interscript 0.1.3 → 0.1.9

data/maps/gost-rus-Cyrl-Latn-7.79-2000-2002.yaml

@@ -0,0 +1,157 @@
+---
+authority_id: gost
+id: 2002
+language: iso-639-2:rus
+source_script: Cyrl
+destination_script: Latn
+name: GOST 7.79-2000 System of standards for information, librarianship and publishing. Rules for transliteration of Cyrillic letters in the Latin alphabet
+url: https://gostexpert.ru/gost/gost-7.79-2000
+creation_date: 2002
+confirmation_date: 2002-02-12
+adoption_date: 2002-02-12
+description: |
+  This standard applies to the rules of transliteration by means of the Latin alphabet of individual letters,
+  words, expressions, as well as related texts in languages ​​whose writing is based on the Cyrillic alphabet.
+  The rules in accordance with this standard are applied wherever it is required to provide an unambiguous
+  representation of the Cyril text in Latin letters and the possibility of algorithmic recovery of the text
+  in the original Cyrillic notation, in particular when transferring documents over computer networks.
+  This standard does not apply to the rules for the transmission of the sound appearance of words written in
+  Cyrillic in Latin letters.
+
+tests:
+  - source: адрес
+    expected: adres
+  - source: баба
+    expected: baba
+  - source: вы
+    expected: vy
+  - source: голова
+    expected: golova
+  - source: да
+    expected: da
+  - source: еда
+    expected: eda
+  - source: ёлка
+    expected: ëlka
+  - source: журнал
+    expected: žurnal
+  - source: звезда
+    expected: zvezda
+  - source: книга
+    expected: kniga   
+  - source: первый
+    expected: pervyj
+  - source: как
+    expected: kak  
+  - source: липа
+    expected: lipa 
+  - source: муж
+    expected: muž 
+  - source: нижний
+    expected: nižnij
+  - source: общество
+    expected: obŝestvo
+  - source: пара
+    expected: para
+  - source: рыба
+    expected: ryba
+  - source: сестра
+    expected: sestra
+  - source: товарищ
+    expected: tovariŝ
+  - source: утро
+    expected: utro
+  - source: физика
+    expected: fizika
+  - source: химический
+    expected: himičeskij
+  - source: центр
+    expected: centr
+  - source: часы
+    expected: časy
+  - source: школа
+    expected: škola
+  - source: щит
+    expected: ŝit
+  - source: съезд
+    expected: s"ezd
+  - source: был
+    expected: byl
+  - source: альбом
+    expected: al´bom
+  - source: это
+    expected: èto
+  - source: южный
+    expected: ûžnyj
+  - source: яма
+    expected: âma
+
+map:
+  characters:
+    '\u0410' : 'A'  # A
+    '\u0411' : 'B'  # Б
+    '\u0412' : 'V'  # B
+    '\u0413' : 'G'  # Г
+    '\u0414' : 'D'  # Д
+    '\u0415' : 'E'  # Е
+    '\u0401' : "\u00CB" # Ё
+    '\u0416' : 'Ž'  # Ж
+    '\u0417' : 'Z'  # З
+    '\u0418' : "I"  # И
+    '\u0419' : 'J'  # Й
+    '\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
+    '\u0424' : 'F'  # Ф
+    '\u0425' : 'H'  # Х
+    '\u0426' : 'C'  # Ц
+    '\u0427' : 'Č'  # Ч
+    '\u0428' : 'Š'  # Ш
+    '\u0429' : 'Ŝ'  # Щ
+    '\u042a' : '"'  # Ъ
+    '\u042B' : 'Y'  # Ы
+    '\u042C' : "\u00B4" # Ь => ’
+    '\u042D' : "E\u0300" # Э => È
+    '\u042E' : 'Û' # Ю
+    '\u042F' : 'Â' # Я
+
+    '\u0430' : 'a'  # а
+    '\u0431' : 'b'  # б
+    '\u0432' : 'v'  # в
+    '\u0433' : 'g'  # г
+    '\u0434' : 'd'  # д
+    '\u0435' : 'e'  # е
+    '\u0451' : "\u00EB" # ё
+    '\u0436' : 'ž'  # ж
+    '\u0437' : 'z'  # з
+    '\u0438' : 'i'  # и
+    '\u0439' : 'j'  # й
+    '\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
+    '\u0444' : 'f'  # ф
+    '\u0445' : 'h'  # х
+    '\u0446' : 'c'  # ц
+    '\u0447' : 'č'  # ч
+    '\u0448' : 'š'  # ш
+    '\u0449' : 'ŝ'  # щ
+    '\u044A' : '"'  # ъ
+    '\u044B' : 'y'  # ы
+    '\u044C' : "\u00B4" # ь => ’
+    '\u044D' : "e\u0300" # э => è
+    '\u044E' : 'û' # ю
+    '\u044F' : 'â' # я

data/maps/hk-yue-Hani-Latn-1888.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: hk
 id: 1888
-language: yue
+language: iso-639-3:yue
 source_script: Hani
 destination_script: Latn
 name: Hong Kong Government Cantonese Romanisation

data/maps/icao-bel-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Belorussian Cyrillic to Latin
@@ -134,8 +134,3 @@ map:
     "\u0457": "i"    # ї
     "\u0453": "g"    # ѓ
     "\u0456": "i"     # і
-
-
-
-
-

data/maps/icao-bul-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Bulgarian Cyrillic to Latin
@@ -116,7 +116,3 @@ map:
     "\u0454": "ie"    # є
     "\u0457": "i"     # ї
     "\u0453": "g"     # ѓ
-
-
-
-

data/maps/{icao-per-Arab-Latn-9303.yaml → icao-fas-Arab-Latn-9303.yaml}

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: per
+language: iso-639-2:fas
 source_script: Arab
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Persian Arabic to Latin
@@ -101,4 +101,3 @@ map:
     "\u06D0": "Y"    # ې
     "\u06D2": "XYB"  # ے
     "\u06D3": "XBE"  # ۓ
-

data/maps/icao-heb-Hebr-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: heb
+language: iso-639-2:heb
 source_script: Hebr
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Hebrew to Latin

data/maps/icao-mkd-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: mkd
+language: iso-639-2:mkd
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Macedonian Cyrillic to Latin

data/maps/icao-rus-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Russian Cyrillic to Latin
@@ -115,4 +115,3 @@ map:
     "\u0454": "ie"   # є
     "\u0457": "i"    # ї
     "\u0453": "g"    # ѓ
-

data/maps/icao-srp-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: srp
+language: iso-639-2:srp
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Serbian Cyrillic to Latin

data/maps/icao-ukr-Cyrl-Latn-9303.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: icao
 id: 9303
-language: ukr
+language: iso-639-2:ukr
 source_script: Cyrl
 destination_script: Latn
 name: ICAO Doc 9303 Machine Readable Travel Documents Part 3 -- Ukranian Cyrillic to Latin
@@ -117,4 +117,3 @@ map:
     "\u0454": "ie"   # є
     "\u0457": "i"    # ї
     "\u0453": "g"    # ѓ
-

data/maps/iso-ara-Arab-Latn-233-1984.yaml

@@ -0,0 +1,323 @@
+---
+authority_id: iso
+id: 233-1984
+language: iso-639-2:ara
+source_script: Arab
+destination_script: Latn
+name: ISO 233:1984 Documentation — Transliteration of Arabic characters into Latin characters
+url:
+  - https://www.iso.org/standard/4117.html
+  - http://transliteration.eki.ee/pdf/Arabic_2.2.pdf
+  - http://www.eki.ee/wgrs/rom1_ar.pdf
+creation_date: 1984
+confirmation date: 2018-06
+description: |
+  Is one of a series of International Standards dealing with
+  the conversion of systems of writing, following the
+  principles of stringent conversion in order to permit
+  international information exchange. Its aim is to provide a
+  means for international communication of written messages
+  in a form which permits the automatic transmission and
+  reconstitution of these by men or machines. Cancels and
+  replaces ISO Recommendation R 233-1961
+notes:
+  - |
+    The transliteration ISO 233:1984 WRT ara-arab-latn-2017 gives every character and diacritical mark a unique
+    equivalent and e.g. long vowels in Arabic ā, ī and ū are consequently written a’, iy and uw
+    respectively in the ISO transliteration. Other main correspondences
+    ث is ṯ instead of th
+    ج is ǧ instead of j
+    ح is ḥ instead of ẖ
+    خ is ẖ instead of kh
+    ذ is ḏ instead of dh
+    ش is š instead of sh
+    ص is ṣ instead of s̱
+    ض is ḍ instead of ḏ
+    ط is ṭ instead of ṯ
+    ظ is ẓ instead of d͟h
+    غ is ġ instead of gh
+    ة is ẗ instead of h/t
+    ى is ỳ
+    ـِي is iy instead of iy
+    ـُو is uw instead of ū
+    ـَا is a’ instead of ā
+    ـَى is aỳ instead of á
+
+tests:
+
+  - source: مِصر
+    expected: Miṣr
+
+  - source: قَطَر
+    expected: Qaṭar
+
+  - source: الجُمهُورِيَّة العِرَاقِيَّة
+    expected: Al Ǧumhuwriyaẗ al ‘Ira’qiyaẗ
+
+  - source: جُمهُورِيَّة مِصر العَرَبِيَّة
+    expected: Ǧumhuwriyaẗ Miṣr al ‘Arabiyaẗ
+
+  - source: الرِيَاض
+    expected: Ar Riya’ḍ
+
+  - source: الشارِقة
+    expected: Aš Šâriqaẗ
+
+map:
+  postrules:
+    - pattern: (?<=\b)(?<!\b[‘|’|'])[\u0061-\uFFFF]
+      result: "upcase"
+    # don't capitalize defined article in the middle of a sentence
+    - pattern : ' At T'  # الت
+      result: ' at T'
+    - pattern : ' Aṯ Ṯ'  # الث
+      result: ' aṯ Ṯ'
+    - pattern : ' Ad D' # الد
+      result: ' ad D'
+    - pattern : ' Aḏ Ḏ'  # الذ
+      result: ' aḏ Ḏ'
+    - pattern : ' Ar R' # الر
+      result: ' ar R'
+    - pattern : ' Az Z'  # الز
+      result: ' az Z'
+    - pattern : ' As S' # الس
+      result: ' as S'
+    - pattern : ' Aš Š' # الش
+      result: ' aš Š'
+    - pattern : ' Aṣ Ṣ'  # الص
+      result: ' aṣ Ṣ'
+    - pattern : ' Aḍ Ḍ'  # الض
+      result: ' aḍ Ḍ'
+    - pattern : ' Aṭ Ṭ'  # الط
+      result: ' aṭ Ṭ'
+    - pattern : ' Aẓ Ẓ' # الظ
+      result: ' aẓ Ẓ'
+    - pattern : ' Al L'  # الل
+      result: ' al L'
+    - pattern : ' An N'  # الن
+      result: ' an N'
+    - pattern: " Al " # ال
+      result: " al "
+
+  characters:
+
+    # pointing
+    '\u064e' : 'a' # َ fatha
+    '\u064e(?=\u0629)' : '' # َ fatha followed by ta' marboota
+    '\u0650' : 'i' # ِ kasra
+    '\u064f' : 'u' # ُ damma
+    '\u0652' : ''  # ْ sokoon, see note A below
+
+    # special pointed letters
+    # special pointed letters
+    '\u0639\u064e' : '‘a'  # عَ
+    '\u0639\u0650' : '‘i'  # عِ
+    '\u0639\u064f' : '‘ū'  # عُ
+    # handle MacOS regex difference
+    '\u0639\u064f\u0648' : '‘ū'  # عُو damma followed by و
+
+    '\u0650\u064a' : 'iy' # ـِي kasra followed by ي
+    '\u0650\u064a\u0651\u064e' : 'iy' # ـِيَّ
+    '\u0650\u064a(?=\u064e|u064f)' : 'iy' # ـِي kasra followed by ي
+    '\u064e\u0627' : 'a’'  # ـَا fatha followed by ا
+    '\u064e\u0649' : 'aỳ'  # ـَى fatha followed by ى which is ا not ي
+    '\u064f\u0648' : 'uw'  # ـُو damma followed by و
+    '\u064e\u0648\u0652' : 'aw'  # ـَوْ
+    '\u064e\u064a\u0652' : 'ay'  # ـَيْ
+
+    # Sun letters
+
+    '\b\u0627\u0644\u062a' : 'at t'  # الت
+    '\b\u0627\u0644\u062b' : 'aṯ ṯ'  # الث
+    '\b\u0627\u0644\u062f' : 'ad d' # الد
+    '\b\u0627\u0644\u0630' : 'aḏ ḏ'  # الذ
+    '\b\u0627\u0644\u0631' : 'ar r' # الر
+    '\b\u0627\u0644\u0632' : 'az z'  # الز
+    '\b\u0627\u0644\u0633' : 'as s' # الس
+    '\b\u0627\u0644\u0634' : 'aš š' # الش
+    '\b\u0627\u0644\u0635' : 'aṣ ṣ'  # الص
+    '\b\u0627\u0644\u0636' : 'aḍ ḍ'  # الض
+    '\b\u0627\u0644\u0637' : 'aṭ ṭ'  # الط
+    '\b\u0627\u0644\u0638' : 'aẓ ẓ' # الظ
+    '\b\u0627\u0644\u0644' : 'al l'  # الل
+    '\b\u0627\u0644\u0646' : 'an n'  # الن
+
+    # ta' marboota in iso-233-1984 is all the same `aẗ`
+    '\u0629' : 'aẗ' # ة in the middle of the sentence
+
+    # Shadda
+
+
+    '\u0628\u0651' : 'bb'  # ب
+    '\u062a\u0651' : 'tt'  # ت
+    '\u062b\u0651' : 'ṯṯ'  # ث
+    '\u062c\u0651' : 'ǧǧ'  # ج
+    '\u062d\u0651' : 'ḥḥ' # ح
+    '\u062e\u0651' : 'ẖẖ'  # خ
+    '\u062f\u0651' : 'dd'  # د
+    '\u0630\u0651' : 'ḏḏ'  # ذ
+    '\u0631\u0651' : 'rr'  # ر
+    '\u0632\u0651' : 'zz'  # ز
+    '\u0633\u0651' : 'ss'  # س
+    '\u0634\u0651' : 'šš'  # ش
+    '\u0635\u0651' : 'ṣṣ'  # ص
+    '\u0636\u0651' : 'ḍḍ'  # ض
+    '\u0637\u0651' : 'ṭṭ'  # ط
+    '\u0638\u0651' : 'ẓẓ'  # ظ
+    '\u063a\u0651' : 'ġġ'  # غ
+    '\u0641\u0651' : 'ff'  # ف
+    '\u0642\u0651' : 'qq'  # ق
+    '\u0643\u0651' : 'kk'  # ك
+    '\u0644\u0651' : 'll'  # ل
+    '\u0645\u0651' : 'mm'  # م
+    '\u0646\u0651' : 'nn'  # ن
+    '\u0647\u0651' : 'hh'  # ه
+    '\u0648\u0651' : 'ww'  # و
+    '\u064a\u0651' : 'yy'  # ي
+
+
+    '\u0622' : '’â'  # آ
+
+    '\u0627' : 'â'  # ا
+
+    '\u0649' : 'ỳ'  # ى
+
+    '\u0626' : "'" # ئ
+
+
+    '\u0621' : # ء
+       - '’'
+       - '' # see note A
+
+    '\u0623' : 'a'  # أ
+
+    # See note B
+    '\b\u0627\u0644' : 'al '  # ال
+    # '\uFE8E' : ''  # ﺎ
+
+    '\u0628' : 'b'  # ب
+    '\uFE91' : 'b'  # ﺑ
+    '\uFE92' : 'b'  # ﺒ
+    '\uFE90' : 'b'  # ﺐ
+
+    # See note C
+    '\u062a' : 't'  # ت
+    '\ufe97' : 't'  # ﺗ
+    '\ufe98' : 't'  # ﺘ
+    '\ufe96' : 't'  # ﺖ
+
+    '\u062b' : 'ṯ'  # ث
+    '\ufe9b' : 'ṯ'  # ﺛ
+    '\ufe9c' : 'ṯ'  # ﺜ
+    '\ufe9a' : 'ṯ'  # ﺚ
+
+    '\u062c' : 'ǧ'  # ج
+    '\ufe9f' : 'ǧ'  # ﺟ
+    '\ufea0' : 'ǧ'  # ﺠ
+    '\ufe9e' : 'ǧ'  # ﺞ
+
+    '\u062d' : 'ḥ' # ح
+    '\ufea3' : 'ḥ' # ﺣ
+    '\ufea4' : 'ḥ' # ﺤ
+    '\ufea2' : 'ḥ' # ﺢ
+
+    '\u062e' : 'ẖ'  # خ
+    '\ufea7' : 'ẖ'  # ﺧ
+    '\ufea8' : 'ẖ'  # ﺨ
+    '\ufea6' : 'ẖ'  # ﺦ
+
+    '\u062f' : 'd'  # د
+    '\ufeaa' : 'd'  # ﺪ
+
+    '\u0630' : 'ḏ'  # ذ
+    '\ufeac' : 'ḏ'  # ﺬ
+
+    '\u0631' : 'r'  # ر
+    '\ufeae' : 'r'  # ﺮ
+
+    '\u0632' : 'z'  # ز
+    '\ufeb0' : 'z'  # ﺰ
+
+    '\u0633' : 's'  # س
+    '\ufeb3' : 's'  # ﺳ
+    '\ufeb4' : 's'  # ﺴ
+    '\ufeb2' : 's'  # ﺲ
+
+    '\u0634' : 'š'  # ش
+    '\ufeb7' : 'š'  # ﺷ
+    '\ufeb8' : 'š'  # ﺸ
+    '\ufeb6' : 'š'  # ﺶ
+
+    '\u0635' : 'ṣ'  # ص
+    '\ufebb' : 'ṣ'  # ﺻ
+    '\ufebc' : 'ṣ'  # ﺼ
+    '\ufeba' : 'ṣ'  # ﺺ
+
+    '\u0636' : 'ḍ'  # ض
+    '\ufebf' : 'ḍ'  # ﺿ
+    '\ufec0' : 'ḍ'  # ﻀ
+    '\ufebe' : 'ḍ'  # ﺾ
+
+    '\u0637' : 'ṭ'  # ط
+    '\ufec3' : 'ṭ'  # ﻃ
+    '\ufec4' : 'ṭ'  # ﻄ
+    '\ufec2' : 'ṭ'  # ﻂ
+
+    '\u0638' : 'ẓ'  # ظ
+    '\ufec7' : 'ẓ'  # ﻇ
+    '\ufec8' : 'ẓ'  # ﻈ
+    '\ufec6' : 'ẓ'  # ﻆ
+
+    '\u0639' : '‘'  # ع
+    '\ufecb' : '‘'  # ﻋ
+    '\ufecc' : '‘'  # ﻌ
+    '\ufeca' : '‘'  # ﻊ
+
+    '\u063a' : 'ġ'  # غ
+    '\ufecf' : 'ġ'  # ﻏ
+    '\ufed0' : 'ġ'  # ﻐ
+    '\ufece' : 'ġ'  # ﻎ
+
+    '\u0641' : 'f'  # ف
+    '\ufed3' : 'f'  # ﻓ
+    '\ufed4' : 'f'  # ﻔ
+    '\ufed2' : 'f'  # ﻒ
+
+    '\u0642' : 'q'  # ق
+    '\ufed7' : 'q'  # ﻗ
+    '\ufed8' : 'q'  # ﻘ
+    '\ufed6' : 'q'  # ﻖ
+
+    '\u0643' : 'k'  # ك
+    '\ufedb' : 'k'  # ﻛ
+    '\ufedc' : 'k'  # ﻜ
+    '\ufeda' : 'k'  # ﻚ
+
+    '\u0644' : 'l'  # ل
+    '\ufedf' : 'l'  # ﻟ
+    '\ufee0' : 'l'  # ﻠ
+    '\ufede' : 'l'  # ﻞ
+
+    '\u0645' : 'm'  # م
+    '\ufee3' : 'm'  # ﻣ
+    '\ufee4' : 'm'  # ﻤ
+    '\ufee2' : 'm'  # ﻢ
+
+    '\u0646' : 'n'  # ن
+    '\ufee7' : 'n'  # ﻧ
+    '\ufee8' : 'n'  # ﻨ
+    '\ufee6' : 'n'  # ﻦ
+
+    # See note C
+    '\u0647' : 'h'  # ه
+    '\ufeeb' : 'h'  # ﻫ
+    '\ufeec' : 'h'  # ﻬ
+    '\ufeea' : 'h'  # ﻪ
+
+    '\u0648' : 'w'  # و
+    '\ufeee' : 'w'  # ﻮ
+
+    '\u064a' : 'y'  # ي
+    '\ufef3' : 'y'  # ﻳ
+    '\ufef4' : 'y'  # ﻴ
+    '\ufef1' : 'y'  # ﻱ