interscript 0.1.7 → 0.1.9

data/maps/alalc-tel-Telu-Latn-1997.yaml

@@ -0,0 +1,284 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:tel
+source_script: Telu
+destination_script: Latn
+name: Telugu Romanization, 1997
+alias:
+  ogc11122:
+    code: tel_Telu2Latn_ALA_1997
+    description: Telugu ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/telugu.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Telugu
+
+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 superscript sign ( ౬ ) called valapalagilaka.
+  - |
+    Exception: Sunna is transliterated by:
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+  - |
+    Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m
+
+tests:
+  - source: "తమిళనాడు"
+    expected: "tamiḷanāḍu"
+  - source: "తంటికొండ ఘటన: ఆగని మృత్యుఘోష"
+    expected: "taṃṭikoṇḍa ghaṭana: āgani mṛtayughŏṣa"
+  - source: "మళ్లీ వివాదం: అమితాబ్‌పై కేసు"
+    expected: "maḷalī vivādaṃ: amitābapai kēsu"
+  - source: "‘వరద సాయం పేరుతో వైట్ కాలర్ దోపిడీ’"
+    expected: "‘varada sāyaṃ pērutŏ vaiṭa kālara dŏpiḍī’"
+  - source: "రెండో విడత జీఎస్టీ పరిహారం"
+    expected: "reṃḍŏ viḍata jīesaṭī parihāraṃ"
+  - source: "నితీష్‌ కుమార్‌ అధ్యాయం ముగిసినట్లేనా?!"
+    expected: "nitīṣa kumāra adhayāyaṃ mugisinaṭalēnā?!"
+  - source: "వారిపై జీవితాంతం నిషేధం విధించండి!"
+    expected: "vāripai jīvitāntaṃ niṣēdhaṃ vidhiñcaṃḍi!"
+  - source: "మరో లాక్‌డౌన్‌ వల్ల అన్నీ అనర్థాలే!"
+    expected: "marŏ lākaḍauna valala ananī anarathālē!"
+  - source: "జెసిండా మరో సంచలనం"
+    expected: "jesiṃḍā marŏ sañcalanaṃ"
+  - source: "స్వీయ నిర్బంధంలోకి డబ్ల్యూహెచ్‌ఓ డైరెక్టర్‌"
+    expected: "savīya nirabandhaṃlŏki ḍabalayūhecaō ḍairekaṭara"
+  - source: "కరోనాపై యుద్ధంలో సమిధలు"
+    expected: "karŏnāpai yudadhaṃlŏ samidhalu"
+  - source: "అమెరికా ఎన్నికలు: ‘పెద్దన్న’ ఎవరో?!"
+    expected: "amerikā enanikalu: ‘pedadanana’ evarŏ?!"
+  - source: "౪౬౨౬౯"
+    expected: "46269"
+
+map:
+
+  rules:
+    # rule II
+    - pattern: ([క]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'k'
+    - pattern: ([ఖ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'kh'
+    - pattern: ([గ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'g'
+    - pattern: ([ఘ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'gh'
+    - pattern: ([ఙ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṅ'
+    - pattern: ([చ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'c'
+    - pattern: ([ౘ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ĉ'
+    - pattern: ([ఛ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ch'
+    - pattern: ([జ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'j'
+    - pattern: ([ౙ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ĵ'
+    - pattern: ([ఝ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'jh'
+    - pattern: ([ఞ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ñ'
+    - pattern: ([ట]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṭ'
+    - pattern: ([ఠ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṭh'
+    - pattern: ([డ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ḍ'
+    - pattern: ([ఢ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ḍh'
+    - pattern: ([ణ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṇ'
+    - pattern: ([త]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  't'
+    - pattern: ([థ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'th'
+    - pattern: ([ద]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'd'
+    - pattern: ([ధ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'dh'
+    - pattern: ([న]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'n'
+    - pattern: ([ప]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'p'
+    - pattern: ([ఫ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ph'
+    - pattern: ([బ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'b'
+    - pattern: ([భ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'bh'
+    - pattern: ([మ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'm'
+    - pattern: ([య]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'y'
+    - pattern: ([ర]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'r'
+    - pattern: ([ఱ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṛ'
+    - pattern: ([ల]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'l'
+    - pattern: ([ళ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ḷ'
+    - pattern: ([వ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'v'
+    - pattern: ([శ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ś'
+    - pattern: ([ష]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'ṣ'
+    - pattern: ([స]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  's'
+    - pattern: ([హ]=?)(?=[\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c])
+      result:  'h'
+
+    # rule III
+    - pattern: \u0C02(?=[కఖగఘఙ])
+      result: ṅ
+    - pattern: \u0C02(?=[చౘఛజౙఝఞ])
+      result: ñ
+    - pattern: \u0C02(?=[టఠడఢణ])
+      result: ṇ
+    - pattern: \u0C02(?=[తథదధన])
+      result: n
+    - pattern: \u0C02(?=[పఫబభమ])
+      result: m
+
+    # rule IV
+    - pattern: \u0C01(?=[కఖగఘఙచౘఛజౙఝఞటఠడఢణతథదధన])    # before guttural, palatal, cerebral, and dental
+      result: n̐
+
+  characters:
+
+    'అ': 'a'
+    'ఆ': 'ā'
+    'ఇ': 'i'
+    'ఈ': 'ī'
+    'ఉ': 'u'
+    'ఊ': 'ū'
+    'ఋ': 'ṛ'
+    'ౠ': 'ṝ'
+    'ఌ': 'ḻ'
+    'ఎ': 'e'
+    'ఏ': 'ē'
+    'ఐ': 'ai'
+    'ఒ': 'o'
+    'ఓ': 'ō'
+    'ఔ': 'au'
+
+    # Gutturals
+    'క': 'ka'
+    'ఖ': 'kha'
+    'గ': 'ga'
+    'ఘ': 'gha'
+    'ఙ': 'ṅa'
+
+    # Palatals
+    'చ': 'ca'
+    'ౘ': 'ĉa'
+    'ఛ': 'cha'
+    'జ': 'ja'
+    'ౙ': 'ĵa'
+    'ఝ': 'jha'
+    'ఞ': 'ña'
+
+    # Cerebrals
+    'ట':  'ṭa'
+    'ఠ':  'ṭha'
+    'డ':  'ḍa'
+    'ఢ':  'ḍha'
+    'ణ':  'ṇa'
+
+    # Dentals
+    'త': 'ta'
+    'థ': 'tha'
+    'ద': 'da'
+    'ధ': 'dha'
+    'న': 'na'
+
+    # Labials
+    'ప': 'pa'
+    'ఫ': 'pha'
+    'బ': 'ba'
+    'భ': 'bha'
+    'మ': 'ma'
+
+    # Semivowels
+    'య': 'ya'
+    'ర': 'ra'
+    'ఱ': 'ṛa'
+    'ల': 'la'
+    'ళ': 'ḷa'
+    'వ': 'va'
+
+    # Sibilants
+    'శ': 'śa'
+    'ష': 'ṣa'
+    'స': 'sa'
+
+
+
+    # Aspirate
+    'హ': 'ha'
+
+
+
+    # Chandrabindu
+    'ঁ': 'm̐'
+    'ఁ': 'm̐'
+
+    # Bisarga
+    'ః': 'ḥ'
+
+    # Anusvāra
+    'ం': 'ṃ'
+
+    # Medials # Needed for connecting constants
+
+    'ా': 'ā'
+    'ి': 'i'
+    'ీ': 'ī'
+    'ు': 'u'
+    'ూ': 'ū'
+    'ృ': 'ṛ'
+    'ె': 'e'
+    'ే': 'ē'
+    'ై': 'ai'
+    'ొ': 'o'
+    'ో': 'ŏ'
+    'ౌ': 'au'
+    '\u09CD': '' # Used for joining
+
+
+    '\u0c4d': '' #verma sign for halanta
+    'ౕ	': ''
+    'ౖ	': ''
+    '्': ''
+    '़': ''
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+
+    # numbers
+
+    '౦': '0'
+    '౧': '1'
+    '౨': '2'
+    '౩': '3'
+    '౪': '4'
+    '౫': '5'
+    '౬': '6'
+    '౭': '7'
+    '౮': '8'
+    '౯': '9'

data/maps/alalc-tel-Telu-Latn-2011.yaml

@@ -0,0 +1,64 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:tel
+source_script: Telu
+destination_script: Latn
+name: Telugu Romanization, 2011
+url: http://catdir.loc.gov/catdir/cpso/romanization/telugu.pdf
+creation_date: 2011
+description: |
+  ALA-LC Romanization table for Telugu
+
+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 superscript sign ( ౬ ) called valapalagilaka.
+  - |
+    Exception: Sunna is transliterated by:
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+  - |
+    Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m
+
+tests:
+  - source: "తమిళనాడు"
+    expected: "tamiḷanāḍu"
+  - source: "దేవాస్‌కు ౮౯౩౯ కోట్లివ్వండి"
+    expected: "dēvāsaku 8939 kŏṭalivavaṃḍi"
+  - source: "యూరప్, అమెరికాకు కోవిడ్‌ దడ"
+    expected: "yūrapa, amerikāku kŏviḍa daḍa"
+  - source: "జనవరి నాటికి అమెరికాలో టీకా"
+    expected: "janavari nāṭiki amerikālŏ ṭīkā"
+  - source: "ఫ్రాన్స్‌ను ముస్లింలు శిక్షించవచ్చు"
+    expected: "pharānasanu musaliṃlu śikaṣiñcavacacu"
+  - source: "క్లాస్‌ రూంలో ఉపాధ్యాయుడి వికృత చేష్టలు"
+    expected: "kalāsa rūṃlŏ upādhayāyuḍi vikṛta cēṣaṭalu"
+  - source: "భారీ భూకంపం; భయంకరమైన అనుభవాలు"
+    expected: "bhārī bhūkampaṃ; bhayaṅkaramaina anubhavālu"
+  - source: "నిట్ట నిలువునా కూలిన అపార్ట్‌మెంట్‌"
+    expected: "niṭaṭa niluvunā kūlina apāraṭameṇṭa"
+  - source: "పిచ్చి ప్రయోగాలకు పోతే జరిగేది ఇదే"
+    expected: "picaci parayŏgālaku pŏtē jarigēdi idē"
+  - source: "కరోనాపై సీడీసీ వైఫల్యం ఎందుకు?"
+    expected: "karŏnāpai sīḍīsī vaiphalayaṃ eṃduku?"
+  - source: "అత్యంత అరుదైన పులి పిల్లలు ఇవే!"
+    expected: "atayanta arudaina puli pilalalu ivē!"
+
+map:
+
+  inherit: alalc-tel-Telu-Latn-1997
+
+

data/maps/az-aze-Cyrl-Latn-1939.yaml

@@ -0,0 +1,105 @@
+---
+authority_id: az
+id: 1939
+language: iso-639-2:aze
+source_script: Cyrl
+destination_script: Latn
+url: https://omniglot.com/writing/azeri.htm
+creation_date: 1939
+description: |
+  In 1939 Joseph Stalin ordered the Cyrillic alphabet to be used by Azeri speakers in the Soviet Union.
+
+notes:
+  # from Wikipedia
+  - The letter Ц, intended for the sound [ц] in borrowed words, was used in the Azerbaijani Cyrillic alphabet until 1951. In the Azeri language, the sound [c] usually becomes [s].
+
+tests:
+  - source: Юя
+    expected: Yuya
+  # from internet
+  - source: Азәрбайҹан әлифбасы
+    expected: Azərbaycan əlifbası
+  - source: |
+      Бүтүн инсанлар ләйагәт вә һүгугларына ҝөрә азад бәрабәр доғулурлар.
+      Онларын шүурлары вә виҹданлары вар вә бир-бирләринә мүнасибәтдә гардашлыг руһунда давранмалыдырлар.
+    expected: |
+      Bütün insanlar ləyaqət və hüquqlarına görə azad bərabər doğulurlar.
+      Onların şüurları və vicdanları var və bir-birlərinə münasibətdə qardaşlıq ruhunda davranmalıdırlar.
+
+map:
+  characters:
+    "\u0410": "A"       # А
+    "\u0411": "B"       # Б
+    "\u0412": "V"       # В
+    "\u0413": "Q"       # Г
+    "\u0492": "\u011E"  # Ғ
+    "\u0414": "D"       # Д
+    "\u0415": "E"       # Е
+    "\u04D8": "\u018F"  # Ә
+    "\u0416": "J"       # Ж
+    "\u0417": "Z"       # З
+    "\u0418": "\u0130"  # И
+    "\u0419": "Y"       # Й
+    "\u041A": "K"       # К
+    "\u049C": "G"       # Ҝ
+    "\u041B": "L"       # Л
+    "\u041C": "M"       # М
+    "\u041D": "N"       # Н
+    "\u041E": "O"       # О
+    "\u04E8": "\u00D6"  # Ө
+    "\u041F": "P"       # П
+    "\u0420": "R"       # Р
+    "\u0421": "S"       # С
+    "\u0422": "T"       # Т
+    "\u0423": "U"       # У
+    "\u04AE": "\u00DC"  # Ү
+    "\u0424": "F"       # Ф
+    "\u0425": "X"       # Х
+    "\u0426": "s"       # Ц note[1]
+    "\u04BA": "H"       # Һ
+    "\u0427": "\u00C7"  # Ч
+    "\u04B8": "C"       # Ҹ
+    "\u0428": "\u015E"  # Ш
+    "\u042B": "I"       # Ы
+    "\u042D": "E"       # Э
+    "\u042E": "Yu"      # Ю
+    "\u042F": "Ya"      # Я
+
+    "\u0430": "a"       # а
+    "\u0431": "b"       # б
+    "\u0432": "v"       # в
+    "\u0433": "q"       # г
+    "\u0493": "\u011F"  # ғ
+    "\u0434": "d"       # д
+    "\u0435": "e"       # е
+    "\u04D9": "\u0259"  # ә
+    "\u0436": "j"       # ж
+    "\u0437": "z"       # з
+    "\u0438": "i"       # и
+    "\u0439": "y"       # й
+    "\u043A": "k"       # к
+    "\u049D": "g"       # ҝ
+    "\u043B": "l"       # л
+    "\u043C": "m"       # м
+    "\u043D": "n"       # н
+    "\u043E": "o"       # о
+    "\u04E9": "\u00F6"  # ө
+    "\u043F": "p"       # п
+    "\u0440": "r"       # р
+    "\u0441": "s"       # с
+    "\u0442": "t"       # т
+    "\u0443": "u"       # у
+    "\u04AF": "\u00FC"  # ү
+    "\u0444": "f"       # ф
+    "\u0445": "x"       # х
+    "\u0446": "s"       # ц note[1]
+    "\u04BB": "h"       # һ
+    "\u0447": "\u00E7"  # ч
+    "\u04B9": "c"       # ҹ
+    "\u0448": "\u015F"  # ш
+    "\u044B": "\u0131"  # ы
+    "\u044D": "e"       # э
+    "\u044E": "yu"      # ю
+    "\u044F": "ya"      # я
+
+    "\u0027": ""        # '