interscript 0.1.2 → 0.1.7

data/maps/alalc-guj-Gujr-Latn-1997.yaml

@@ -0,0 +1,266 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: Gujarati Romanization, 1997
+alias:
+  ogc11122:
+    code: guj_Gujr2Latn_ALA_1997
+    description: Gujarati ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/gujarati.pdf
+creation_date: 1997
+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: "અમિત શાહનો કોરોના રિપોર્ટ ૨ ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
+    expected: "amita śāhanȏ kȏrȏnā ripȏrṭa 2 ȏgasṭȇ pȏjhiṭiva āvyȏ hatȏ, tyārathī tȇmanuṃ svāsthya sāruṃ nathī"
+  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
+    expected: "mȇdāntā hȏspiṭalamāṃ tȇmanȏ ilāja cālī rahyȏ hatȏ"
+  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
+    expected: "bhāratanā viśvanāthana ānandȇ śȇnayānamāṃ pahȇlȏ phiḍȇ śatarañja viśva kapa jītyȏ"
+  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ ૪૦ લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
+    expected: "bhāratīya vaḍā pradhāna javāharalāla nȇharuȇ 40 lākha hinduȏ anȇ musalamānȏnā pārasparika sthānāntaraṇanuṃ sūcana āpyuṃ"
+  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન ૫૮ ડિગ્રી સેલ્સિયસ હતું."
+    expected: "libiyānā ȇla ajijiyāmāṃ dharatī para sauthī vadhu tāpamāna nȏndhāyuṃ. ȇ vakhatȇ chāyāmāṃ nȏndhavāmāṃ āvȇluṃ tāpamāna 58 ḍigrī sȇlsiyasa hatuṃ."
+  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
+    expected: "prathama viśvayuddhaḥ jarmanī anȇ phrānsa vaccȇ ȇsnȇnī laḍāī śarū thaī hatī"
+  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
+    expected: "ȇnglȏ-mistra yuddhaḥ tȇla ala kȇbiranuṃ yuddha laḍavāmāṃ āvyuṃ hatuṃ."
+  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
+    expected: "purāvā na hatā, ȇ ja kāraṇȇ kȇsa cālyȏ nahīṃ, paṇa tȇmanȇ najarakȇda rākhavāmāṃ āvyā"
+  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; ૯૧ વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
+    expected: "saradāra paṭȇlȇ nakkī karyuṃ hatuṃ kȇ kāśmīra bhāratanȏ hissȏ banaśȇ; 91 varsha pahȇlāṃ lāhȏra jȇlamāṃ bhūkhahaḍatāḷa daramiyāna śahīda thayā hatā jatīna dāsa"
+  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
+    expected: "kȏrȏnā prȏṭȏkȏla vaccȇ ājȇ mȇḍikala pravȇśa parīkshā lȇvāśȇḥ ȇnṭrī ṭaca phrī rahȇśȇ, ȇḍamiṭa kārḍa bāra kȏḍathī cȇka thaśȇ"
+  - source: "અલ્ ક઼`ઇદ્ માં હવામાન"
+    expected: "al ka`id māṃ havāmāna"
+  - source: "મંત્રાલય તથા ખ઼.ય ના વિ૨ષ્ઠ અધિકા૨ીઓ ઉપસ્થિત ૨હ્યા હતા"
+    expected: "mantrālaya tathā kha.ya nā vi2shṭha adhikā2īȏ upasthita 2hyā hatā"
+
+
+map:
+
+  rules:
+    # note 3
+    - 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
+
+    # note[2(a,b)]
+    - pattern: ([ક]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'k'    
+    - pattern: ([ખ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'kh'   
+    - pattern: ([ગ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'g'    
+    - pattern: ([ઘ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'gh'   
+    - pattern: ([ઙ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ṅ'   
+    - pattern: ([ચ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'c'    
+    - pattern: ([છ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ch'   
+    - pattern: ([જ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'j'    
+    - pattern: ([ઝ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'jh'   
+    - pattern: ([ઞ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ñ'   
+    - pattern: ([ટ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṭ'  
+    - pattern: ([ઠ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṭh' 
+    - pattern: ([ડ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ḍ'  
+    - pattern: ([ઢ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ḍh' 
+    - pattern: ([ણ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṇ'  
+    - pattern: ([ત]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 't'    
+    - pattern: ([થ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'th'   
+    - pattern: ([દ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'd'    
+    - pattern: ([ધ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'dh'   
+    - pattern: ([ન]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'n'    
+    - pattern: ([પ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'p'    
+    - pattern: ([ફ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ph'   
+    - pattern: ([બ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'b'    
+    - pattern: ([ભ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'bh'   
+    - pattern: ([મ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'm'    
+    - pattern: ([ય]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'y'    
+    - pattern: ([ર]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'r'    
+    - pattern: ([લ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'l'    
+    - pattern: ([ળ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ḷ'    
+    - pattern: ([વ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'v'    
+    - pattern: ([શ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ś'   
+    - pattern: ([ષ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'sh'   
+    - pattern: ([સ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 's'    
+    - pattern: ([હ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'h'    
+
+
+  characters:
+
+    'અ': 'a'
+    'આ': 'ā'
+    'ઇ': 'i'
+    'ઈ': 'ī'
+    'ઉ': 'u'
+    'ઊ': 'ū'
+    'ઋ': 'ṛ'
+
+    'ઍ': 'e'
+    'એ': 'ȇ'
+    'ઐ': 'ai'
+
+    'ઑ': 'o'
+    'ઓ': 'ȏ'
+    'ઔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ક': 'ka'
+    'ખ': 'kha'
+    'ગ': 'ga'
+    'ઘ': 'gha'
+    'ઙ': 'ṅa'
+
+    # Palatals
+    'ચ': 'ca'
+    'છ': 'cha'
+    'જ': 'ja'
+    'ઝ': 'jha'
+    'ઞ': 'ña'
+
+    # Cerebrals
+    'ટ':  'ṭa'
+    'ઠ':  'ṭha'
+    'ડ':  'ḍa'
+    'ઢ':  'ḍha'
+    'ણ':  'ṇa'
+
+    # Dentals
+    'ત': 'ta'
+    'થ': 'tha'
+    'દ': 'da'
+    'ધ': 'dha'
+    'ન': 'na'
+
+    # Labials
+    'પ': 'pa'
+    'ફ': 'pha'
+    'બ': 'ba'
+    'ભ': 'bha'
+    'મ': 'ma'
+
+    # Semivowels
+    'ય': 'ya'
+    'ર': 'ra'
+    'લ': 'la'
+    'ળ': 'ḷa'
+    'વ': 'va'
+
+    # Sibilants
+    'શ': 'śa'
+    'ષ': 'sha'
+    'સ': 'sa'
+
+
+    # Aspirate
+    'હ': 'ha'
+
+    # Bisarga
+    'ઃ': 'ḥ'
+
+    # Anusvāra
+    'ં': 'ṃ'
+
+    # Abagraha  (see Note 4)
+    'ઽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    'ા': 'ā'
+    'િ': 'i'
+    'ી': 'ī'
+    'ુ': 'u'
+    'ૂ': 'ū'
+    'ૃ': 'ṛ'
+    'ૅ': 'e'
+    'ે': 'ȇ'
+    'ૈ': 'ai'
+    'ૉ': 'o'
+    'ો': 'ȏ'
+    'ૌ': 'au'
+
+    # digits
+
+    '૦': '0'
+    '૧': '1'
+    '૨': '2'
+    '૩': '3'
+    '૪': '4'
+    '૫': '5'
+    '૬': '6'
+    '૭': '7'
+    '૮': '8'
+    '૯': '9'
+
+
+
+    '્': ''
+    '઼': ''
+    '।': '.'
+    '\u09CD': '' # Used for joining
+    "‍": ''# Used for joining

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 +1,211 @@
+---
+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: "maīna"
+  - source: "औसत"
+    expected: "ăusata"
+  - source: "माँऽऽऽ!"
+    expected: "maān̐’’’!"
+  - source: "माँ"
+    expected: "maām̐"
+  - source: "गंभीर मरीजों के मामले में भारत दूसरे नंबर पर"
+    expected: "gaṃbhaīra maraījaoṃ kae maāmalae maeṃ bhaārata daūsarae naṃbara para"
+  - source: "कोरोना अपडेट्स"
+    expected: "kaoraonaā apaḍaeṭasa"
+  - source: "सीडीसी चीफ का बयान अहम"
+    expected: "saīḍaīsaī caīpha kaā bayaāna ahama"
+  - source: "गूगल प्ले स्टोर पर पेटीएम की वापसी"
+    expected: "gaūgala palae saṭaora para paeṭaīema kaī vaāpasaī"
+  - source: "भारत में गैंबलिंग की इजाजत नहीं"
+    expected: "bhaārata maeṃ gaaiṃbalaiṅga kaī ijaājata nahaīṃ"
+  - source: "कोरोना वैक्सीन मुद्दे पर घिरे राष्ट्रपति; जो बाइडेन बोले- मुझे और देश को वैज्ञानिकों पर भरोसा है, डोनाल्ड ट्रम्प पर नहीं"
+    expected: "kaoraonaā vaaikasaīna maudadae para ghairae raāshaṭarapatai; jao baāiḍaena baolae- maujhae ăura daeśa kao vaaijañaānaikaoṃ para bharaosaā haai, ḍaonaālaḍa ṭaramapa para nahaīṃ"
+  - 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: "gaūgala kaī kaāraravaāī para paeṭaīema nae kahaā thaā kai aipa kao asathaāyaī taăura para palae-saṭaora sae haṭaāyaā gayaā haai, āpakae paaisae saurakashaita haaiṃ"
+  - source: "२५६८७५४४६४४६१६११"
+    expected: "2568754464461611"
+
+map:
+
+  rules:
+    # 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'
+    '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'