interscript 0.1.6 → 0.1.7

data/maps/din-tam-Taml-Latn-33903-2016.yaml

@@ -0,0 +1,213 @@
+---
+authority_id: din
+id: 33903-2016
+language: iso-639-2:tam
+source_script: Taml
+destination_script: Latn
+name: "DIN 33903:2016-02: Information und Dokumentation - Umschrift Tamil"
+url: https://www.beuth.de/de/norm/din-33903/247150527
+creation_date: 2018
+description: |
+  This standard specifies the transcription of the letters of the
+  Tamil alphabet in Latin letters. It is based on international
+  standards as well as on the preprint of the alphabetical tables,
+  which were published in 1976 with the introduction of the rules for
+  alphabetical cataloging. It can be used in all areas, but in
+  particular the aim is to standardize the library and publication
+  area.
+
+notes:
+  - |
+    Since the Tamil script is a syllabic script, the consonant -a inherent in the transliteration is always written, even in the final.
+
+  - |
+    A point above the consonant, the so-called "pulli", means in Tamil that the inherent -a is omitted:
+      கார்த்திகேயன் kārttikēyaṉ
+  - |
+    Tamil has no anusvara; in contrast to other South Asian scripts, the class nasal is always written.
+  - |
+    Tamil also has no ligatures.
+
+tests:
+  - source: "கார்த்திகேயன்"
+    expected: "kārttikēyaṉ"
+  - source: "௲"
+    expected: "1000"
+  - source: "இளைஞர்களின் உறுதியான மனநிலையை பிரதிபலிக்கிறது: நீட் தேர்வில் ௮௫-௯௦ சதவீத மாணவர்கள் பங்கேற்பு - ரமேஷ் பொக்ரியால்"
+    expected: "iḷaiñarkaḷiṉ uṟutiyāṉa maṉanilaiyai piratipalikkiṟatu: nīṭ tērvil 85-90 catavīta māṇavarkaḷ paṅkēṟpu - ramēṣ pokriyāl"
+  - source: "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்"
+    expected: "nāṭāḷumaṉṟattil 4 macōtākkaḷai etirkka kāṅkiras muṭivu - jeyarām ramēṣ"
+  - source: "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி"
+    expected: "karnāṭakāvil mēlum 9,894 pērukku korōṉā toṟṟu uṟuti"
+  - source: "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?"
+    expected: "aitarāpāttukku kaikoṭukkumā atiraṭi?"
+  - source: "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்"
+    expected: "amerikka ōpaṉ ṭeṉṉis: iṟutippōṭṭiyil ṭomiṉik-sverēv"
+  - source: "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்"
+    expected: "ai.pi.el. kirikkeṭṭil kaḷam iṟaṅkum amerikka vīrar"
+  - source: "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்"
+    expected: "amerikka ōpaṉ ṭeṉṉis; navōmi ocākā cāmpiyaṉ paṭṭam veṉṟār"
+  - source: "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்"
+    expected: "putiya kalvikkoḷkaikku etirppu: muṉṉāḷ tuṇaivēntarkaḷ 20 pēr piratamarukku kaṭitam"
+  - source: "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு"
+    expected: "inta āṇṭu ai.pi.el. kōppaiyai enta aṇi vellum? - keviṉ pīṭṭarcaṉ kaṇippu"
+  - source: "இந்திய எண்ணெய் கப்பலில் தீ: விபத்து குறித்த எச்சரிக்கையை கப்பல் அதிகாரிகள் புறக்கணித்தனர் - இலங்கை கோர்ட்டு தகவல்"
+    expected: "intiya eṇṇey kappalil tī: vipattu kuṟitta eccarikkaiyai kappal atikārikaḷ puṟakkaṇittaṉar - ilaṅkai kōrṭṭu takaval"
+
+map:
+
+  rules:
+    - pattern: ([க]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'k'
+    - pattern: ([ங]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṅ'
+    - pattern: ([ச]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'c'
+    - pattern: ([ஞ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ñ'
+    - pattern: ([ட]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṭ'
+    - pattern: ([ண]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṇ'
+    - pattern: ([த]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 't'
+    - pattern: ([ந]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'n'
+    - pattern: ([ப]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'p'
+    - pattern: ([ம]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'm'
+    - pattern: ([ய]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'y'
+    - pattern: ([ர]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'r'
+    - pattern: ([ல]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'l'
+    - pattern: ([ள]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ḷ'
+    - pattern: ([ழ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ḻ'
+    - pattern: ([வ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'v'
+    - pattern: ([ற]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṟ'
+    - pattern: ([ன]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṉ'
+    - pattern: ([ஜ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'j'
+    - pattern: ([ஶ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ś'
+    - pattern: ([ஷ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'ṣ'
+    - pattern: ([ஸ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 's'
+    - pattern: ([ஹ]=?)(?=[\u0BBE\u0BBF\u0BC0\u0BC1\u0BC2\u0BC6\u0BC7\u0BC8\u0BCA\u0BCB\u0BCC\u094B\u094C])
+      result: 'h'
+
+  characters:
+    'அ': 'a'
+    'ஆ': 'ā'
+    'ா': 'ā'
+
+    'இ': 'i'
+    'ி': 'i'
+
+    'ஈ': 'ī'
+    'ீ': 'ī'
+
+    'உ': 'u'
+    'ு': 'u'
+
+    'ஊ': 'ū'
+    'ூ': 'ū'
+
+    'ெ': "e"
+    'எ': 'e'
+
+    'ே': "ē"
+    'ஏ': 'ē'
+
+    'ஐ': 'ai'
+    'ை': "ai"
+
+    'ஒ': 'o'
+    'ொ': 'o'
+
+    'ோ': 'ō'
+    'ஓ': 'ō'
+
+    'ஔ': 'au'
+    'ௌ': 'au'
+
+    'க்': 'k'
+    'ங்': 'ṅ'
+    'ச்': 'c'
+    'ஞ்': 'ñ'
+    'ட்':  'ṭ'
+    'ண்':  'ṇ'
+    'த்': 't'
+    'ந்':  'n'
+    'ப்': 'p'
+    'ம்': 'm'
+    'ய்': 'y'
+    'ர்': 'r'
+    'ல்': 'l'
+    'ள்': 'ḷ'
+    'ழ்': 'ḻ'
+    'வ்': 'v'
+    'ற்': 'ṟ'
+    'ன்': 'ṉ'
+    'ஜ்': 'j'
+
+    'ஶ்': 'ś'
+    'ஷ்': 'ṣ'
+    'ஸ்': 's'
+    'ஹ்': 'h'
+
+
+    'க': 'ka'
+    'ங': 'ṅa'
+    'ஃ': 'ḵ'
+    'ச': 'ca'
+    'ஞ': 'ña'
+    'ட': 'ṭa'
+    'ண': 'ṇa'
+    'த': 'ta'
+    'ந': 'na'
+    'ப': 'pa'
+    'ம': 'ma'
+    'ய': 'ya'
+    'ர': 'ra'
+    'ல': 'la'
+    'ள': 'ḷa'
+    'ழ': 'ḻa'
+    'வ': 'va'
+    'ற': 'ṟa'
+    'ன': 'ṉa'
+    'ஜ': 'ja'
+    'ஶ': 'śa'
+    'ஷ': 'ṣa'
+    'ஸ': 'sa'
+    'ஹ': 'ha'
+
+    # Digits
+    '௧': '1'
+    '௨': '2'
+    '௩': '3'
+    '௪': '4'
+    '௫': '5'
+    '௬': '6'
+    '௭': '7'
+    '௮': '8'
+    '௯': '9'
+    '௦': '0'
+    '௰': '10'
+    '௱': '100'
+    '௲': '1000'
+
+
+
+
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner
+

data/maps/dos-nep-Deva-Latn-1997.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: bgnpcgn
 id: 1997
-language: nep
+language: iso-639-2:nep
 source_script: Deva
 destination_script: Latn
 name: Nepali Romanization, 1997
@@ -22,6 +22,20 @@ notes:
 tests:
   - source: "दुःख"
     expected: "duhkh"
+  - source: "पूरा भइसकेका विषयलाई माग बनाएर दबाब नदिनुस्"
+    expected: "pūrā bhiskekā viṣylāī māg bnāer dbāb ndinusa"
+  - source: "जाँदै छ कता नेपाली संगीत"
+    expected: "jā~dai chh ktā nepālī sṅgīt"
+  - source: "३५ मिनेटको यो डकुमेन्ट्री फिल्मले प्रथम पुरस्कारस्वरूप ग्रान्ड पिक्स अवार्ड पाएको हो"
+    expected: "35 mineṭko yo ḍkumenaṭarī philamle parthm pursakārsavrūp garānaḍ pikas avāraḍ pāeko ho"
+  - source: "विक्षनरी"
+    expected: "vikṣnrī"
+  - source: "रुसमा उत्कृष्ट"
+    expected: "rusmā utakṛiṣaṭ"
+  - source: "वाणिज्य"
+    expected: "vāṇijay"
+  - source: "अंक विद्या"
+    expected: "aṅk vidayā"
 
 map:
 

data/maps/elot-ell-Grek-Latn-743-1982-tl.yaml

@@ -1,7 +1,7 @@
 ---
-authority_id: un
-id: 1982
-language: ell
+authority_id: elot
+id: 1982-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: ELOT 743:1982 (transliteration)

data/maps/elot-ell-Grek-Latn-743-1982-ts.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: elot
-id: 1982
-language: ell
+id: 1982-ts
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: ELOT 743:1982

data/maps/elot-ell-Grek-Latn-743-2001-tl.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: elot
-id: 2001
-language: ell
+id: 2001-tl
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: ELOT 743:2001

data/maps/elot-ell-Grek-Latn-743-2001-ts.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: elot
-id: 2001
-language: ell
+id: 2001-ts
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: ELOT 743:2001

data/maps/ggg-kat-Geor-Latn-2002.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: ggg
 id: 2002
-language: kat
+language: iso-639-2:kat
 source_script: Geor
 destination_script: Latn
 name: Georgian State Department of Geodesy and Cartography 2002 System
+alias:
+  ogc11122:
+    code: kat_Geor2Latn_GGG_2002
+    description: Georgian State Department of Geodesy and Cartography 2002 System
 url: https://transliteration.eki.ee/pdf/Georgian.pdf
 creation_date: 1998
 confirmation_date: 2002

data/maps/gki-bel-Cyrl-Latn-1992.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: gki
 id: 1992
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: Byelorussian National Cartographic Authority 1992-3 System (based on GOST 1983)

data/maps/gki-bel-Cyrl-Latn-2000.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: gki
 id: 2000
-language: bel
+language: iso-639-2:bel
 source_script: Cyrl
 destination_script: Latn
 name: On approval of the Instructions for the transliteration of geographical names of the Republic of Belarus with letters of the Latin alphabet

data/maps/gost-rus-Cyrl-Latn-16876-71-1983.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: gost
 id: 1983
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: LETTERS TRANSLATION RULES OF KIRILLOVSKY ALPHABET WITH LETTERS OF LATIN ALPHABET GOST 16876-71
+alias:
+  ogc11122:
+    code: rus_Cyrl2Latn_GOST_1983
+    description: Russian GOST 1983 System, Main Administration of Geodesy and Cartography of the Former Soviet Union
 url: https://unstats.un.org/unsd/geoinfo/UNGEGN/docs/7th-uncsgn-docs/econf/7th_UNCSGN_econf.91_3_Add1.pdf
 creation_date: 1978
 confirmation_date: 1982-04-16
@@ -147,7 +151,7 @@ map:
     '\u042a' : '"'  # Ъ
     '\u042B' : 'Y'  # Ы
     '\u042C' : "\u00B4" # Ь => ’
-    '\u042D' : "E\u0300" # È
+    '\u042D' : "E\u0300" # Э => È
     '\u042E' : 'Ju' # Ю
     '\u042F' : 'Ja' # Я
 
@@ -181,6 +185,6 @@ map:
     '\u044A' : '"'  # ъ
     '\u044B' : 'y'  # ы
     '\u044C' : "\u00B4" # ь => ’
-    '\u044D' : "e\u0300" # è
+    '\u044D' : "e\u0300" # э => è
     '\u044E' : 'ju' # ю
     '\u044F' : 'ja' # я

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