interscript 0.1.3 → 0.1.9

data/maps/alalc-ori-Orya-Latn-1997.yaml

@@ -0,0 +1,284 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:ori
+source_script: Orya
+destination_script: Latn
+name: Oriya Romanization, 1997
+alias:
+  ogc11122:
+    code: ori_Orya2Latn_ALA_1997
+    description: Oriya ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/oriya.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Oriya
+
+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 hasanta.
+  - |
+    ବ is used both as a labial and as a semivowel. When it occurs as the second consonant of a
+    consonant cluster, it is transliterated va. When ବ is doubled, it is transliterated bba.
+  - |
+    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.
+  - |
+    Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m̐.
+  - When doubled, abagraha is transliterated by two apostrophes ( ’’ ).
+tests:
+  - source: "ର୍କ"
+    expected: "rka"
+  - source: "ଓଡ଼ିଆ"
+    expected: "oṙiā"
+  - source: "ଓଡ଼ିଶା"
+    expected: "oṙiśā"
+  - source: "ଭୁବନେଶ୍ୱର"
+    expected: "bhubaneśwara"
+  - source: "ଆଇପିଏଲ୍‌-୧୩: ରୟାଲ ଚ୍ୟାଲେଞ୍ଜର୍ସ ବାଙ୍ଗାଲୋରକୁ ୫ ଓ୍ୱିକେଟରେ ପରାସ୍ତ କଲା ମୁମ୍ବାଇ ଇଣ୍ଡିଆନ୍ସ"
+    expected: "āipiel-13: raẏāla cẏāleñjarsa bāṅgāloraku 5 obikeṭare parāsta kalā mumbāi iṇḍiānsa"
+  - source: "ଓଡ଼ିଶା ସିଭିଲ ସର୍ଭିସେସ୍‌ ମେନ୍‌ ପରୀକ୍ଷା ଡିସେମ୍ବରରେ, ଜାଣନ୍ତୁ କେଉଁ ବିଷୟର ପରୀକ୍ଷା କେବେ"
+    expected: "oṙiśā sibhila sarbhises men parīkshā ḍisembarare, jāṇantu keum̐ bishaẏara parīkshā kebe"
+  - source: "ଗଞ୍ଜାମରେ କୋଭିଡ଼ ମୃତ୍ୟୁ ୨୨୮ରେ ପହଞ୍ଚିଲା"
+    expected: "gañjāmare keābhiṙa mṛtẏu 228re pahañcilā"
+  - source: "ଭାରତ ମହାସାଗର ଦ୍ବୀପରାଷ୍ଟ୍ର ଶ୍ରୀଲଙ୍କା ଓ ମାଳଦ୍ବୀପରେ ପମ୍ପିଓଙ୍କ ଚୀନ୍‌ବିରୋଧୀ ଅଭିଯାନ"
+    expected: "bhārata mahāsāgara dbīparāshṭra śrīlaṅkā o māḷadbīpare pampioṅka cīnbireādhī abhiyāna"
+  - source: "କଟକ ସହରରୁ ଆଜି ୩୯ କରୋନା ପଜିଟିଭ୍‌ ଚିହ୍ନଟ, ସ୍ଥାନୀୟ ଅଂଚଳରୁ ୨୪ ଜଣ ଆକ୍ରାନ୍ତ"
+    expected: "kaṭaka sahararu āji 39 karonā pajiṭibh cihnaṭa, sthānīẏa aṃcaḷaru 24 jaṇa ākrānta"
+  - source: "ବିଧାୟକ ସୌମ୍ୟରଂଜନଙ୍କ ମାରାଥନ ପ୍ରଚାର: ‘ଦ୍ୱିତୀୟବାର ସୁଯୋଗ ମିଳିଛି, ବୁଝି ବିଚାରି ଭୋଟ ଦିଅ’"
+    expected: "bidhāẏaka seୗmẏaraṃjanaṅka mārāthana pracāra: ‘dbitīẏabāra suyeāga miḷichi, bujhi bicāri bheāṭa dia’"
+  - source: "ଅଣ୍ଡା ବିଗାଡ଼ିଛି ପୁଷ୍ଟିକର ଖାଦ୍ୟ ଯୋଜନା ଅଙ୍କ"
+    expected: "aṇḍā bigāṙichi pushṭikara khādẏa yeājanā aṅka"
+  - source: "ପଥରଗଡ଼ ମଦ ମୃତ୍ୟୁ ମାମଲା : ଠିକାଦାର ସହ ବନ୍ଧାହେଲେ ୪"
+    expected: "patharagaḍa mada mṛtẏu māmalā : ṭhikādāra saha bandhāhele 4"
+  - source: "ତିର୍ତ୍ତୋଲର ବିକାଶ ନେଇ ବିଷ୍ଣୁବାବୁ ମୋତେ ବହୁ ବାର ଭେଟୁଥିଲେ: ନବୀନ"
+    expected: "tirtteālara bikāśa nei bishṇubābu mote bahu bāra bheṭuthile: nabīna"
+
+
+map:
+
+  rules:
+    # Rule II
+    - pattern: ([କ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'k'
+    - pattern: ([ଖ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'kh'
+    - pattern: ([ଗ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'g'
+    - pattern: ([ଘ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'gh'
+    - pattern: ([ଙ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṅ'
+    - pattern: ([ଚ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'c'
+    - pattern: ([ଛ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ch'
+    - pattern: ([ଜ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'j'
+    - pattern: ([ଝ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'jh'
+    - pattern: ([ଞ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ñ'
+    - pattern: ([ଟ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṭ'
+    - pattern: ([ଠ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṭh'
+    - pattern: ([ଡ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ḍ'
+    - pattern: ([ଢ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ḍh'
+    - pattern: ([ଣ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṇ'
+    - pattern: ([ତ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  't'
+    - pattern: ([ଥ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'th'
+    - pattern: ([ଦ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'd'
+    - pattern: ([ଧ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'dh'
+    - pattern: ([ନ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'n'
+    - pattern: ([ପ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'p'
+    - pattern: ([ଫ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ph'
+    - pattern: ([ବ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'b'
+    - pattern: ([ଭ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'bh'
+    - pattern: ([ମ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'm'
+    - pattern: ([ଯ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'y'
+    - pattern: ([ୟ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ẏ'
+    - pattern: ([ର]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'r'
+    - pattern: ([ଲ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'l'
+    - pattern: ([ଳ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ḷ'
+    - pattern: ([ଶ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ś'
+    - pattern: ([ଷ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'sh'
+    - pattern: ([ସ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  's'
+    - pattern: ([ହ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'h'
+    - pattern: ([ୱ]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'b'
+    - pattern: ([ଡ଼]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṙ'
+    - pattern: ([ଢ଼]=?)(?=[\u0b4d\u0b3e\u0b3f\u0b40\u0b41\u0b42\u0b43\u0b47\u0b48\u0b4b\u0b4c])
+      result:  'ṙh'
+
+    # Rule III
+    - pattern: ([ବ]=?)(?=[\u0b2c])
+      result:  'bba'
+    # Rule IV
+    - pattern: \u0902(?=[କଖଗଘଙ])
+      result: ṅ
+    - pattern: \u0902(?=[ଚଛଜଝଞ])
+      result: ñ
+    - pattern: \u0902(?=[ଟଠଡଢଣ])
+      result: ṇ
+    - pattern: \u0902(?=[ତଥଦଧନ])
+      result: n
+    # Rule V
+    - pattern: \u0b01(?=[ପଫବଭମଯୟରଲଳଶଷସହଅଆଇଈଉଊଋୠଌଏଐଓଔ])
+      result: "m̐"
+    - pattern: (?<=)\u0b01(?=\b)
+      result: "m̐"
+
+  characters:
+    'ଅ': 'a'
+    'ଆ': 'ā'
+    'ଇ': 'i'
+    'ଈ': 'ī'
+    'ଉ': 'u'
+    'ଊ': 'ū'
+    'ଋ': 'ṛ'
+    'ୠ': 'ṝ'
+    'ଌ': 'ḻ'
+    'ଏ': 'e'
+    'ଐ': 'ai'
+    'ଓ': 'o'
+    'ଔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'କ': 'ka'
+    'ଖ': 'kha'
+    'ଗ': 'ga'
+    'ଘ': 'gha'
+    'ଙ': 'ṅa'
+
+    # Palatals
+    'ଚ': 'ca'
+    'ଛ': 'cha'
+    'ଜ': 'ja'
+    'ଝ': 'jha'
+    'ଞ': 'ña'
+
+    # Cerebrals
+    'ଟ':  'ṭa'
+    'ଠ':  'ṭha'
+    'ଡ':  'ḍa'
+    'ଢ':  'ḍha'
+    'ଣ':  'ṇa'
+
+    # Dentals
+    'ତ': 'ta'
+    'ଥ': 'tha'
+    'ଦ': 'da'
+    'ଧ': 'dha'
+    'ନ': 'na'
+
+    # Labials
+    'ପ': 'pa'
+    'ଫ': 'pha'
+    'ବ': 'ba'
+    'ଭ': 'bha'
+    'ମ': 'ma'
+
+    # Semivowels
+    'ଯ': 'ya'
+    'ୟ': 'ẏa'
+    'ର': 'ra'
+    'ଲ': 'la'
+    'ଳ': 'ḷa'
+
+    # Sibilants
+    'ଶ': 'śa'
+    'ଷ': 'sha'
+    'ସ': 'sa'
+
+
+    # Aspirate
+    'ହ': 'ha'
+
+    # Chandrabindu
+    'ଁ': 'n̐'
+
+    # Bisarga
+    'ଃ': 'ḥ'
+
+    # Anusvāra
+    'ଂ': 'ṃ'
+
+    # Abagraha
+    'ଽ': "’"
+
+    # Medials # Needed for connecting constants
+
+    'ା': 'ā'
+    'ି': 'i'
+    'ୀ': 'ī'
+    'ୁ': 'u'
+    'ୂ': 'ū'
+    'ୃ': 'ṛ'
+    'େ': 'e'
+    'ୈ': 'ai'
+    'ୋ': 'o'
+    'ୌ': 'au'
+
+    '्': ''
+    '୍': ''
+    '़': ''
+    '଼': ''
+    '।': '.'
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+
+    #Absent but used
+    'ୱ': 'wa'
+    'ଡ଼':  'ṙa'
+    'ଢ଼':  'ṙha'
+
+    # Numbers
+
+    '୦': '0'
+    '୧': '1'
+    '୨': '2'
+    '୩': '3'
+    '୪': '4'
+    '୫': '5'
+    '୬': '6'
+    '୭': '7'
+    '୮': '8'
+    '୯': '9'
+

data/maps/alalc-ori-Orya-Latn-2011.yaml

@@ -0,0 +1,67 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:ori
+source_script: Orya
+destination_script: Latn
+name: Oriya Romanization, 2011
+alias:
+  ogc11122:
+    code: ori_Orya2Latn_ALA_2011
+    description: Oriya ALA-Library of Congress 2011 System
+url: https://www.loc.gov/catdir/cpso/romanization/oriya.pdf
+creation_date: 2011
+description: |
+  ALA-LC Romanization table for Oriya
+
+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 hasanta.
+  - |
+    ବ is used both as a labial and as a semivowel. When it occurs as the second consonant of a
+    consonant cluster, it is transliterated va. When ବ is doubled, it is transliterated bba.
+  - |
+    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.
+  - |
+    Candrabindu before guttural, palatal, cerebral, and dental occlusives is transliterated n̐.
+    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
+    transliterated m̐.
+  - When doubled, abagraha is transliterated by two apostrophes ( ’’ ).
+tests:
+  - source: "ବିହାର ନିର୍ବାଚନ: ସନ୍ଧ୍ୟା ୬ଟା ସୁଦ୍ଧା ୫୩.୫୪ ପ୍ରତିଶତ ମତଦାନ"
+    expected: "bihāra nirbācana: sandhẏā 6ṭā suddhā 53.54 pratiśata matadāna"
+  - source: "ଡିସେମ୍ବର ସୁଦ୍ଧା ପ୍ରସ୍ତୁତ ହୋଇଯିବ ଅକ୍ସଫୋର୍ଡ କରୋନାଭାଇରସ୍ ଟିକା: ଅଦର ପୁନାୱାଲା"
+    expected: "ḍisembara suddhā prastuta heāiyiba aksapheārḍa kareānābhāiras ṭikā: adara punābālā"
+  - source: "କରୋନା ଆକ୍ରାନ୍ତ ହେଲେ କେନ୍ଦ୍ରମନ୍ତ୍ରୀ ସ୍ମୃତି ଇରାନୀ"
+    expected: "karonā ākrānta hele kendramantrī smṛti irānī"
+  - source: "ଆମେରିକା ଉପରେ ଉତ୍‌କ୍ଷିପ୍ତ ହୋଇ ଚୀନ୍ କହିଲା: ଭାରତ ସହ ଆମର ସୀମା ବିବାଦ ଦ୍ବିପାକ୍ଷିକ ମାମଲା"
+    expected: "āmerikā upare utkshipta heāi cīn kahilā: bhārata saha āmara sīmā bibāda dbipākshika māmalā"
+  - source: "ପରଲୋକରେ ଦକ୍ଷିଣ କୋରିଆର ସବୁଠୁ ଧନୀବ୍ୟକ୍ତି ‘ସାମ୍‌ସଙ୍ଗ୍’ ଅଧ୍ୟକ୍ଷ ଲି କୁନ୍-ହି; ଛାଡ଼ିଯାଇଛନ୍ତି ୨୧ ବିଲିୟନ୍ ଡଲାର୍‌ର ସାମ୍ରାଜ୍ୟ"
+    expected: "paraleākare dakshiṇa keāriāra sabuṭhu dhanībẏakti ‘sāmsaṅg’ adhẏaksha li kun-hi; chāṙiyāichanti 21 biliẏan ḍalārra sāmrājẏa"
+  - source: "ଉପନିର୍ବାଚନ ପାଇଁ ବାଲେଶ୍ୱରରେ ବିଜେଡିର ସମାବେଶ। (ଫଟୋ: ମନୋଜ ବିଶ୍ୱାଳ)"
+    expected: "upanirbācana pāim̐ bāleśwarare bijeḍira samābeśa. (phaṭo: manoja biśbāḷa)"
+  - source: "ନୂଆପଲ୍ଲୀ ଦୁର୍ଗାପୂଜା ମଣ୍ଡପ ବାହାରେ ମା’ଙ୍କୁ ପୂଜାର୍ଚ୍ଚନା କରୁଛନ୍ତି ଭକ୍ତ। (ଫଟୋ: ବିଭୂତି)"
+    expected: "nūāpallī durgāpūjā maṇḍapa bāhāre mā’ṅku pūjārccanā karuchanti bhakta. (phaṭo: bibhūti)"
+  - source: "ମା ଶାରଳାଙ୍କ ପୀଠରେ ଦଶମୀ ପୂଜା। (ଫଟୋ: ସୋମନାଥ, ଜଗତସିଂହପୁର ଟାଉନ୍‌)"
+    expected: "mā śāraḷāṅka pīṭhare daśamī pūjā. (phaṭo: somanātha, jagatasiṃhapura ṭāun)"
+  - source: "ଆଜି ବିହାରରେ ପ୍ରଥମ ପର୍ଯ୍ୟାୟ ଭୋଟ, ମହାମେଣ୍ଟ-ଏନ୍‌ଡିଏ କଡ଼ା ଟକ୍କର"
+    expected: "āji bihārare prathama paryẏāẏa bheāṭa, mahāmeṇṭa-enḍie kaṙā ṭakkara"
+  - source: "ନିର୍ବାଚନ ପ୍ରଚାରରୁ ଫେରି ନିଜ ଅଭିଜ୍ଞତା ବଖାଣି ଅମିଷା କହିଲେ, ‘କୌଣସି ପରିସ୍ଥିତିରେ ମୋର ସହିତ ଦୁଷ୍କର୍ମ ହେବାର ଆଶଙ୍କା ରହିଥିଲା’"
+    expected: "nirbācana pracāraru pheri nija abhijñatā bakhāṇi amishā kahile, ‘keୗṇasi paristhitire meāra sahita dushkarma hebāra āśaṅkā rahithilā’"
+  - source: "ବ୍ଲୁ ଫ୍ଲାଗ ବିଚ୍‌ରେ ଅଘଟଣ: ମା’ ଆଗରେ ସମୁଦ୍ରରେ ଭାସିଗଲେ ପୁଅ, ଖୋଜିବା ପାଇଁ ଲାଇଫଗାର୍ଡ ଟିମ୍‌ ନିୟୋଜିତ"
+    expected: "blu phlāga bicre aghaṭaṇa: mā’ āgare samudrare bhāsigale pua, kheājibā pāim̐ lāiphagārḍa ṭim niẏeājita"
+
+map:
+
+  inherit: alalc-ori-Orya-Latn-1997

data/maps/alalc-pan-Guru-Latn-1997.yaml

@@ -0,0 +1,256 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:pan
+source_script: Guru
+destination_script: Latn
+name: Panjabi Romanization, 1997
+alias:
+  ogc11122:
+    code: pan_Deva2Latn_ALA_1997
+    description: Panjabi ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/panjabi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Panjabi
+
+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 consonant clusters and may be implicit after consonants except
+    when they are final or when another vowel is indicated by its appropriate sign. The cases in
+    which the vowel a is implicit, however, can be determined only from a knowledge of the
+    language or from suitable reference sources. In such cases the a is supplied in transliteration.
+
+  - The dotted letters (ਸ਼ ਖ਼ ਗ਼ ਜ਼ ਫ਼ ਲ਼) are used in Urdu words.
+
+  - |
+    Exception: Bindī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: Ṭippī is transliterated by:
+
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - |
+    Exception: When adhik implies the combination of a non-aspirated and an aspirated
+    consonant, the combination is transliterated as a non-aspirated, followed by an aspirated
+    consonant.
+
+tests:
+  - source: "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ"
+    expected: "pañjaāba 'ca wadha raihaā khaudakaushaīāṃ daā raujhaāna"
+  - source: "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ"
+    expected: "lakkha taoṃ paāra paujjaā saragarama kaesaāṃ daā aṅkaṛaā, daillaī 'ca dao lakkha taoṃ paāra inaphaaikaṭaiḍa"
+  - source: "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ"
+    expected: "paraiwaāraka samassaiāwaāṃ atae waiāha waī haai haora ahaima kaārana"
+  - source: "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ"
+    expected: "maradaāṃ 'ca aurataāṃ naālaoṃ waddha haai khaudakaushaī daā raujhaāna"
+  - source: "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ"
+    expected: "raāshaṭaraī paddhara 'tae pañjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+  - source: "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ"
+    expected: "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujawaānaāṃ baārae dassaiā"
+  - source: "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ"
+    expected: "saākharataā dae maāmalae 'ca daesha 'ca 7waeṃ nam̆̐bara 'tae pañjaāba"
+  - source: "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ"
+    expected: "daillaī kamaeṭaī dae maaiṃbara shaṇṭaī nae akaālaī dala taoṃ daittaā asataīfaā"
+  - source: "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+    expected: "102 haora kaoraonaā paāzaīṭaiwa maraīzaāṃ daī paushaṭaī, ika daī maauta"
+  - source: "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ"
+    expected: "saṛaka haādasae daauraāna ika daī maauta"
+
+map:
+
+  rules:
+    # note[4]
+    - pattern: \u0A02(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ਂ  before gutturals
+      result: ṅ
+    - pattern: \u0A02(?=[ਚਛਜਜ਼ਝਞ])    # ਂ   before palatals
+      result: ñ
+    - pattern: \u0A02(?=[ਟਠਡਢਣ])    # ਂ   before cerebrals
+      result: ṇ
+    - pattern: \u0A02(?=[ਤਥਦਧਨ])    # ਂ   before dentals
+      result: n
+
+    # note[5]
+    - pattern: \u0A70(?=[ਕਖਖ਼ਗਗ਼ਘਙ])    # ੰ  before gutturals
+      result: ṅ
+    - pattern: \u0A70(?=[ਚਛਜਜ਼ਝਞ])    # ੰ  before palatals
+      result: ñ
+    - pattern: \u0A70(?=[ਟਠਡਢਣ])    # ੰ  before cerebrals
+      result: ṇ
+    - pattern: \u0A70(?=[ਤਥਦਧਨ])    # ੰ  before dentals
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ਏ': 'e'
+    'ਐ': 'ai'
+    'ਓ': 'o'
+    'ਔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ਕ': 'ka'
+    'ਖ': 'kha'
+    'ਖ਼': 'kha'
+    'ਗ': 'ga'
+    'ਗ਼': 'gha'
+    'ਘ': 'gha'
+    'ਙ': 'ṅa'
+
+    # Palatals
+    'ਚ': 'ca'
+    'ਛ': 'cha'
+    'ਜ਼': 'za'
+    'ਜ': 'ja'
+    'ਝ': 'jha'
+    'ਞ': 'ña'
+
+    # Cerebrals
+    'ਟ': 'ṭa'
+    'ਠ': 'ṭha'
+    'ਡ': 'ḍa'
+    'ਢ': 'ḍha'
+    'ਣ': 'ṇa'
+
+    # Dentals
+    'ਤ': 'ta'
+    'ਥ': 'tha'
+    'ਦ': 'da'
+    'ਧ': 'dha'
+    'ਨ': 'na'
+
+    # Labials
+    'ਪ': 'pa'
+    'ਫ': 'pha'
+    'ਫ਼': 'fa'
+    'ਬ': 'ba'
+    'ਭ': 'bha'
+    'ਮ': 'ma'
+
+    # Semivowels
+    'ਯ': 'ya'
+    'ਰ': 'ra'
+    'ਲ': 'la'
+    'ਲੵ': 'ḷa'
+    'ਲ਼': 'ḷa'
+    'ਵ': 'wa'
+    'ੜ': 'ṛa'
+
+    # Sibilants
+    'ਸ': 'sa'
+    'ਸ਼': 'sha'
+
+    # Aspirate
+    'ਹ': 'ha'
+
+    # Bindī (see Note 4)
+    'ਂ': 'ṃ'
+
+    # Ṭippī (see Note 5)
+    'ੰ': 'm̆̐'
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ੇ': "e"
+    'ੈ': "ai"
+    'ੋ': "o"
+    'ੌ': "au"
+
+    # For adhik character[Note 6]
+
+    # Gutturals
+    'ੱਕ': 'kka'
+    'ੱਖ': 'kkha'
+    'ੱਖ਼': 'kkha'
+    'ੱਗ': 'gga'
+    'ੱਗ਼': 'ggha'
+    'ੱਘ': 'ggha'
+    'ੱਙ': 'ṅṅa'
+
+    # Palatals
+    'ੱਚ': 'cca'
+    'ੱਛ': 'ccha'
+    'ੱਜ': 'jja'
+    'ੱਜ਼': 'zza'
+    'ੱਝ': 'jjha'
+    'ੱਞ': 'ñña'
+
+    # Cerebrals
+    'ੱਟ': 'ṭṭa'
+    'ੱਠ': 'ṭṭha'
+    'ੱਡ': 'ḍḍa'
+    'ੱਢ': 'ḍḍha'
+    'ੱਣ': 'ṇṇa'
+
+    # Dentals
+    'ੱਤ': 'tta'
+    'ੱਥ': 'ttha'
+    'ੱਦ': 'dda'
+    'ੱਧ': 'ddha'
+    'ੱਨ': 'nna'
+
+    # Labials
+    'ੱਪ': 'ppa'
+    'ੱਫ': 'ppha'
+    'ੱਫ਼': 'ffa'
+    'ੱਬ': 'bba'
+    'ੱਭ': 'bbha'
+    'ੱਮ': 'mma'
+
+    # Semivowels
+    'ੱਯ': 'yya'
+    'ੱਰ': 'rra'
+    'ੱਲ': 'lla'
+    'ੱਲੵ': 'ḷḷa'
+    'ੱਵ': 'wwa'
+    'ੱੜ': 'ṛṛa'
+
+    # Sibilants
+    'ੱਸ': 'ssa'
+    'ੱਸ਼': 'ssha'
+
+    # Aspirate
+    'ੱਹ': 'hha'
+
+
+    # digits
+
+    '੦': '0'
+    '੧': '1'
+    '੨': '2'
+    '੩': '3'
+    '੪': '4'
+    '੫': '5'
+    '੬': '6'
+    '੭': '7'
+    '੮': '8'
+    '੯': '9'
+