interscript 0.1.6 → 0.1.7

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

@@ -0,0 +1,144 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:pli
+source_script: Deva
+destination_script: Latn
+name: Pali Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/pali.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Pali
+
+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: Niggahīta combinations representing nasals are romanized by ṅ
+    before gutturals, ñ before palatals, ṇ before cerebrals, n before dentals, and m before
+    labials.
+
+tests:
+  - source: "तेन खो पन समयेन वेसालिया अविदूरे कलन्दगामो नाम अत्थि"
+    expected: "taena khao pana samayaena vaesaālaiyaā avaidaūrae kalanadagaāmao naāma atathai"
+  - source: "तत्थ सुदिन्‍नो नाम कलन्दपुत्तो सेट्ठिपुत्तो होति"
+    expected: "tatatha saudainanao naāma kalanadapautatao saeṭaṭhaipautatao haotai"
+  - source: "अथ खो सुदिन्‍नो कलन्दपुत्तो सम्बहुलेहि"
+    expected: "atha khao saudainanao kalanadapautatao samabahaulaehai"
+  - source: "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा"
+    expected: "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+  - source: "अथ खो सुदिन्‍नो कलन्दपुत्तो अचिरवुट्ठिताय परिसाय येन भगवा तेनुपसङ्कमि; उपसङ्कमित्वा भगवन्तं अभिवादेत्वा एकमन्तं निसीदि"
+    expected: "atha khao saudainanao kalanadapautatao acairavauṭaṭhaitaāya paraisaāya yaena bhagavaā taenaupasaṅakamai; upasaṅakamaitavaā bhagavanataṃ abhaivaādaetavaā ekamanataṃ naisaīdai"
+  - source: "अथ खो सुदिन्‍नस्स कलन्दपुत्तस्स मातापितरो सुदिन्‍नं कलन्दपुत्तं एतदवोचुं"
+    expected: "atha khao saudainanasasa kalanadapautatasasa maātaāpaitarao saudainanaṃ kalanadapautataṃ etadavaocauṃ"
+  - source: "त्वं खोसि, तात सुदिन्‍न, अम्हाकं एकपुत्तको पियो मनापो सुखेधितो सुखपरिहतो"
+    expected: "tavaṃ khaosai, taāta saudainana, amahaākaṃ ekapautatakao paiyao manaāpao saukhaedhaitao saukhaparaihatao"
+  - source: "न त्वं, तात सुदिन्‍न, किञ्‍चि दुक्खस्स जानासि"
+    expected: "na tavaṃ, taāta saudainana, kaiñacai daukakhasasa jaānaāsai"
+  - source: "अनुञ्‍ञातोम्हि किर मातापितूहि अगारस्मा अनगारियं पब्बज्‍जाया’’ति, हट्ठो उदग्गो पाणिना गत्तानि परिपुञ्छन्तो वुट्ठासि"
+    expected: "anauñañaātaomahai kaira maātaāpaitaūhai agaārasamaā anagaāraiyaṃ pababajajaāyaā’’tai, haṭaṭhao udagagao paāṇainaā gatataānai paraipauñachanatao vauṭaṭhaāsai"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+
+  characters:
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    'अ': 'a'
+    'आ': 'ā'
+    'इ': 'i'
+    'ई': 'ī'
+    'उ': 'u'
+    'ऊ': 'ū'
+    'ए': 'e'
+    'ओ': 'o'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    'ढ': 'ḍha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'ळ': 'ḻa'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'ṣa'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Visagga
+    'ः': 'ḥ'
+
+    # Niggahīta/Anusvāra
+    'ं': 'ṃ'
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'े': "e"
+    'ो': "o"
+    '्': ""
+    '‍': ''# Used for joining

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

@@ -0,0 +1,47 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:pra
+source_script: Deva
+destination_script: Latn
+name: Prakrit Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/sanskrit.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Prakrit
+
+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.
+    In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि"
+    expected: "saṛṣaṭaisathaitaivainaāśaānaāṃ śakataibhaūtae sanaātanai"
+  - source: "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते"
+    expected: "gauṇaāśarayae gauṇamayae naāraāyaṇai namao’satau tae"
+
+map:
+
+  inherit: "alalc-san-Deva-Latn-2012"

data/maps/alalc-rus-Cyrl-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization System 1997
+alias:
+  ogc11122:
+    code: rus_Cyrl2Latn_ALA_1997
+    description: Russian ALA-Library of Congress 1997 System
 url: https://en.wikipedia.org/wiki/ALA-LC_romanization_for_Russian
 creation_date: 1997
 description: |

data/maps/alalc-rus-Cyrl-Latn-2012.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 2012
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization System 2012

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

@@ -0,0 +1,172 @@
+---
+authority_id: alalc
+id: 2012
+language: iso-639-2:san
+source_script: Deva
+destination_script: Latn
+name: Sanskrit Romanization, 2012
+url: https://www.loc.gov/catdir/cpso/romanization/sanskrit.pdf
+creation_date: 2012
+description: |
+  ALA-LC Romanization table for Sanskrit
+
+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.
+    In other circumstances it is transliterated by a tilde (~) over the vowel.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "पूर्णमदः पूर्णमिदं पूर्णात् पूर्ण्मुदच्यते"
+    expected: "paūraṇamadaḥ paūraṇamaidaṃ paūraṇaāta paūraṇamaudacayatae"
+  - source: "पूर्णस्य पूर्णमादाय पूर्णमेवावशिष्यते"
+    expected: "paūraṇasaya paūraṇamaādaāya paūraṇamaevaāvaśaiṣayatae"
+  - source: "यथा चतुर्भिः कनकं परीक्ष्यते निर्घषणच्छेदन तापताडनैः"
+    expected: "yathaā cataurabhaiḥ kanakaṃ paraīkaṣayatae nairaghaṣaṇacachaedana taāpataāḍanaaiḥ"
+  - source: "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा"
+    expected: "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+  - source: "यो न हृष्यति न द्वेष्टि न शोचति न काङ्‍क्षति"
+    expected: "yao na haṛṣayatai na davaeṣaṭai na śaocatai na kaāṅakaṣatai"
+  - source: "शुभाशुभपरित्यागी भक्तिमान्यः स मे प्रियः"
+    expected: "śaubhaāśaubhaparaitayaāgaī bhakataimaānayaḥ sa mae paraiyaḥ"
+  - source: "सत्य -सत्यमेवेश्वरो लोके सत्ये धर्मः सदाश्रितः"
+    expected: "sataya -satayamaevaeśavarao laokae satayae dharamaḥ sadaāśaraitaḥ"
+  - source: "सत्यमूलनि सर्वाणि सत्यान्नास्ति परं पदम्"
+    expected: "satayamaūlanai saravaāṇai satayaānanaāsatai paraṃ padama"
+  - source: "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ"
+    expected: "paitaā maātaāganairaātamaā ca gaurauśaca bharataraṣabha"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0902(?=[कखगघङ])
+      result: ṅ
+    - pattern: \u0902(?=[चछजझञ])
+      result: ñ
+    - pattern: \u0902(?=[टठडढण])
+      result: ṇ
+    - pattern: \u0902(?=[तथदधन])
+      result: n
+
+  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'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'क': 'ka'
+    'ख': 'kha'
+    'ग': 'ga'
+    'घ': 'gha'
+    'ङ': 'ṅa'
+
+    # Palatals
+    'च': 'ca'
+    'छ': 'cha'
+    'ज': 'ja'
+    'झ': 'jha'
+    'ञ': 'ña'
+
+    # Cerebrals
+    'ट': 'ṭa'
+    'ठ': 'ṭha'
+    'ड': 'ḍa'
+    'ढ': 'ḍha'
+    'ण': 'ṇa'
+
+    # Dentals
+    'त': 'ta'
+    'थ': 'tha'
+    'द': 'da'
+    'ध': 'dha'
+    'न': 'na'
+
+    # Labials
+    'प': 'pa'
+    'फ': 'pha'
+    'ब': 'ba'
+    'भ': 'bha'
+    'म': 'ma'
+
+    # Semivowels
+    'य': 'ya'
+    'र': 'ra'
+    'ल': 'la'
+    'ळ': 'ḻa'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'ṣa'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    # Anusvāra
+    'ं': 'ṃ'
+
+    # Bisarga
+    'ः': 'ḥ'
+
+    # Anunāsika
+    'ँ': 'm̐'
+
+    # Abagraha
+    'ऽ': '’' # (apostrophe)
+
+    #Jihvāmūlīya
+    '\u0CF1': 'ẖ'
+
+    #Upadhmānīya
+    '\u0CF2': 'ḫ'
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ृ': "ṛ"
+    'ॄ': "ṝ"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+    '्': ""
+    '‍': ''# Used for joining

data/maps/alalc-sin-Sinh-Latn-1997.yaml

@@ -0,0 +1,292 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:sin
+source_script: Sinh
+destination_script: Latn
+name: Sinhalese Romanization, 1997
+alias:
+  ogc11122:
+    code: sin_Sinh2Latn_ALA_1997
+    description: Sinhalese ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/sinhales.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Sinhalese
+
+
+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 sign ් called virāma.
+
+  - |
+    Exceptions: 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.
+
+  - |
+    Exceptions:
+    a) when saññaka represents a nasal, it is romanized according to the rule for anusvāra.
+    b) when saññaka is combined with an aspirated consonant, the combination is romanized as a non-aspirated, followed by an aspirated consonant.
+
+
+tests:
+  - source: "ශී‍්‍ර ලංකාවේ කී‍්‍රඩාව ඉතිහාසයේ ඉහළම තැනකට ගේන්න කටයුතු කරනවා"
+    expected: "śīra laṃkāvē kīraḍāva itihāsayē ihaḷama tănakaṭa gēnanna kaṭayutu karanavā"
+  - source: "කොච්චිකඬේ මෝයකට අසල නෑමට ගිය තරුණයෝ ෩ක් මරුට - මිතුරාගේ උපන් දිනය සැමරීමට ඇවිත්"
+    expected: "kocañcikaṇḍē mōyakaṭa asala nâmaṭa giya taruṇayō 3k maruṭa - miturāgē upan dinaya sămarīmaṭa ăvit"
+  - source: "ලෝක ළමා දිනයදා සිසුන් පිරිසක් කසිප්පු බීලා"
+    expected: "lōka ḷamā dinayadā sisun pirisak kasippu bīlā"
+  - source: "කෝටි 16ක හෙරොයින් සමග දන්කොටුවේදී 7ක් දැලේ"
+    expected: "kōṭi 16ka heroyin samaga danaṅkoṭuvēdī 7k dălē"
+  - source: "මිනුවන්ගොඩ පීසීආර් දෙදහසක් සිදුකරයි"
+    expected: "minuvanaṅgoḍa pīsīār dedahasak sidukarayi"
+  - source: "පාස්කු ප‍්‍රහාරය වගේම පාස්කු ප්‍රෝඩාව ගැනත් සොයන්න කොමිසමක් පත්කළ යුතුයි - විපක්‍ෂ නායක සජිත් පේ‍්‍රමදාස"
+    expected: "pāsaṅku parahāraya vagēma pāsaṅku prōḍāva gănat soyananna komisamak pataṅkaḷa yutuyi - vipakṣa nāyaka sajit pēramadāsa"
+  - source: "ට‍්‍රම්ප්ගේ සෞඛ්‍යය තීරණාත්මකයි - ට්විටර් හරහා ජනතාව අමතයි"
+    expected: "ṭarampaṅgē saukhyaya tīraṇātmakayi - ṭviṭar harahā janatāva amatayi"
+  - source: "පාස්කු දා ප‍්‍රහාරය පිළිබඳ පරීක්‍ෂණවලින් කිසිවකුට අසාධාරණයක් වීමට ඉඩ දෙන්නේ නෑ - අගමැති"
+    expected: "pāsaṅku dā parahāraya piḷibanda parīkṣaṇavalin kisivakuṭa asādhāraṇayak vīmaṭa iḍa denannē nâ - agamăti"
+  - source: "දිල්ලි කැපිටල්ස් සහ කෝලිගේ බැංගලෝර් තෙවැනි ජය ලබයි"
+    expected: "dilli kăpiṭals saha kōligē băṃgalōr tevăni jaya labayi"
+  - source: "ශ‍්‍රී ලාංකික සම්භවයක් සහිත ප‍්‍රංශයේ පවුලක 5 ක් ඝාතනය කරලා"
+    expected: "śarī lāṃkika sambhavayak sahita paraṃśayē pavulaka 5 k ghātanaya karalā"
+  - source: "පැතිකුදය ඉක්මනින් සුව කරන ප‍්‍රතිකාර"
+    expected: "pătikudaya ikmanin suva karana paratikāra"
+
+map:
+
+  rules:
+    # note[3]
+    - pattern: \u0DCA(?=[කඛගඝඞ])
+      result: ṅ
+    - pattern: \u0DCA(?=[චඡජඣඤ])
+      result: ñ
+    - pattern: \u0DCA(?=[ටඨඩඪණ])
+      result: ṇ
+    - pattern: \u0DCA(?=[තථදධන])
+      result: n
+
+    # note[2(a,b)]
+    - pattern: ([ක]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'k'
+    - pattern: ([ඛ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'kh'
+    - pattern: ([ග]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'g'
+    - pattern: ([ඝ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'gh'
+    - pattern: ([ඞ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṅ'
+    - pattern: ([ච]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'c'
+    - pattern: ([ඡ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ch'
+    - pattern: ([ජ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'j'
+    - pattern: ([ඣ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'jh'
+    - pattern: ([ඤ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ñ'
+    - pattern: ([ට]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṭ'
+    - pattern: ([ඨ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṭh'
+    - pattern: ([ඩ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ḍ'
+    - pattern: ([ඪ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ḍh'
+    - pattern: ([ණ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṇ'
+    - pattern: ([ත]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 't'
+    - pattern: ([ථ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'th'
+    - pattern: ([ද]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'd'
+    - pattern: ([ධ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'dh'
+    - pattern: ([න]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'n'
+    - pattern: ([ප]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'p'
+    - pattern: ([ඵ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ph'
+    - pattern: ([බ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'b'
+    - pattern: ([භ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'bh'
+    - pattern: ([ම]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'm'
+    - pattern: ([ය]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'y'
+    - pattern: ([ර]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'r'
+    - pattern: ([ල]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'l'
+    - pattern: ([ළ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ḷ'
+    - pattern: ([ව]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'v'
+    - pattern: ([ශ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ś'
+    - pattern: ([ෂ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṣ'
+    - pattern: ([ස]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 's'
+    - pattern: ([හ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'h'
+    - pattern: ([ඟ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṅg'
+    - pattern: ([ඦ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ñj'
+    - pattern: ([ඬ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṇḍ'
+    - pattern: ([ඳ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'nd'
+    - pattern: ([ඹ]=?)(?=[\u0dcf\u0dd0\u0dd1\u0dd2\u0dd3\u0dd4\u0dd6\u0dd8\u0df2\u0ddf\u0df3\u0dd9\u0dda\u0ddb\u0ddc\u0ddd\u0dde\u0dca])
+      result: 'ṃb'
+
+
+  characters:
+
+    #Vowels and Diphthongs (see Note 1)
+
+    'අ': 'a'
+    'ආ': 'ā'
+    'ඇ': 'ă'
+    'ඈ': 'â'
+    'ඉ': 'i'
+    'ඊ': 'ī'
+    'උ': 'u'
+    'ඌ': 'ū'
+    'ඍ': 'ṛ'
+    'ඎ': 'ṝ'
+    'ඏ': 'ḷ'
+    'ඐ': 'ḹ'
+    'එ': 'e'
+    'ඒ': 'ē'
+    'ඓ': 'ai'
+    'ඔ': 'o'
+    'ඕ': 'ō'
+    'ඖ': 'au'
+
+    'ා': 'ā'
+    'ැ': 'ă'
+    'ෑ': 'â'
+    'ි': 'i'
+    'ී': 'ī'
+    'ු': 'u'
+    'ූ': 'ū'
+    'ෘ': 'ṛ'
+    'ෲ': 'ṝ'
+    'ෟ': 'ḷ'
+    'ෳ': 'ḹ'
+    'ෙ': 'e'
+    'ේ': 'ē'
+    'ෛ': 'ai'
+    'ො': 'o'
+    'ෝ': 'ō'
+    'ෞ': 'au'
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ක': 'ka'
+    'ඛ': 'kha'
+    'ග': 'ga'
+    'ඝ': 'gha'
+    'ඞ': 'ṅa'
+
+
+    # Palatals
+    'ච': 'ca'
+    'ඡ': 'cha'
+    'ජ': 'ja'
+    'ඣ': 'jha'
+    'ඤ': 'ña'
+
+
+    # Cerebrals
+    'ට':  'ṭa'
+    'ඨ':  'ṭha'
+    'ඩ':  'ḍa'
+    'ඪ':  'ḍha'
+    'ණ':  'ṇa'
+
+
+    # Dentals
+    'ත': 'ta'
+    'ථ': 'tha'
+    'ද': 'da'
+    'ධ': 'dha'
+    'න': 'na'
+
+
+    # Labials
+    'ප': 'pa'
+    'ඵ': 'pha'
+    'බ': 'ba'
+    'භ': 'bha'
+    'ම': 'ma'
+
+
+    # Semivowels
+    'ය': 'ya'
+    'ර': 'ra'
+    'ල': 'la'
+    'ළ': 'ḷa'
+    'ව': 'va'
+
+    # Sibilants
+    'ශ': 'śa'
+    'ෂ': 'ṣa'
+    'ස': 'sa'
+
+    # Aspirate
+    'හ': 'ha'
+
+
+    # Visarga
+    'ඃ': 'ḥ'
+
+    # Anusvāra (see Note 3)
+    'ං': 'ṃ'
+
+
+    # numbers
+    '\u0DE6': '0'
+    '\u0DE7': '1'
+    '\u0DE8': '2'
+    '\u0DE9': '3'
+    '\u0DEA': '4'
+    '\u0DEB': '5'
+    '\u0DEC': '6'
+    '\u0DED': '7'
+    '\u0DEE': '8'
+    '\u0DEF': '9'
+
+
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+    '්': ''
+
+    # Rule no 4
+    'ඟ': 'ṅga'
+    'ඦ': 'ñja'
+    'ඬ': 'ṇḍa'
+    'ඳ': 'nda'
+    'ඹ': 'ṃba'