interscript 0.1.6 → 2.1.0a9

data/maps/bis-gjr-Gujr-Latn-13194-1991.yaml

@@ -1,166 +0,0 @@
----
-authority_id: bis
-id: 1991
-language: gjr
-source_script: Gujr
-destination_script: Latn
-name: Indian script code for information interchange - ISCII - Gujrati Romanization
-#url:
-creation_date: 1991
-description: |
-  IS 13194 (1991): Indian script code for information
-  interchange - ISCII [LITD 20: Indian Language Technologies
-  and Products]
-
-notes:
-  - |
-    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.
-
-tests:
-  - source: "અમિત શાહનો કોરોના રિપોર્ટ 2 ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
-    expected: "amit śāhnŏ kŏrŏnā ripŏrṭ 2 ŏgsṭē pŏjhiṭiv āvyŏ htŏ, tyārthī tēmnuṃ svāsthy sāruṃ nthī"
-  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
-    expected: "mēdāntā hŏspiṭlmāṃ tēmnŏ ilāj cālī rhyŏ htŏ"
-  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
-    expected: "bhārtnā viśvnāthn ānndē śēnyānmāṃ phēlŏ phiḍē śtrñj viśv kp jītyŏ"
-  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ 40 લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
-    expected: "bhārtīy vḍā prdhān jvāhrlāl nēhruē 40 lākh hinduŏ anē muslmānŏnā pārsprik sthānāntrṇnuṃ sūcn āpyuṃ"
-  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન 58 ડિગ્રી સેલ્સિયસ હતું."
-    expected: "libiyānā ēl ajijiyāmāṃ dhrtī pr sauthī vdhu tāpmān nŏndhāyuṃ. ē vkhtē chāyāmāṃ nŏndhvāmāṃ āvēluṃ tāpmān 58 ḍigrī sēlsiys htuṃ."
-  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
-    expected: "prthm viśvyuddhḥ jrmnī anē phrāns vccē ēsnēnī lḍāī śrū thī htī"
-  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
-    expected: "ēnglŏ-mistr yuddhḥ tēl al kēbirnuṃ yuddh lḍvāmāṃ āvyuṃ htuṃ."
-  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
-    expected: "purāvā n htā, ē j kārṇē kēs cālyŏ nhīṃ, pṇ tēmnē njrkēd rākhvāmāṃ āvyā"
-  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; 91 વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
-    expected: "srdār pṭēlē nkkī kryuṃ htuṃ kē kāśmīr bhārtnŏ hissŏ bnśē; 91 vrṣ phēlāṃ lāhŏr jēlmāṃ bhūkhhḍtāḷ drmiyān śhīd thyā htā jtīn dās"
-  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
-    expected: "kŏrŏnā prŏṭŏkŏl vccē ājē mēḍikl prvēś prīkṣā lēvāśēḥ ēnṭrī ṭc phrī rhēśē, ēḍmiṭ kārḍ bār kŏḍthī cēk thśē"
-
-
-
-map:
-
-  rules:
-    # note
-    - pattern: \u0A82(?=[કખગઘઙ])
-      result: ṅ
-    - pattern: \u0A82(?=[ચછજઝઞ])
-      result: ñ
-    - pattern: \u0A82(?=[ટઠડઢણ])
-      result: ṇ
-    - pattern: \u0A82(?=[તથદધન])
-      result: n
-    - pattern: \u0A82(?=[પફબભમ])
-      result: m
-
-
-  characters:
-    'અ': 'a'
-    'આ': 'ā'
-    'ઇ': 'i'
-    'ઈ': 'ī'
-    'ઉ': 'u'
-    'ઊ': 'ū'
-   # 'ઋ': 'ṛ'
-    'ઌ': 'ḻ'
-
-    'ઍ': 'e'
-    'એ': 'ē'
-    'ઐ': 'ai'
-
-    'ઑ': 'o'
-    'ઓ': 'ŏ'
-    'ઔ': 'au'
-
-    # II. Consonants (see Note 2)
-    # Gutturals
-    'ક': 'k'
-    'ખ': 'kh'
-    'ગ': 'g'
-    'ઘ': 'gh'
-    'ઙ': 'ṅ'
-
-    # Palatals
-    'ચ': 'c'
-    'છ': 'ch'
-    'જ': 'j'
-    'ઝ': 'jh'
-    'ઞ': 'ñ'
-
-    # Cerebrals
-    'ટ':  'ṭ'
-    'ઠ':  'ṭh'
-    'ડ':  'ḍ'
-    'ઢ':  'ḍh'
-    'ણ':  'ṇ'
-
-    # Dentals
-    'ત': 't'
-    'થ': 'th'
-    'દ': 'd'
-    'ધ': 'dh'
-    'ન': 'n'
-
-    # Labials
-    'પ': 'p'
-    'ફ': 'ph'
-    'બ': 'b'
-    'ભ': 'bh'
-    'મ': 'm'
-
-    # Semivowels
-    'ય': 'y'
-    'ર': 'r'
-    'લ': 'l'
-    'ળ': 'ḷ'
-    'વ': 'v'
-
-    # Sibilants
-    'શ': 'ś'
-    'ષ': 'ṣ'
-    'સ': 's'
-
-
-    # Aspirate
-    'હ': 'h'
-
-    # Chandrabindu
-    'ઁ': 'm'
-
-    # Bisarga
-    'ઃ': 'ḥ'
-
-    # Anusvāra
-    'ં': 'ṃ'
-
-    # Medials # Needed for connecting constants
-
-    'ા': 'ā'
-    'િ': 'i'
-    'ી': 'ī'
-    'ુ': 'u'
-    'ૂ': 'ū'
-    'ૃ': 'ṛ'
-    #'ૄ': 'ṛr'
-    'ૅ': 'e'
-    'ે': 'ē'
-    'ૈ': 'ai'
-    'ૉ': 'o'
-    'ો': 'ŏ'
-    'ૌ': 'au'
-
-
-
-    '\u09CD': '' # Used for joining
-    '્': ''
-    '઼': ''
-    '।': '.'
-    "‍": ''# Used for joining

data/maps/bis-knd-Knda-Latn-13194-1991.yaml

@@ -1,173 +0,0 @@
----
-authority_id: bis
-id: 1991
-language: knd
-source_script: Knda
-destination_script: Latn
-name: Indian script code for information interchange - ISCII - Kannada Romanization
-#url:
-creation_date: 1991
-description: |
-  IS 13194 (1991): Indian script code for information
-  interchange - ISCII [LITD 20: Indian Language Technologies
-  and Products]
-
-notes:
-  - |
-    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.
-
-tests:
-  - source: "ಈಗ ವೈರಲ್ ಆಗುತ್ತಿದೆ ಕಂಗನಾ ರಣಾವುತ್ ಹಳೇಯ ವಿಡಿಯೋ"
-    expected: "īg vairl āguttide kṅgnā rṇāvut hḷēy viḍiyō"
-  - source: "ಸಂಕಷ್ಟ ಎದುರಾದರೆ ಬಿಎಸ್‌ವೈ ಬೆನ್ನಿಗೆ ಎಚ್‌ಡಿಕೆ ?"
-    expected: "sṅkṣṭ edurādre biesvai bennige ecḍike ?"
-  - source: "ಶಾಸಕರಿಂದಲೂ ಒತ್ತಡ?"
-    expected: "śāskrindlū ottḍ?"
-  - source: "ಏಕೆಂದರೆ, ಇವರ ಹೆಸರೇ ಕೊರೊನಾ!"
-    expected: "ēkendre, ivr hesrē keūronā!"
-  - source: "ಕೊರೊನಾಕ್ಕಿಂತಲೂ ಮುಂಚೆಯೇ ಅವರು ಕೊರೊನಾ ಆಗಿದ್ದವರು!"
-    expected: "keūronākkintlū muñceyē avru keūronā āgiddvru!"
-  - source: "ಕೇರಳದ ಕೊಟ್ಟಾಯಂನ ಮಹಿಳೆಯೊಬ್ಬರು ಈಗ ತಮ್ಮ ಹೆಸರು ಹೇಳಲು ಮುಜುಗರ ಪಡುವಂತಾಗಿದೆ"
-    expected: "kērḷd keūṭṭāynn mhiḷeyobbru īg tmm hesru hēḷlu mujugr pḍuvntāgide"
-  - source: "ಬೇರೆ ಬೆಳವಣಿಗೆಗೆ ಸಾಕ್ಷಿ ಸಾಧ್ಯತೆ"
-    expected: "bēre beḷvṇigege sākṣi sādhyte"
-  - source: "ಗುರು ಶನಿ ಗ್ರಹಗಳ ನಡುವೆ 3 ಜನರ ಪ್ರಯಾಣ"
-    expected: "guru śni grhgḷ nḍuve 3 jnr pryāṇ"
-  - source: "ಕೊರೊನಾ ಬಿಕ್ಕಟ್ಟಿನ ಕಾಲದಲ್ಲಿ “ಮಿಸೆಸ್‌ ಕೊರೊನಾ’ಗೆ ಸಮಸ್ಯೆ!"
-    expected: "keūronā bikkṭṭin kāldlli “mises keūronā’ge smsye!"
-  - source: "ಕೆಲವು ತಿಂಗಳಿಂದ ರಷ್ಯಾ ದೇಶದ ಏನಾಟೊಲಿ ಇವ್ಯಾನಿಶಿನ್‌ ಮತ್ತು ಇವಾನ್‌ ವ್ಯಾಗನರ್‌ ಹಾಗೂ ಅಮೆರಿಕಾದ ಕ್ರಿಸ್‌ ಕ್ಯಾಸಿಡಿ ಈ ಉಪಗ್ರಹದಲ್ಲಿ ವಾಸಿಸುತ್ತಿದ್ದಾರೆ"
-    expected: "kelvu tiṅgḷind rṣyā dēśd ēnāṭeūli ivyāniśin mttu ivān vyāgnr hāgū amerikād kris kyāsiḍi ī upgrhdlli vāsisuttiddāre"
-
-
-map:
-
-  rules:
-    # note
-    - pattern: \u0C82(?=[ಕಖಗಘಙ])
-      result: ṅ
-    - pattern: \u0C82(?=[ಚಛಜಝಞ])
-      result: ñ
-    - pattern: \u0C82(?=[ಟಠಡಢಣ])
-      result: ṇ
-    - pattern: \u0C82(?=[ತಥದಧನ])
-      result: n
-    - pattern: \u0C82(?=[ಪಫಬಭಮ])
-      result: m
-
-  characters:
-    'ಅ': 'a'
-    'ಆ': 'ā'
-    'ಇ': 'i'
-    'ಈ': 'ī'
-    'ಉ': 'u'
-    'ಊ': 'ū'
-    'ಋ': 'ṛ'
-    'ಌ': 'ḻ'
-
-    'ಎ': 'e'
-    'ಏ': 'ē'
-    'ಐ': 'ai'
-
-    'ಒ': 'o'
-    'ಓ': 'ŏ'
-    'ಔ': 'au'
-
-    # II. Consonants (see Note 2)
-    # Gutturals
-    'ಕ': 'k'
-    'ಖ': 'kh'
-    'ಗ': 'g'
-    'ಘ': 'gh'
-    'ಙ': 'ṅ'
-
-    # Palatals
-    'ಚ': 'c'
-    'ಛ': 'ch'
-    'ಜ': 'j'
-    'ಝ': 'jh'
-    'ಞ': 'ñ'
-
-    # Cerebrals
-    'ಟ': 'ṭ'
-    'ಠ': 'ṭh'
-    'ಡ': 'ḍ'
-    'ಢ': 'ḍh'
-    'ಣ': 'ṇ'
-
-    # Dentals
-    'ತ': 't'
-    'ಥ': 'th'
-    'ದ': 'd'
-    'ಧ': 'dh'
-    'ನ': 'n'
-
-    # Labials
-    'ಪ': 'p'
-    'ಫ': 'ph'
-    'ಬ': 'b'
-    'ಭ': 'bh'
-    'ಮ': 'm'
-
-    # Semivowels
-    'ಯ': 'y'
-    'ರ': 'r'
-    'ಱ': 'ṟ'
-    'ಲ': 'l'
-    'ಳ': 'ḷ'
- #   'ऴ': 'ẕ'
-
-
-    'ವ': 'v'
-
-    # Sibilants
-    'ಶ': 'ś'
-    'ಷ': 'ṣ'
-    'ಸ': 's'
-
-
-    # Aspirate
-    'ಹ': 'h'
-
-
-    # Chandrabindu
-    '\u0C80': 'm'
-    '\u0C81': 'm'
-
-    # Bisarga
-    'ಃ': 'ḥ'
-
-    # Anusvāra
-    'ಂ': 'ṃ'
-
-    '$಼': '' #nukta
-
-    # Medials # Needed for connecting constants
-    'ಾ': "ā"
-    'ಿ': "i"
-    'ೀ': "ī"
-    'ು': "u"
-    'ೂ': "ū"
-    'ೃ': "ṛ"
-    'ೄ': "ṛr"
-
-
-    'ೆ': "e"
-    'ೇ': "ē"
-    'ೈ': "ai"
-
-
-    'ೊ': 'o'
-    'ೋ': 'ō'
-    'ೌ': 'au'
-
-    '्': ''
-    '़': ''
-    '್': ''
-    "‍": '' # no need for zero with joiner
-    "‌": '' # no need for zero with non joiner

data/maps/bis-mlm-Mlym-Latn-13194-1991.yaml

@@ -1,176 +0,0 @@
----
-authority_id: bis
-id: 1991
-language: mlm
-source_script: Mlym
-destination_script: Latn
-name: Indian script code for information interchange - ISCII - Malayalam Romanization
-#url:
-creation_date: 1991
-description: |
-  IS 13194 (1991): Indian script code for information
-  interchange - ISCII [LITD 20: Indian Language Technologies
-  and Products]
-
-notes:
-  - |
-    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.
-
-tests:
-  - source: "സ്വപ്നയ്ക്കൊപ്പം ഹോട്ടലിൽ മന്ത്രിപുത്രൻ, ചിത്രങ്ങൾ; 4 കോടി കമ്മിഷനിലും പങ്കുപറ്റി"
-    expected: "svpnykkeāppṃ hōṭṭlil mntriputrṇ, citrṅṅḷ; 4 kōṭi kmmiṣniluṃ pṅkupṟṟi"
-  - source: "വിവാദങ്ങളിൽ മാപ്പില്ല, ആദ്യമായി ഐപിഎൽ കമന്ററിക്കില്ലാതെ മ‍ഞ്ജരേക്കര്‍; പുറത്ത് തന്നെ"
-    expected: "vivādṅṅḷil māppill, ādymāyi aipiel kmnṟṟikkillāte mñjrēkkr; puṟtt tnne"
-  - source: "പരമാവധി ഊറ്റിയെടുത്തു; എല്ലാം കഴിഞ്ഞ് ഉപേക്ഷിച്ചു: വിങ്ങലോടെ റംസിയുടെ സഹോദരി"
-    expected: "prmāvdhi ūṟṟiyeṭuttu; ellāṃ kẕiññ upēkṣiccu: viṅṅlōṭe ṟṃsiyuṭe shōdri"
-  - source: "വഴിനീളെ രോഷം; യൂത്ത്‌ കോണ്‍ഗ്രസുകാരന്റെ  കയ്യൊടിഞ്ഞു, കൈവീശികാട്ടി ജലീൽ"
-    expected: "vẕinīḷe rōṣṃ; yūtt kōṇgrsukārnṟe  kyyoṭiññu, kaivīśikāṭṭi jlīl"
-  - source: "‘വികൃതിപ്പയ്യനാ’യിരുന്ന കോലി മിന്നും താരമായത് ഇന്ത്യൻ ക്രിക്കറ്റിന്റെ ഗുണം: അക്തർ"
-    expected: "‘vikṛtippyynā’yirunn kōli minnuṃ tārmāyt intyṇ krikkṟṟinṟe guṇṃ: aktr"
-  - source: "ലോകത്തിനു വാക്സീൻ വേണമെങ്കിൽ ഈ നഗരം കനിയണം; തലയുയർത്തി ഇന്ത്യ"
-    expected: "lōkttinu vāksīṇ vēṇmeṅkil ī ngrṃ kniyṇṃ; tlyuyrtti inty"
-  - source: "‘അദ്ദേഹം ഒരു മകളെപ്പോലെ എന്നെ കേട്ടു’: ഗവർണറെ കണ്ട് കങ്കണ റനൗട്ട്"
-    expected: "‘addēhṃ oru mkḷeppōle enne kēṭṭu’: gvrṇṟe kṇṭ kṅkṇ ṟnṭṭ"
-  - source: "‘എല്ലാം ഫെയ്‌സ്ബുക്കില്‍ പറയുമെന്നു ജലീല്‍; കനത്ത സുരക്ഷയില്‍ യാത്ര, കരിങ്കൊടി"
-    expected: "‘ellāṃ pheysbukkil pṟyumennu jlīl; kntt surkṣyil yātr, kriṅkoṭi"
-  - source: "ഏറ്റവും ചെറുപ്പം ജോയി; ജയലക്ഷ്മി, ദീപ്തി, ജ്യോതി; പട്ടികയിലെ നിര ഇങ്ങനെ‌"
-    expected: "ēṟṟvuṃ ceṟuppṃ jōyi; jylkṣmi, dīpti, jyōti; pṭṭikyile nir iṅṅne"
-  - source: "പരിശോധന കുറച്ച് കേരളം; കോവിഡ് ടെസ്റ്റ് പോസിറ്റിവിറ്റി നിരക്ക് എറ്റവും ഉയർന്ന്; ആശങ്ക‌"
-    expected: "priśōdhn kuṟcc kērḷṃ; kōvid̂ ṭesṟṟ pōsiṟṟiviṟṟi nirkk eṟṟvuṃ uyrnn; āśṅk"
-
-map:
-
-  rules:
-    # note
-    - pattern: \u0D02(?=[കൿഖഗഘങ])
-      result: ṅ
-    - pattern: \u0D02(?=[ചഛജഝഞ])
-      result: ñ
-    - pattern: \u0D02(?=[ടഠഡഢണ])
-      result: ṇ
-    - pattern: \u0D02(?=[തഥദധന])
-      result: n
-    - pattern: \u0D02(?=[പഫബഭമ])
-      result: m
-
-
-  characters:
-    'അ': 'a'
-    'ആ': 'ā'
-    'ഇ': 'i'
-    'ഈ': 'ī'
-    'ഉ': 'u'
-    'ഊ': 'ū'
-    'ഋ': 'ṛ'
-    'ഌ': 'ḻ'
-
-
-    'എ': 'e'
-    'ഏ': 'ē'
-    'ഐ': 'ai'
-
-    'ഒ': 'o'
-    'ഓ': 'ŏ'
-    'ഔ': 'au'
-
-    # II. Consonants (see Note 2)
-    # Gutturals
-    'ക': 'k'
-    'ൿ': 'k'
-    'ഖ': 'kh'
-    'ഗ': 'g'
-    'ഘ': 'gh'
-    'ങ': 'ṅ'
-
-    # Palatals
-    'ച': 'c'
-    'ഛ': 'ch'
-    'ജ': 'j'
-    'ഝ': 'jh'
-    'ഞ': 'ñ'
-
-    # Cerebrals
-    'ട':  'ṭ'
-    'ഠ':  'ṭh'
-    'ഡ': 'd̂'
-    'ഢ':  'ḍh'
-    'ണ':  'ṇ'
-
-    # Dentals
-    'ത': 't'
-    'ഥ': 'th'
-    'ദ': 'd'
-    'ധ': 'dh'
-    'ന': 'n'
-
-    # Labials
-    'പ': 'p'
-    'ഫ': 'ph'
-    'ബ': 'b'
-    'ഭ': 'bh'
-    'മ': 'm'
-
-    # Semivowels
-    'യ': 'y'
-    'ര': 'r'
-    'ർ': 'r'
-    'റ': 'ṟ'
-    'ൽ': 'l'
-    'ല': 'l'
-    'ള': 'ḷ'
-    'ൾ': 'ḷ'
-    'ഴ': 'ẕ'
-    # Sibilants
-    'വ': 'v'
-    'ശ': 'ś'
-    'ഷ': 'ṣ'
-    'സ': 's'
-
-
-    # Aspirate
-    'ഹ': 'h'
-
-    # Chandrabindu
-    '\u0D01': 'm'
-
-    # Bisarga
-    'ഃ': 'ḥ'
-
-    # Anusvāra
-    'ം': 'ṃ'
-
-    # Medials # Needed for connecting constants
-
-    'ാ': 'ā'
-    'ി': 'i'
-    'ീ': 'ī'
-    'ു': 'u'
-    'ൂ': 'ū'
-
-    'ൃ': "ṛ"
-    'ൄ': "ṝ"
-
-
-    'െ': "e"
-    'േ': "ē"
-    'ൈ': "ai"
-    'ൊ': 'o'
-    'ോ': 'ō'
-    'ൌ': 'au'
-
-
-    'ൺ': 'n'
-    'ൻ': 'ṇ'
-
-    '्': ''
-    '്': ''
-    '़': ''
-    'ൗ': ''
-    "‍": '' # no need for zero with joiner
-    "‌": '' # no need for zero with non joiner