-1997.yaml

@@ -1,94 +0,0 @@
----
-authority_id: alalc
-id: 1997
-language: kor
-source_script: Hang
-destination_script: Latn
-name: ALA-LC Romanization Table -- Korean (1997)
-url: http://catdir.loc.gov/catdir/cpso/romanization/korean.pdf
-creation_date: 1997
-adoption_date:
-description:
-  "1. General Practice
-The Library of Congress will continue to follow the McCune-Reischauer system
-to romanize Korean with the exceptions noted in this document. See:
-Romanization of the Korean Language: Based upon its Phonetic Structure by
-G.M. McCune and E.O. Reischauer ([S.l.: s.n., 1939?), reprinted from the
-Transactions of the Korea Branch of the Royal Asiatic Society. Full text of the
-original document is available online from the National Library of Australia Web
-site: http://www.nla.gov.au/librariesaustralia/cjk/download/ras_1939.pdf"
-
-notes:
-
-
-tests:
-  - source: 은하-리
-    expected: "Ŭnha-ri"
-  - source: 은중-리
-    expected: "Ŭnjung-ni"
-  - source: 은장-령
-    expected: "Ŭnjang-nyŏng"
-  - source: 은혜-동
-    expected: "Ŭnhye-dong"
-  - source: 은호-리
-    expected: "Ŭnho-ri"
-  - source: 은행정
-    expected: "Ŭnhaengjŏng"
-  - source: 은행-동
-    expected: "Ŭnhaeng-dong"
-  - source: 은행-촌
-    expected: "Ŭnhaeng-ch’on"
-  - source: 원수
-    expected: "Wŏnsu"
-  - source: 원소리-고개
-    expected: "Wŏnsori-gogae"
-  - source: 원소참
-    expected: "Wŏnsoch’am"
-  - source: 원소-리
-    expected: "Wŏnso-ri"
-  - source: 원신-리
-    expected: "Wŏnsil-li"
-  - source: 난곡
-    expected: "Nan’gok"
-  - source: 난산-리
-    expected: "Nansal-li"
-  - source: 난직
-    expected: "Nanjik"
-  - source: 영곡
-    expected: "Yŏnggok"
-  - source: 윗두밀
-    expected: "Wittumil"
-  - source: 윗도심이
-    expected: "Wittosimi"
-  - source: 둔지
-    expected: "Tunji"
-  - source: 서승
-    expected: "Sŏsŭng"
-  # - source: 신촌
-  #   expected: "Sinch’on"
-  - source: 비암덕
-    expected: "Piamdŏk"
-  - source: 바위안
-    expected: "Pawian"
-  - source: 오송평
-    expected: "Osongp’yŏng"
-  - source: 그물목
-    expected: "Kŭmulmok"
-  - source: 구원정
-    expected: "Kuwŏnjŏng"
-  - source: 일하
-    expected: "Irha"
-  - source: 황우
-    expected: "Hwangu"
-  - source: 자작보
-    expected: "Chajakpo"
-  # - source: 비파1-동
-  #   expected: "Pip’a Il-tong"
-  - source: 문암 오-동
-    expected: "Munam O-dong"
-
-map:
-  character_separator: ""
-  word_separator: " "
-  title_case: True
-  inherit: "var-kor-Hang-Latn-mr-1939"