interscript 0.1.7 → 0.1.9

data/maps/alalc-kan-Kana-Latn-2011.yaml

@@ -0,0 +1,63 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:kan
+source_script: Kana
+destination_script: Latn
+name: Kannada Romanization, 2011
+url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
+creation_date: 2011
+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: "ಭಾರತದಲ್ಲಿ ಗಾಳಿ ಕಲುಷಿತವಾಗಿದೆ: ಹವಾಮಾನ ಬದಲಾವಣೆ ಸಮರ್ಥನೆಗೆ ಭಾರತವನ್ನು ಟೀಕಿಸಿದ ಟ್ರಂಪ್"
+    expected: "bhāratadalli gāḷi kaluṣitavāgide: havāmāna badalāvaṇe samarthanege bhāratavannu ṭīkisida ṭraṃp"
+  - source: "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ ಅಂತಿಮ ಚರ್ಚೆ: ಭಾರತದ ವಿರುದ್ಧ ಟ್ರಂಪ್ ಆರೋಪವೇನು?!"
+    expected: "amerika adhyakṣīya cunāvaṇe aṃtima carce: bhāratada viruddha ṭraṃp ārōpavēnu?!"
+  - source: "ಹೇಗಿದೆ ಅಮೆರಿಕನ್‌ ಚುನಾವಣ ಕಣ?"
+    expected: "hēgide amerikan cunāvaṇa kaṇa?"
+  - source: "ಫ್ರೀಜರ್ ನಲ್ಲಿಟ್ಟ ನೂಡಲ್ಸ್ ತಿಂದು ಒಂದೇ ಕುಟುಂಬದ ೯ ಮಂದಿ ಸಾವು: ೩ ಮಕ್ಕಳು ಅಪಾಯದಿಂದ ಪಾರು"
+    expected: "phrījar nalliṭṭa nūḍals tiṃdu oṃdē kuṭuṃbada 9 maṃdi sāvu: 3 makkaḷu apāyadinda pāru"
+  - source: "ಉಡುಪಿಯಲ್ಲಿ ಪ್ರಪ್ರಥಮ ಬಾರಿಗೆ ಪ್ರಾರಂಭವಾಗಿರುವ ದೇಶಿ ಉತ್ಪನ್ನಗಳ ಮಳಿಗೆ"
+    expected: "uḍupiyalli praprathama bārige prāraṃbhavāgiruva dēśi utpannagaḷa maḷige"
+  - source: "ಚಿಕ್ಕಮಗಳೂರು : ಪುಷ್ಪ ಸಮರ್ಪಣೆ ವೇಳೆ ಮಗಳನ್ನ ನೆನೆದು ಕಣ್ಣೀರಿಟ್ಟ ಮೃತ ಪೇದೆ ತಾಯಿ"
+    expected: "cikkamagaḷūru : puṣpa samarpaṇe vēḷe magaḷanna nenedu kaṇṇīriṭṭa mṛta pēde tāyi"
+  - source: "ಸಮಂಗಳೂರು: ಡ್ರಗ್ಸ್ ಜಾಗೃತಿ ಬರಹದಿಂದ ಗಮನಸೆಳೆಯುತ್ತಿದೆ ಸಿಟಿ ಬಸ್"
+    expected: "samaṅgaḷūru: ḍrags jāgṛti barahadinda gamanaseḷeyuttide siṭi bas"
+  - source: "ಪುರಸಭೆ, ಪಪಂ ಅಧ್ಯಕ್ಷ-ಉಪಾಧ್ಯಕ್ಷ ಚುನಾವಣೆಗೆ ಹೈಕೋರ್ಟ್‌ ಅಸ್ತು"
+    expected: "purasabhe, papaṃ adhyakṣa-upādhyakṣa cunāvaṇege haikōrṭ astu"
+  - source: "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ ಅಂತಿಮ ಚರ್ಚೆ: ಭಾರತದ ವಿರುದ್ಧ ಟ್ರಂಪ್ ಆರೋಪವೇನು?"
+    expected: "amerika adhyakṣīya cunāvaṇe aṃtima carce: bhāratada viruddha ṭraṃp ārōpavēnu?"
+  - source: "ಮನೆ ಕುಸಿದು ತಂದೆ ಮತ್ತು ಮಗ ಸಾವು, ಇನ್ನಿಬ್ಬರಿಗೆ ಗಾಯ: ಸ್ಥಳಕ್ಕೆ ಶಾಸಕರ ಭೇಟಿ"
+    expected: "mane kusidu taṃde mattu maga sāvu, innibbarige gāya: sthaḷakke śāsakara bhēṭi"
+
+map:
+  inherit: 'alalc-kan-Kana-Latn-1997'

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-pra-Deva-Latn-2012.yaml

@@ -38,9 +38,9 @@ notes:
 
 tests:
   - source: "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि"
-    expected: "saṛṣaṭaisathaitaivainaāśaānaāṃ śakataibhaūtae sanaātanai"
+    expected: "sṛṣṭisthitivināśānāṃ śaktibhūte sanātani"
   - source: "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते"
-    expected: "gauṇaāśarayae gauṇamayae naāraāyaṇai namao’satau tae"
+    expected: "guṇāśraye guṇamaye nārāyaṇi namo’stu te"
 
 map:
 

data/maps/alalc-san-Deva-Latn-2012.yaml

@@ -38,27 +38,96 @@ notes:
 
 tests:
   - source: "पूर्णमदः पूर्णमिदं पूर्णात् पूर्ण्मुदच्यते"
-    expected: "paūraṇamadaḥ paūraṇamaidaṃ paūraṇaāta paūraṇamaudacayatae"
+    expected: "pūrṇamadaḥ pūrṇamidaṃ pūrṇāt pūrṇmudacyate"
   - source: "पूर्णस्य पूर्णमादाय पूर्णमेवावशिष्यते"
-    expected: "paūraṇasaya paūraṇamaādaāya paūraṇamaevaāvaśaiṣayatae"
+    expected: "pūrṇasya pūrṇamādāya pūrṇamevāvaśiṣyate"
   - source: "यथा चतुर्भिः कनकं परीक्ष्यते निर्घषणच्छेदन तापताडनैः"
-    expected: "yathaā cataurabhaiḥ kanakaṃ paraīkaṣayatae nairaghaṣaṇacachaedana taāpataāḍanaaiḥ"
+    expected: "yathā caturbhiḥ kanakaṃ parīkṣyate nirghaṣaṇacchedana tāpatāḍanaiḥ"
   - source: "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा"
-    expected: "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+    expected: "tathā caturbhiḥ puruṣaḥ parīkṣyate tyāgena śīlena guṇena karmaṇā"
   - source: "यो न हृष्यति न द्वेष्टि न शोचति न काङ्‍क्षति"
-    expected: "yao na haṛṣayatai na davaeṣaṭai na śaocatai na kaāṅakaṣatai"
+    expected: "yo na hṛṣyati na dveṣṭi na śocati na kāṅkṣati"
   - source: "शुभाशुभपरित्यागी भक्तिमान्यः स मे प्रियः"
-    expected: "śaubhaāśaubhaparaitayaāgaī bhakataimaānayaḥ sa mae paraiyaḥ"
+    expected: "śubhāśubhaparityāgī bhaktimānyaḥ sa me priyaḥ"
   - source: "सत्य -सत्यमेवेश्वरो लोके सत्ये धर्मः सदाश्रितः"
-    expected: "sataya -satayamaevaeśavarao laokae satayae dharamaḥ sadaāśaraitaḥ"
+    expected: "satya -satyameveśvaro loke satye dharmaḥ sadāśritaḥ"
   - source: "सत्यमूलनि सर्वाणि सत्यान्नास्ति परं पदम्"
-    expected: "satayamaūlanai saravaāṇai satayaānanaāsatai paraṃ padama"
+    expected: "satyamūlani sarvāṇi satyānnāsti paraṃ padam"
   - source: "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ"
-    expected: "paitaā maātaāganairaātamaā ca gaurauśaca bharataraṣabha"
+    expected: "pitā mātāgnirātmā ca guruśca bharatarṣabha"
 
 map:
 
   rules:
+    # note [2]
+    - pattern: (क=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'k'
+    - pattern: (ख=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'kh'
+    - pattern: (ग=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'g'
+    - pattern: (घ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'gh'
+    - pattern: (ङ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ṅ'
+    - pattern: (च=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'c'
+    - pattern: (छ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ch'
+    - pattern: (ज=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'j'
+    - pattern: (झ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'jh'
+    - pattern: (ञ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ñ'
+    - pattern: (ट=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ṭ'
+    - pattern: (ठ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ṭh'
+    - pattern: (ड=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ḍ'
+    - pattern: (ढ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ḍh'
+    - pattern: (ण=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ṇ'
+    - pattern: (त=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  't'
+    - pattern: (थ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'th'
+    - pattern: (द=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'd'
+    - pattern: (ध=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'dh'
+    - pattern: (न=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'n'
+    - pattern: (प=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'p'
+    - pattern: (फ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ph'
+    - pattern: (ब=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'b'
+    - pattern: (भ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'bh'
+    - pattern: (म=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'm'
+    - pattern: (य=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'y'
+    - pattern: (र=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'r'
+    - pattern: (ल=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'l'
+    - pattern: (ळ=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ḻ'
+    - pattern: (व=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'v'
+    - pattern: (श=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ś'
+    - pattern: (ष=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'ṣ'
+    - pattern: (स=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  's'
+    - pattern: (ह=?)(?=[\u093e\u093f\u0940\u0941\u0942\u0943\u0944\u0947\u0948\u094b\u094c\u094d])
+      result:  'h'
     # note[3]
     - pattern: \u0902(?=[कखगघङ])
       result: ṅ