interscript 0.1.0 → 0.1.5

data/maps/alalc-aze-Cyrl-Latn-1997.yaml

@@ -0,0 +1,141 @@
+---
+authority_id: alalc
+id: 1997
+language: aze
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization Table -- Azerbaijani (1997)
+url: https://transliteration.eki.ee/pdf/Azerbaijani.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization Tables: Transliteration Schemes for Non-Roman Scripts. Randal K. Berry (ed.). Library of Congress, 1997.
+
+notes:
+  - "Ј ј replaced Й й in 1959 (Roman: y; ISO 9: j; ALA-LC: ĭ)."
+
+tests: # from internet
+  - source: Азәрбајҹан дили
+    expected: Azărbaı̐jan dili
+  - source: |
+      Бүтүн инсанлар ләјагәт вә һүгугларына ҝөрә азад вә бәрабәр доғулурлар.
+      Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
+    expected: |
+      Bu̇tu̇n insanlar lăı̐agăt vă ḣu̇guglaryna ġȯră azad vă bărabăr doghulurlar.
+      Onlaryn shu̇urlary vă vijdanlary var vă bir-birlărină mu̇nasibătdă gardashlyg ruḣunda davranmalydyrlar.
+  - source: |
+      Азәрбајҹан! Азәрбајҹан!
+      Еј гәһрәман өвладын шанлы Вәтәни!
+      Сәндән өтрү ҹан вермәјә ҹүмлә һазырыз!
+      Сәндән өтрү ган төкмәјә ҹүмлә гадириз!
+      Үчрәнҝли бајрағынла мәсуд јаша!
+      Үчрәнҝли бајрағынла мәсуд јаша!
+      Минләрлә ҹан гурбан олду,
+      Синән һәрбә мејдан олду!
+      Һүгугундан кечән әсҝәр,
+      Һәрә бир гәһрәман олду!
+      Сән оласан ҝүлүстан,
+      Сәнә һәр ан ҹан гурбан!
+      Сәнә мин бир мәһәббәт
+      Синәмдә тутмуш мәкан!
+      Намусуну һифз етмәјә,
+      Бајрағыны јүксәлтмәјә
+      Намусуну һифз етмәјә,
+      Ҹүмлә ҝәнҹләр мүштагдыр!
+      Шанлы Вәтән! Шанлы Вәтән!
+      Азәрбајҹан! Азәрбајҹан!
+      Азәрбајҹан! Азәрбајҹан!
+    expected: |
+      Azărbaı̐jan! Azărbaı̐jan!
+      Eı̐ găḣrăman ȯvladyn shanly Vătăni!
+      Săndăn ȯtru̇ jan vermăı̐ă ju̇mlă ḣazyryz!
+      Săndăn ȯtru̇ gan tȯkmăı̐ă ju̇mlă gadiriz!
+      U̇chrănġli baı̐raghynla măsud ı̐asha!
+      U̇chrănġli baı̐raghynla măsud ı̐asha!
+      Minlărlă jan gurban oldu,
+      Sinăn ḣărbă meı̐dan oldu!
+      Ḣu̇gugundan kechăn ăsġăr,
+      Ḣără bir găḣrăman oldu!
+      Săn olasan ġu̇lu̇stan,
+      Sănă ḣăr an jan gurban!
+      Sănă min bir măḣăbbăt
+      Sinămdă tutmush măkan!
+      Namusunu ḣifz etmăı̐ă,
+      Baı̐raghyny ı̐u̇ksăltmăı̐ă
+      Namusunu ḣifz etmăı̐ă,
+      Ju̇mlă ġănjlăr mu̇shtagdyr!
+      Shanly Vătăn! Shanly Vătăn!
+      Azărbaı̐jan! Azărbaı̐jan!
+      Azărbaı̐jan! Azărbaı̐jan!
+
+map:
+  characters:
+    '\u0410': 'A'       # А
+    '\u0411': 'B'       # Б
+    '\u0412': 'V'       # В
+    '\u0413': 'G'       # Г
+    '\u0492': 'Gh'      # Ғ
+    '\u0414': 'D'       # Д
+    '\u0415': 'E'       # Е
+    '\u04D8': "A\u0306" # Ә
+    '\u0416': 'Zh'      # Ж
+    '\u0417': 'Z'       # З
+    '\u0418': 'I'       # И
+    '\u042B': 'Y'       # Ы
+    '\u0408': "I\u0310" # Ј
+    '\u0419': 'Y'       # Й note[1]
+    '\u0419': 'Y'       # Й
+    '\u041A': 'K'       # К
+    '\u049C': "G\u0307" # Ҝ
+    '\u041B': 'L'       # Л
+    '\u041C': 'M'       # М
+    '\u041D': 'N'       # Н
+    '\u041E': 'O'       # О
+    '\u04E8': "O\u0307" # Ө
+    '\u041F': 'P'       # П
+    '\u0420': 'R'       # Р
+    '\u0421': 'S'       # С
+    '\u0422': 'T'       # Т
+    '\u0423': 'U'       # У
+    '\u04AE': "U\u0307" # Ү
+    '\u0424': 'F'       # Ф
+    '\u0425': 'Kh'      # Х
+    '\u04BA': "H\u0307" # Һ
+    '\u0427': 'Ch'      # Ч
+    '\u04B8': 'J'       # Ҹ
+    '\u0428': 'Sh'      # Ш
+   
+    '\u0430': 'a'       # а
+    '\u0431': 'b'       # б
+    '\u0432': 'v'       # в
+    '\u0433': 'g'       # г
+    '\u0493': 'gh'      # ғ
+    '\u0434': 'd'       # д
+    '\u0435': 'e'       # e
+    '\u04D9': "a\u0306" # ә
+    '\u0436': 'zh'      # ж
+    '\u0437': 'z'       # з
+    '\u0438': 'i'       # и
+    '\u044B': 'y'       # ы
+    '\u0458': "\u0131\u0310" # ј
+    '\u0439': 'y'       # й note[1]
+    '\u043A': 'k'       # к
+    '\u049D': "g\u0307" # ҝ
+    '\u043B': 'l'       # л
+    '\u043C': 'm'       # м
+    '\u043D': 'n'       # н
+    '\u043E': 'o'       # о
+    '\u04E9': "o\u0307" # ө
+    '\u043F': 'p'       # п
+    '\u0440': 'r'       # р
+    '\u0441': 's'       # с
+    '\u0442': 't'       # т
+    '\u0443': 'u'       # у
+    '\u04AF': "u\u0307" # ү
+    '\u0444': 'f'       # ф
+    '\u0445': 'kh'      # х
+    '\u04BB': "h\u0307" # һ
+    '\u0447': 'ch'      # ч
+    '\u04B9': 'j'       # ҹ
+    '\u0448': 'sh'      # ш
+
+    '\u2019': '\u2019'

data/maps/alalc-bel-cyrl-latn-1997.yaml

@@ -0,0 +1,125 @@
+---
+authority_id: alalc
+id: 1997
+language: bel
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization Table -- Byelorussian (1997)
+url: http://catdir.loc.gov/catdir/cpso/romanization/beloruss.pdf
+creation_date: 1997
+
+notes:
+  - Ґ letter found in Old Belarusian and in modern publications in Tarashkevitsa orthography. 
+  - Do not confuse with the digraph кг (also romanized as “kh”). Manual review may be needed when transcribing data in vernacular characters in order to distinguish х from кг. 
+  - The apostrophe (´) is not transliterated.
+  - Soft sign (prime) is USMARC hexadecimal code A7 ~ U+02B9 Unicode character
+
+tests:
+  # https://en.wikipedia.org/wiki/Romanization_of_Belarusian#Examples
+  # https://img.tyt.by/n/02/d/belorusskiy_translit.jpg - with issues
+  - source: Беларусь
+    expected: Belarusʹ
+  - source: Магілёў
+    expected: Mahili͡oŭ
+  - source: Лукашэнка
+    expected: Lukashėnka
+  - source: сям´я
+    expected: si͡ami͡a
+  - source: Уручча
+    expected: Uruchcha
+  - source: Барысаўскі тракт
+    expected: Barysaŭski trakt
+  - source: Усход
+    expected: Uskhod
+  - source: Маскоўская
+    expected: Maskoŭskai͡a
+  - source: Парк Чалюскінцаў
+    expected: Park Chali͡uskintsaŭ
+  - source: Акадэмія навук
+    expected: Akadėmii͡a navuk
+  - source: Плошча Якуба Коласа
+    expected: Ploshcha I͡Akuba Kolasa
+  - source: Плошча Перамогі
+    expected: Ploshcha Peramohi
+  - source: Кастрычніцкая
+    expected: Kastrychnitskai͡a
+  - source: Плошча Леніна
+    expected: Ploshcha Lenina
+  - source: Інстытут Культуры
+    expected: Instytut Kulʹtury
+
+map:
+  characters:
+    # Apostrophes
+    '\u00B4' : '' # official english Apostrophe
+    '\u02BC' : ''
+    '\u0027' : '' # from belarussian keyboard
+
+    # Characters
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'H'  # Г
+    '\u0490' : 'G'  # Ґ
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'E'  # Е
+    '\u0401' : "I\u0361O" # Ё : I͡O
+    '\u0416' : "Z\u0361H" # Ж : Z͡H
+    '\u0417' : 'Z'  # З
+    '\u0406' : 'I'  # І
+    '\u0419' : "\u012C" # Й : Ĭ
+    '\u041A' : 'K'  # К
+    '\u041B' : 'L'  # Л
+    '\u041C' : 'M'  # М
+    '\u041D' : 'N'  # Н
+    '\u041E' : 'O'  # О
+    '\u041F' : 'P'  # П
+    '\u0420' : 'R'  # Р
+    '\u0421' : 'S'  # С
+    '\u0422' : 'T'  # Т
+    '\u0423' : 'U'  # У
+    '\U040E' : "\u016C" # Ў : Ŭ
+    '\u0424' : 'F'  # Ф
+    '\u0425' : 'Kh' # Х
+    '\u0426' : 'Ts' # Ц
+    '\u0427' : 'Ch' # Ч
+    '\u0428' : 'Sh' # Ш
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : "\u02B9" # Ь : ʹ
+    '\u042D' : "\u0116" # Э : Ė
+    '\u042E' : "I\u0361U" # Ю : I͡U
+    '\u042F' : "I\u0361A" # Я : I͡A
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'h'  # г
+    '\u0491' : 'g'  # ґ
+    '\u0434' : 'd'  # д
+    '\u0435' : 'e'  # е
+    '\u0451' : "i\u0361o" # ё : i͡o
+    '\u0436' : "z\u0361h" # ж : z͡h
+    '\u0437' : 'z'  # з
+    '\u0456' : 'i'  # і
+    '\u0439' : "\u012D"  # й : ĭ
+    '\u043A' : 'k'  # к
+    '\u043B' : 'l'  # л
+    '\u043C' : 'm'  # м
+    '\u043D' : 'n'  # н
+    '\u043E' : 'o'  # о
+    '\u043F' : 'p'  # п
+    '\u0440' : 'r'  # р
+    '\u0441' : 's'  # с
+    '\u0442' : 't'  # т
+    '\u0443' : 'u'  # у
+    '\u045E' : "\u016D"  # ў : ŭ
+    '\u0444' : 'f'  # ф
+    '\u0445' : 'kh' # х
+    '\u0446' : 'ts' # Ц
+    '\u0447' : 'ch' # ч
+    '\u0448' : 'sh' # ш
+    '\u044B' : 'y'  # ы
+    '\u044C' : "\u02B9"  # ь : ʹ
+    '\u044D' : "\u0117"  # э : ė
+    '\u044E' : "i\u0361u" # ю : i͡u
+    '\u044F' : "i\u0361a" # я : i͡a

data/maps/alalc-ben-Beng-Latn-2017.yaml

@@ -0,0 +1,130 @@
+---
+authority_id: alalc
+id: 2017
+language: ben
+source_script: Beng
+destination_script: Latn
+name: Bengali Romanization, 2017
+url: https://www.loc.gov/catdir/cpso/romanization/bengali.pdf
+creation_date: 2017
+description: |
+  ALA-LC Romanization table for Bengali
+
+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 symbol ( ্ )
+      called hasanta or birāma.
+
+  - ব is used both as a labial and as a semivowel. When it occurs as the
+    second or subsequent consonant of a consonant cluster, it is
+    transliterated va. When ব is doubled, it is transliterated bba.
+
+  - Candrabindu before guttural, palatal, cerebral, and dental occlusives
+    is transliterated n̐. Before labials, sibilants, semivowels, the
+    aspirate, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, abagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "র্ক"
+    expected: "rka"
+  - source: "গ্র"
+    expected: "gra"
+  - source: "ত্য"
+    expected: "tya"
+
+map:
+  inherit: "un-ben-Beng-Latn-2016"
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'অ': 'a'
+    'ৠ': 'ṝ'
+    'আ': 'ā'
+    'ঌ': 'ḹ'
+    'ই': 'I'
+    'এ': 'e'
+    'ঈ': 'ī'
+    'ঐ': 'ai'
+    'উ': 'u'
+    'ও': 'o'
+    'ঊ': 'ū'
+    'ঔ': 'au'
+    'ঋ': 'ṛ'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ক': 'ka'
+    'খ': 'kha'
+    'গ': 'ga'
+    'ঘ': 'gha'
+    'ঙ': 'ṅa'
+
+    # Palatals
+    'চ': 'ca'
+    'ছ': 'cha'
+    'জ': 'ja'
+    'ঝ': 'jha'
+    'ঞ': 'ña'
+
+    # Cerebrals
+    'ট': 'ṭa'
+    'ঠ': 'ṭha'
+    'ড': 'ḍa'
+    'ড়': 'ṛa'
+    'ঢ': 'ḍha'
+    'ঢ়': 'ṛha'
+    'ণ': 'ṇa'
+
+    # Dentals
+    'ত': 'ta'
+    'ৎ': 't'
+    'থ': 'tha'
+    'দ': 'da'
+    'ধ': 'dha'
+    'ন': 'na'
+
+    # Labials
+    'প': 'pa'
+    'ফ': 'pha'
+    'ব': 'ba' # see Note 3
+    'ভ': 'bha'
+    'ম': 'ma'
+
+    # Semivowels
+    'য': 'ya'
+    'য়': 'ẏa'
+    'র': 'ra'
+    'ল': 'la'
+    'ব': 'ba' # see Note 3
+
+    # Sibilants
+    'শ': 'śa'
+    'ষ': 'sha'
+    'স': 'sa'
+
+    # Aspirate
+    'হ': 'ha'
+
+    # Anusvāra
+    ' ং': 'ṃ'
+
+    # Bisarga
+    ' ঃ': 'ḥ'
+
+    # Candrabindu (anunāsika) see note 4
+    '\u0981': 'n̐' # ঁ : n̐, m̐
+
+    # Abagraha (see Note 5)
+    'ऽ': '’' # (apostrophe)

data/maps/alalc-bul-Cyrl-Latn-1997.yaml

@@ -0,0 +1,94 @@
+---
+authority_id: alalc
+id: 1997
+language: bul
+source_script: Cyrl
+destination_script: Latn
+name: ALA-LC Romanization Table -- Bulgarian (1997)
+url: http://www.rechtertie.nl/databases/judd/downloads/Bulgarian.pdf
+creation_date: 1997
+
+notes:
+  - |
+    The letter Ъ in the initial and medial position is a vowel in Bulgarian and is romanized as ŭ.
+    It appears in the final position chiefly in texts published before 1945, in which it serves as
+    a hard sign and is romanized as ʺ.
+  - The letters Ѣ and Ѫ are found chiefly in texts published before the orthographic reform of 1945.
+
+tests:
+  # missing
+
+map:
+  rules:
+    # note[1]
+    - pattern: (?<=)\u042a(?=\b)
+      result: "\u02BA"
+    - pattern: (?<=)u044a(?=\b)
+      result: "\u02BA"
+
+  characters:
+    '\u0410': 'A'
+    '\u0411': 'B'
+    '\u0412': 'V'
+    '\u0413': 'G'
+    '\u0414': 'D'
+    '\u0415': 'E'
+    '\u0416': 'Zh'
+    '\u0417': 'Z'
+    '\u0418': 'I'
+    '\u0419': "I\u0306" # Ĭ
+    '\u041a': 'K'
+    '\u041b': 'L'
+    '\u041c': 'M'
+    '\u041d': 'N'
+    '\u041e': 'O'
+    '\u041f': 'P'
+    '\u0420': 'R'
+    '\u0421': 'S'
+    '\u0422': 'T'
+    '\u0423': 'U'
+    '\u0424': 'F'
+    '\u0425': 'Kh'
+    '\u0426': "T\u0361S"
+    '\u0427': 'Ch'
+    '\u0428': 'Sh'
+    '\u0429': 'Sht'
+    '\u042a': "U\u0306" # or ʺ check note[1]
+    '\u042c': '\u02B9'
+    '\u0462': "I\u0361E" # Ѣ check note [2]
+    '\u042e': "I\u0361U"
+    '\u042f': "I\u0361A"
+    '\u046A': "U\u0310" # Ѫ check note [2]
+
+    '\u0430': 'a'
+    '\u0431': 'b'
+    '\u0432': 'v'
+    '\u0433': 'g'
+    '\u0434': 'd'
+    '\u0435': 'e'
+    '\u0436': 'zh'
+    '\u0437': 'z'
+    '\u0438': 'i'
+    '\u0439': "i\u0306" # ĭ
+    '\u043a': 'k'
+    '\u043b': 'l'
+    '\u043c': 'm'
+    '\u043d': 'n'
+    '\u043e': 'o'
+    '\u043f': 'p'
+    '\u0440': 'r'
+    '\u0441': 's'
+    '\u0442': 't'
+    '\u0443': 'u'
+    '\u0444': 'f'
+    '\u0445': 'kh'
+    '\u0446': "t\u0361s"
+    '\u0447': 'ch'
+    '\u0448': 'sh'
+    '\u0449': 'sht'
+    '\u044a': "u\u0306" # or ʺ check note[1]
+    '\u044c': '\u02B9'
+    '\u0463': "i\u0361e" # ѣ check note [2]
+    '\u044e': "i\u0361u"
+    '\u044f': "i\u0361a"
+    '\u046B': "u\u0310" # ѫ check note [2]