interscript 0.1.3 → 0.1.9

data/maps/alalc-guj-Gujr-Latn-2011.yaml

@@ -0,0 +1,64 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: Gujarati Romanization, 2011
+alias:
+  ogc11122:
+    code: guj_Gujr2Latn_ALA_2011
+    description: Gujarati ALA-Library of Congress 2011 System
+url: https://www.loc.gov/catdir/cpso/romanization/gujarati.pdf
+creation_date: 2011
+description: |
+  ALA-LC Romanization table for Gujarati
+
+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 halanta or
+    virāma.
+
+  - |
+    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.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "મોર્ગન અને રસેલ ફ્લોપ રહ્યા"
+    expected: "mȏrgana anȇ rasȇla phlȏpa rahyā"
+  - source: "રોયલ ચેલેન્જર્સ બેંગલોરના કેપ્ટન વિરાટ કોહલીએ કોલકાતા નાઈટ રાઈડર્સ સામે શારજાહ ખાતે ટોસ જીતીને બેટિંગ લીધી છે."
+    expected: "rȏyala cȇlȇnjarsa bȇṅgalȏranā kȇpṭana virāṭa kȏhalīȇ kȏlakātā nāīṭa rāīḍarsa sāmȇ śārajāha khātȇ ṭȏsa jītīnȇ bȇṭiṅga līdhī chȇ."
+  - source: "અમદાવાદમાં ભણી ચૂકેલા શ્રીકાંત દાતાર પ્રતિષ્ઠિત હાર્વર્ડ બિઝનેસ સ્કૂલના ડીન બન્યા"
+    expected: "amadāvādamāṃ bhaṇī cūkȇlā śrīkānta dātāra pratishṭhita hārvarḍa bijhanȇsa skūlanā ḍīna banyā"
+  - source: "ઓગસ્ટ મહિનામાં મેન્યુફેક્ચરિંગ સેક્ટરનું ઉત્પાદન ગગડ્યુ"
+    expected: "ȏgasṭa mahināmāṃ mȇnyuphȇkcariṅga sȇkṭaranuṃ utpādana gagaḍyu"
+  - source: "૯૦ વર્ષમાં બે કરોડમાંથી પોણાબે લાખ કરોડ થઈ ગઈ ટાટા ગ્રુપમાં મિસ્ત્રી પરિવારની શેર્સ વેલ્યુ, જૂના સંબંધો અંત ભણી, જાણો કોને શું મળશે, કોણ શું ગુમાવશે?"
+    expected: "90 varshamāṃ bȇ karȏḍamānthī pȏṇābȇ lākha karȏḍa thaī gaī ṭāṭā grupamāṃ mistrī parivāranī śȇrsa vȇlyu, jūnā sambandhȏ anta bhaṇī, jāṇȏ kȏnȇ śuṃ maḷaśȇ, kȏṇa śuṃ gumāvaśȇ?"
+  - source: "મુંબઈના એક સ્ટોક બ્રોકરે જણાવ્યું કે ટાટા પોતાના શેર બહાર જતા રોકવા માટે SP ગ્રુપ સાથે સમજૂતી કરી શકે છે."
+    expected: "mumbaīnā ȇka sṭȏka brȏkarȇ jaṇāvyuṃ kȇ ṭāṭā pȏtānā śȇra bahāra jatā rȏkavā māṭȇ SP grupa sāthȇ samajūtī karī śakȇ chȇ."
+  - source: "કોલકાતા નાઈટ રાઈડર્સનો ઓફ સ્પિનર સુનીલ નારાયણ વિવાદમાં ફસાઈ ગયો છે"
+    expected: "kȏlakātā nāīṭa rāīḍarsanȏ ȏpha spinara sunīla nārāyaṇa vivādamāṃ phasāī gayȏ chȇ"
+  - source: "ટાટા અને મિસ્ત્રી પરિવાર વચ્ચે શેર્સની આપ-લે થાય એ માટે કોઈ પારસી વ્યક્તિને મધ્યસ્થી બનાવી શકાય છે અને આ માટે રતન ટાટા પણ પ્રયત્નો કરી શકે છે"
+    expected: "ṭāṭā anȇ mistrī parivāra vaccȇ śȇrsanī āpa-lȇ thāya ȇ māṭȇ kȏī pārasī vyaktinȇ madhyasthī banāvī śakāya chȇ anȇ ā māṭȇ ratana ṭāṭā paṇa prayatnȏ karī śakȇ chȇ"
+  - source: "મેદાની અમ્પાયરોએ પંજાબ વિરુદ્ધની મેચમાં તેની બોલિંગ એક્શન બાબતે શંકા વ્યક્ત કરી હતી. ફરિયાદ પછી હવે નારાયણને વોર્નિંગ લિસ્ટમાં નાખી દેવાયો છે"
+    expected: "mȇdānī ampāyarȏȇ pañjāba viruddhanī mȇcamāṃ tȇnī bȏliṅga ȇkśana bābatȇ śaṅkā vyakta karī hatī. phariyāda pachī havȇ nārāyaṇanȇ vȏrniṅga lisṭamāṃ nākhī dȇvāyȏ chȇ"
+  - source: "મોદી સરકારના આત્મનિર્ભર ભારત અભિયાનને સફળતા, પાંચ મહિનામાં ચીન સાથેની વેપાર ખાધ અડધી થઈ ગઈ, ચાઈનિઝ સ્માર્ટફોનની હિસ્સેદારી પણ ઘટી"
+    expected: "mȏdī sarakāranā ātmanirbhara bhārata abhiyānanȇ saphaḷatā, pāñca mahināmāṃ cīna sāthȇnī vȇpāra khādha aḍadhī thaī gaī, cāīnijha smārṭaphȏnanī hissȇdārī paṇa ghaṭī"
+
+map:
+
+  inherit: 'alalc-guj-Gujr-Latn-1997'

data/maps/alalc-hin-Deva-Latn-1997.yaml

@@ -0,0 +1,303 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Romanization, 1997
+alias:
+  ogc11122:
+    code: hin_Deva2Latn_ALA_1997
+    description: Hindi ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/hindi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Hindi
+
+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 sign ( ◌् ) called halanta or
+       virāma.
+
+  - |
+    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.
+
+  - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "हम"
+    expected: "hama"
+  - source: "मीन"
+    expected: "mīna"
+  - source: "औसत"
+    expected: "ăusata"
+  - source: "माँऽऽऽ!"
+    expected: "mān̐’’’!"
+  - source: "माँ"
+    expected: "mām̐"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "gaṃbhīr marījoṃ ke māmale meṃ bhārat dūsare naṃbar para"
+  - source: "कोरोना अपडेट्स"
+    expected: "koronā apaḍeṭsa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "sīḍīsī cīph kā bayān ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gūgal ple sṭor par peṭīem kī vāpasī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhārat meṃ gaiṃbaliṃg kī ijājat nahīṃ"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "koronā vaiksīn mudde par ghire rāshṭrapati; jo bāiḍen bole- mujhe ăur deś ko vaijñānikoṃ par bharosā hai, ḍonālḍ ṭramp par nahīṃ"
+  - source: "गूगल की कार्रवाई पर पेटीएम ने कहा था कि ऐप को अस्थायी तौर पर प्ले-स्टोर से हटाया गया है, आपके पैसे सुरक्षित हैं"
+    expected: "gūgal kī kārravāī par peṭīem ne kahā thā ki aip ko asthāyī tăur par ple-sṭor se haṭāyā gayā hai, āpake paise surakshit haiṃ"
+  - source: "२५६८७५४४६४४६१६११"
+    expected: "2568754464461611"
+
+map:
+
+  rules:
+    # note[2]
+    - pattern: (क=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'k'
+    - pattern: (क़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'q'
+    - pattern: (ख=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'kh'
+    - pattern: (ख़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'kh'
+    - pattern: (ग=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'g'
+    - pattern: (ग़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'gh'
+    - pattern: (घ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'gh'
+    - pattern: (ङ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṅ'
+    - pattern: (च=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'c'
+    - pattern: (छ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ch'
+    - pattern: (ज=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'j'
+    - pattern: (ज़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'j'
+    - pattern: (झ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'jh'
+    - pattern: (ञ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ñ'
+    - pattern: (ट=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṭ'
+    - pattern: (ट़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  't̤'
+    - pattern: (ठ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṭh'
+    - pattern: (ड=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ḍ'
+    - pattern: (ड़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṛ'
+    - pattern: (ड़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṛ'
+    - pattern: (ढ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ḍh'
+    - pattern: (ढ़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṛh'
+    - pattern: (ण=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ṇ'
+    - pattern: (त=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  't'
+    - pattern: (थ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'th'
+    - pattern: (द=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'd'
+    - pattern: (ध=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'dh'
+    - pattern: (न=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'n'
+    - pattern: (प=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'p'
+    - pattern: (फ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ph'
+    - pattern: (फ़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ph'
+    - pattern: (ब=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'b'
+    - pattern: (भ=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'bh'
+    - pattern: (म=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'm'
+    - pattern: (य=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'y'
+    - pattern: (र=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'r'
+    - pattern: (ल=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'l'
+    - pattern: (व=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'v'
+    - pattern: (श=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'ś'
+    - pattern: (ष=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'sh'
+    - pattern: (स=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  's'
+    - pattern: (स़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  's̤'
+    - pattern: (ह=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'h'
+    - pattern: (ह़=?)(?=[\u093E\u093F\u0940\u0941\u0942\u0943\u0944\u0945\u0947\u0948\u0949\u094B\u094C\u0020\u094d])
+      result:  'h'
+
+    # note[3]
+    - pattern: \u0902(?=[कक़खख़गग़घङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजज़झञ])
+      result: ñ
+    - pattern: \u0902(?=[टट़ठडड़ढढ़ण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+    # note[4]
+    - pattern: (?<=)\u0901(?=\b)
+      result: "m̐"
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ऋ': 'ṛ'
+    'ॠ': 'ṝ'
+    'ऌ': 'ḷ'
+    'ॳ': 'ĕ'
+    'ए': 'e'
+    'ॲ': 'ê'
+    'अै': 'ăi'
+    'ऐ': 'ai'
+    'ऒ': 'ŏ'
+    'ओ': 'o'
+    'ऑ': 'ô'
+    'औ': 'ău'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'क़': 'qa'
+    'ख': 'kha'
+    'ख़': 'kha'
+    'ग': 'ga'
+    'ग़': 'gha'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'ज़': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ट़': 't̤a'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    'ड़': 'ṛa'
+    'ड़': 'ṛa'
+    'ढ': 'ḍha'
+    'ढ़': 'ṛha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'फ़': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'sha'
+    'स': 'sa'
+    'स़': 's̤a'
+
+    # Aspirate
+    'ह': 'ha'
+    'ह़': 'ha'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Bisarga
+    'ः ': 'ḥ'
+
+    # Anunāsika
+    'ँ': 'n̐' # ঁ : n̐, m̐
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ॉ': "ô"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛ"
+    'ॄ': "ṝ"
+    'े': "e"
+    'ॊ': "ŏ"
+    'ौ': "ău"
+    'ै': "ai"
+    'ो': "o"
+    '्': ""
+    '़': ""
+
+    # digits
+
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'

data/maps/alalc-hin-Deva-Latn-2011.yaml

@@ -0,0 +1,65 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Romanization, 2011
+url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Hindi
+
+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 sign ( ◌् ) called halanta or
+       virāma.
+
+  - |
+    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.
+
+  - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "इस चुनौतीपूर्ण समय में 'वर्क फ्रॉम होम’ सामान्य बन चुका है"
+    expected: "is cunăutīpūrṇ samay meṃ 'vark phrôm homa’ sāmāny ban cukā hai"
+  - source: "दिल्ली में त्योहार पर खरीददारी करने निकले बड़ी संख्या में लोग, कई जगहों पर लगा भीषण जाम"
+    expected: "dillī meṃ tyohār par kharīdadārī karane nikale baṛī saṃkhyā meṃ loga, kaī jagahoṃ par lagā bhīshaṇ jāma"
+  - source: "सरकार ने पेंशन भोगियों को लाइफ सर्टिफिकेट जमा कराने के मामले में दी बड़ी राहत"
+    expected: "sarakār ne peṃśan bhogiyoṃ ko lāiph sarṭiphikeṭ jamā karāne ke māmale meṃ dī baṛī rāhata"
+  - source: "कांग्रेस ने माना उसके लचर प्रदर्शन ने डुबोई महागठबंधन की लुटिया, पार्टी में उठने लगी आत्ममंथन की आवाज"
+    expected: "kāṃgres ne mānā usake lacar pradarśan ne ḍuboī mahāgaṭhabandhan kī luṭiyā, pārṭī meṃ uṭhane lagī ātmamanthan kī āvāja"
+  - source: "डिजिटल पेमेंट सिस्टम ने छोटे-मध्यम कारोबारों का दिया साथ, कोरोना की परेशानियों को किया कम"
+    expected: "ḍijiṭal pemeṃṭ sisṭam ne choṭe-madhyam kārobāroṃ kā diyā sātha, koronā kī pareśāniyoṃ ko kiyā kama"
+  - source: "छोटे व्यापारियों को ढूंढें, उनसे खरीदें और उनका साथ दें"
+    expected: "choṭe vyāpāriyoṃ ko ḍhūṃḍheṃ, unase kharīdeṃ ăur unakā sāth deṃ"
+  - source: "भारत के साथ साझीदारी को महत्व देंगे बाइडन, ओबामा प्रशासन में रहीं वरिष्ठ अधिकारी एलिसा ने जताई उम्मीद"
+    expected: "bhārat ke sāth sājhīdārī ko mahatv deṃge bāiḍana, obāmā praśāsan meṃ rahīṃ varishṭh adhikārī elisā ne jatāī ummīda"
+  - source: "दो महीने से कोमा में था युवक, चिकन की चर्चा सुनते ही आया होश"
+    expected: "do mahīne se komā meṃ thā yuvaka, cikan kī carcā sunate hī āyā hośa"
+  - source: "कोरोना के टीके पर खुशखबरी, भारत पहुंची रूसी वैक्सीन की पहली खेप"
+    expected: "koronā ke ṭīke par khuśakhabarī, bhārat pahuṃcī rūsī vaiksīn kī pahalī khepa"
+  - source: "दिल्ली के गांधी नगर स्थित एक दुकान में लगी भीषण आग, दमकल की 20 गाड़ियां मौके पर"
+    expected: "dillī ke gāṃdhī nagar sthit ek dukān meṃ lagī bhīshaṇ āga, damakal kī 20 gāṛiyāṃ măuke para"
+
+map:
+
+  inherit: "alalc-hin-Deva-Latn-1997"

data/maps/alalc-kan-Kana-Latn-1997.yaml

@@ -0,0 +1,274 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:kan
+source_script: Kana
+destination_script: Latn
+name: Kannada Romanization, 1997
+url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Kannada
+
+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 (◌್).
+
+  - |
+    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: "ಕರ್ಣಾಟಕ"
+    expected: "karṇāṭaka"
+  - source: "ಬೆಂಗಳೂರು"
+    expected: "beṅgaḷūru"
+  - source: "ಉಡುಪಿಯಲ್ಲಿ ಪ್ರಪ್ರಥಮ ಬಾರಿಗೆ ಪ್ರಾರಂಭವಾಗಿರುವ ದೇಶಿ ಉತ್ಪನ್ನಗಳ ಮಳಿಗೆ"
+    expected: "uḍupiyalli praprathama bārige prāraṃbhavāgiruva dēśi utpannagaḷa maḷige"
+  - source: "ದೇವರ ಹೆಸರು ಬಳಸಿ ಆನ್‌ಲೈನ್‌ ಬೆಟ್ಟಿಂಗ್‌!"
+    expected: "dēvara hesaru baḷasi ānlain beṭṭiṃg!"
+  - source: "ಚಿಕ್ಕಮಗಳೂರು : ಪುಷ್ಪ ಸಮರ್ಪಣೆ ವೇಳೆ ಮಗಳನ್ನ ನೆನೆದು ಕಣ್ಣೀರಿಟ್ಟ ಮೃತ ಪೇದೆ ತಾಯಿ"
+    expected: "cikkamagaḷūru : puṣpa samarpaṇe vēḷe magaḷanna nenedu kaṇṇīriṭṭa mṛta pēde tāyi"
+  - source: "ಸ್ವಾಮಿತ್ವ: ಹೊಸ ಯೋಜನೆಯಿಂದ ನಮಗೆ ಏನು ಲಾಭ ?"
+    expected: "svāmitva: hosa yōjaneyinda namage ēnu lābha ?"
+  - source: "ಮರಳು ಸಾಗಾಣಿಕೆ ವ್ಯವಹಾರ ಆಗಬಾರದು :ಅಧಿಕಾರಿಗಳಿಗೆ ಖಡಕ್ ಸೂಚನೆ ನೀಡಿದ ಜಿಲ್ಲಾಧಿಕಾರಿ"
+    expected: "maraḷu sāgāṇike vyavahāra āgabāradu :adhikārigaḷige khaḍak sūcane nīḍida jillādhikāri"
+  - source: "ಹಾವೇರಿ ಜಿಲ್ಲೆಯಲ್ಲಿ ೯೭ ಜನರಲ್ಲಿ ಕೋವಿಡ್ ಸೋಂಕು ಪತ್ತೆ ; 54 ಮಂದಿ ಗುಣಮುಖ"
+    expected: "hāvēri jilleyalli 97 janaralli kōviḍ sōṃku patte ; 54 maṃdi guṇamukha"
+  - source: "ಸಿಂದಗಿ ಐಸಿಐಸಿಐ ಬ್ಯಾಂಕ್ ಸೆಕ್ಯುರಿಟಿ ಗಾರ್ಡ್ ಹತ್ಯೆ ಪ್ರಕರಣ ಭೇದಿಸಿದ ಪೊಲೀಸರು"
+    expected: "sindagi aisiaisiai byāṃk sekyuriṭi gārḍ hatye prakaraṇa bhēdisida polīsaru"
+  - source: "ಬ್ಯಾಂಕರ್‌ಗಳೊಂದಿಗೆ ಡಿವಿ ಸಭೆ : ಆಧ್ಯತಾ ವಲಯ, ಸಾಲ ಯೋಜನೆ ತ್ವರಿತ ಮಂಜೂರಿಗೆ ಸೂಚನೆ"
+    expected: "byāṅkargaḷoṃdige ḍivi sabhe : ādhyatā valaya, sāla yōjane tvarita maṃjūrige sūcane"
+  - source: "ಪೊಲೀಸ್‌ ಇಲಾಖೆ ಸಮಗ್ರ ಅಭಿವೃದ್ಧಿ; ಡಿಜಿಪಿ ನೇತೃತ್ವದಲ್ಲಿ ಸಮಿತಿ ರಚನೆ: ಬೊಮ್ಮಾಯಿ"
+    expected: "polīs ilākhe samagra abhivṛddhi; ḍijipi nētṛtvadalli samiti racane: beūmmāyi"
+  - source: "ಕೆಟ್ಟಿರುವ ರಸ್ತೆಗಳ ದುರಸ್ತಿಗೆ ಸರಕಾರದ ಯೋಜನೆ"
+    expected: "keṭṭiruva rastegaḷa durastige sarakārada yōjane"
+
+map:
+
+
+  rules:
+    # to cover diacritic and vowel less consonants rule II
+    - pattern: ([ಕ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'k'
+    - pattern: ([ಖ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'kh'
+    - pattern: ([ಗ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'g'
+    - pattern: ([ಘ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'gh'
+    - pattern: ([ಙ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṅ'
+    - pattern: ([ಚ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'c'
+    - pattern: ([ಛ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ch'
+    - pattern: ([ಜ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'j'
+    - pattern: ([ಝ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'jh'
+    - pattern: ([ಞ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ñ'
+    - pattern: ([ಟ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṭ'
+    - pattern: ([ಠ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṭh'
+    - pattern: ([ಡ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ḍ'
+    - pattern: ([ಢ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ḍh'
+    - pattern: ([ಣ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṇ'
+    - pattern: ([ತ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  't'
+    - pattern: ([ಥ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'th'
+    - pattern: ([ದ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'd'
+    - pattern: ([ಧ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'dh'
+    - pattern: ([ನ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'n'
+    - pattern: ([ಪ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'p'
+    - pattern: ([ಫ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ph'
+    - pattern: ([ಬ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'b'
+    - pattern: ([ಭ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'bh'
+    - pattern: ([ಮ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'm'
+    - pattern: ([ಯ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'y'
+    - pattern: ([ರ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'r'
+    - pattern: ([ಱ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṟ'
+    - pattern: ([ಲ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'l'
+    - pattern: ([ಳ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ḷ'
+    - pattern: ([ೞ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'l̤'
+    - pattern: ([ವ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'v'
+    - pattern: ([ಶ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ś'
+    - pattern: ([ಷ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'ṣ'
+    - pattern: ([ಸ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  's'
+    - pattern: ([ಹ]=?)(?=[\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd])
+      result:  'h'
+
+    # rule[III]
+    - pattern: \u0C82(?=[ಕಖಗಘಙ])
+      result: ṅ
+    - pattern: \u0C82(?=[ಚಛಜಝಞ])
+      result: ñ
+    - pattern: \u0C82(?=[ಟಠಡಢಣ])
+      result: ṇ
+    - pattern: \u0C82(?=[ತಥದಧನ])
+      result: n
+
+  characters:
+    'ಅ': 'a'
+    'ಆ': 'ā'
+    'ಇ': 'i'
+    'ಈ': 'ī'
+    'ಉ': 'u'
+    'ಊ': 'ū'
+    'ಋ': 'ṛ'
+    'ೠ': 'ṝ'
+
+    'ಌ': 'ḻ'
+
+    'ಎ': 'e'
+    'ಏ': 'ē'
+    'ಐ': 'ai'
+
+    'ಒ': 'o'
+    'ಓ': 'ō'
+    'ಔ': 'au'
+
+    # Gutturals
+    'ಕ': 'ka'
+    'ಖ': 'kha'
+    'ಗ': 'ga'
+    'ಘ': 'gha'
+    'ಙ': 'ṅa'
+
+    # Palatals
+    'ಚ': 'ca'
+    'ಛ': 'cha'
+    'ಜ': 'ja'
+    'ಝ': 'jha'
+    'ಞ': 'ña'
+
+    # Cerebrals
+    'ಟ': 'ṭa'
+    'ಠ': 'ṭha'
+    'ಡ': 'ḍa'
+    'ಢ': 'ḍha'
+    'ಣ': 'ṇa'
+
+    # Dentals
+    'ತ': 'ta'
+    'ಥ': 'tha'
+    'ದ': 'da'
+    'ಧ': 'dha'
+    'ನ': 'na'
+
+    # Labials
+    'ಪ': 'pa'
+    'ಫ': 'pha'
+    'ಬ': 'ba'
+    'ಭ': 'bha'
+    'ಮ': 'ma'
+
+    # Semivowels
+    'ಯ': 'ya'
+    'ರ': 'ra'
+    'ಱ': 'ṟa'
+    'ಲ': 'la'
+    'ಳ': 'ḷa'
+    'ೞ': 'l̤a'
+
+
+    'ವ': 'va'
+
+    # Sibilants
+    'ಶ': 'śa'
+    'ಷ': 'ṣa'
+    'ಸ': 'sa'
+
+
+    # Aspirate
+    'ಹ': 'ha'
+
+
+    # Bisarga
+    'ಃ': 'ḥ'
+
+    # Anusvāra
+    'ಂ': 'ṃ'
+
+    '\u0cbc': '' #nukta
+
+    # Medials # Needed for connecting constants
+    'ಾ': "ā"
+    'ಿ': "i"
+    'ೀ': "ī"
+    'ು': "u"
+    'ೂ': "ū"
+    'ೃ': "ṛ"
+    'ೄ': "ṝ"
+    '\u0CE2': 'ḻ' # KANNADA VOWEL SIGN VOCALIC L ( ೢ)
+
+
+    'ೆ': "e"
+    'ೇ': "ē"
+    'ೈ': "ai"
+
+
+    'ೊ': 'o'
+    'ೋ': 'ō'
+    'ೌ': 'au'
+
+
+    '्': ''
+    '़': ''
+    '್': '' # used for pronounciation without vowel
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner
+
+
+
+    # Digits
+
+    '೦': '0'
+    '೧': '1'
+    '೨': '2'
+    '೩': '3'
+    '೪': '4'
+    '೫': '5'
+    '೬': '6'
+    '೭': '7'
+    '೮': '8'
+    '೯': '9'