interscript 0.1.3 → 0.1.9

data/maps/iso-pan-Guru-Latn-15919-2001.yaml

@@ -0,0 +1,222 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pan
+source_script: Guru
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - Bindi shall be transliterated as ṃ and Tippi as ṁ .
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+     - Removal of ambiguity in the limited character set option. Tamil perii:i:iya, “really big”, separating the vowels.
+     - Gurmukhi Adhik before a vowel, as in bac: ā (not bacā without Adhik).
+     - Gurmukhi Bindi or Tippi written before the vowel ī (instead of after the vowel) in old orthography, transliterated
+    as ī:ṃ or ī:ṁ , respectively.
+     - Gurmukhi hala making a conjunct h in old orthography, as in tum:ha formed with hala (not tumha formed with the usual subscript h).
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+tests:
+  - source: "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ"
+    expected: "paṁjaāba 'ca vadha raihaā ḵẖaudakauśaīāṃ daā raujhaāna"
+  - source: "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ"
+    expected: "lakha taoṃ paāra paujaā saragarama kaesaāṃ daā aṁkaṛaā, dailaī 'ca dao lakha taoṃ paāra inaphaaikaṭaiḍa"
+  - source: "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ"
+    expected: "paraivaāraka samasaiāvaāṃ atae vaiāha vaī haai haora ahaima kaārana"
+  - source: "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ"
+    expected: "maradaāṃ 'ca aurataāṃ naālaoṃ vadha haai ḵẖaudakauśaī daā raujhaāna"
+  - source: "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ"
+    expected: "raāśaṭaraī padhara 'tae paṁjaāba 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 naaujavaānaāṃ baārae dasaiā"
+  - source: "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ"
+    expected: "saākharataā dae maāmalae 'ca daeśa 'ca 7vaeṃ naṁbara 'tae paṁjaāba"
+  - source: "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ"
+    expected: "dailaī kamaeṭaī dae maaiṃbara śaṁṭaī nae akaālaī dala taoṃ daitaā asataīfaā"
+  - source: "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ"
+    expected: "102 haora kaoraonaā paāzaīṭaiva maraīzaāṃ daī pauśaṭaī, ika daī maauta"
+  - source: "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ"
+    expected: "saṛaka haādasae daauraāna ika daī maauta"
+  - source: "ਅਸੀਂ ਲੁੱਕ ਛੁੱਪ ਕ਼ ਆਪਣੀ ਜਾਨ"
+    expected: "asaīṃ lauka chaupa qa āpaṇaī jaāna"
+
+map:
+
+  characters:
+
+    # Vowels
+
+    'ਅ': 'a'
+    'ਆ': 'ā'
+    'ਇ': 'i'
+    'ਈ': 'ī'
+    'ਉ': 'u'
+    'ਊ': 'ū'
+    'ਏ': 'e'
+    'ਐ': 'ai'
+    'ਓ': 'o'
+    'ਔ': 'au'
+
+    # Consonants
+    # Gutturals
+    'ਕ': 'ka'
+    'ਖ': 'kha'
+    'ਗ': 'ga'
+    'ਘ': 'gha'
+    'ਙ': 'ṅa'
+
+    # Palatals
+    'ਚ': 'ca'
+    'ਛ': 'cha'
+    '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'
+    'ਬ': 'ba'
+    'ਭ': 'bha'
+    'ਮ': 'ma'
+
+    # Semivowels
+    'ਯ': 'ya'
+    'ਰ': 'ra'
+    'ਲ': 'la'
+    'ਲ਼': 'ḷa'
+    'ਵ': 'va'
+    'ੜ': 'ṛa'
+
+    # Sibilants
+    'ਸ': 'sa'
+
+    # Aspirate
+    'ਹ': 'ha'
+
+    # Bindī
+    'ਂ': 'ṃ'
+
+    # Ṭippī
+    'ੰ': 'ṁ'
+
+    # Bisarga
+    'ਃ': 'ḥ'
+
+    # candrabindu
+    '\u0A01': 'm̐'
+
+
+    # Medials # Needed for connecting constants
+    'ਾ': "ā"
+    'ਿ': "i"
+    'ੀ': "ī"
+    'ੁ': "u"
+    'ੂ': "ū"
+    'ੇ': "e"
+    'ੈ': "ai"
+    'ੋ': "o"
+    'ੌ': "au"
+    'ੱ': ""
+
+    # For adhik before a vowel rule 9 exception
+
+    'ੱਅ': ':a'
+    'ੱਆ': ':ā'
+    'ੱਇ': ':i'
+    'ੱਈ': ':ī'
+    'ੱਉ': ':u'
+    'ੱਊ': ':ū'
+    'ੱਏ': ':e'
+    'ੱਐ': ':ai'
+    'ੱਓ': ':o'
+    'ੱਔ': ':au'
+
+    'ੱਾ': ":ā"
+    'ੱਿ': ":i"
+    'ੱੀ': ":ī"
+    'ੱੁ': ":u"
+    'ੱੂ': ":ū"
+    'ੱੇ': ":e"
+    'ੱੈ': ":ai"
+    'ੱੋ': ":o"
+    'ੱੌ': ":au"
+
+
+    # rule 9 exception for bindi and tippi
+
+    'ਂਈ' : 'ī:ṃ'
+    'ੰਈ' : 'ī:ṁ'
+
+
+    # digits
+
+    '੦': '0'
+    '੧': '1'
+    '੨': '2'
+    '੩': '3'
+    '੪': '4'
+    '੫': '5'
+    '੬': '6'
+    '੭': '7'
+    '੮': '8'
+    '੯': '9'
+
+
+    # Perso-Arabic Characters
+
+    'ਖ਼': 'ḵẖa'
+    'ਕ਼': 'qa'
+    'ਗ਼': 'ġa'
+    'ਫ਼': 'fa'
+    'ਸ਼': 'śa'
+    'ਜ਼': 'za'

data/maps/iso-pli-Beng-Latn-15919-2001.yaml

@@ -0,0 +1,73 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pli
+source_script: Beng
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+tests:
+  - source: "তেন সমযেন বুদ্ধো ভগৰা ৰেরঞ্জাযং ৰিহরতি নল়েরুপুচিমন্দমূলে মহতা ভিক্খুসঙ্ঘেন সদ্ধিং পঞ্চমত্তেহি ভিক্খুসতেহি"
+    expected: "taena samayaena baudadhao bhagavaā vaerañajaāyaṁ vaiharatai nala়eraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ pañacamatataehai bhaikakhausataehai"
+  - source: "অস্সোসি খো ৰেরঞ্জো ব্রাহ্মণো"
+    expected: "asasaosai khao vaerañajao baraāhamaṇao"
+  - source: "সমণো খলু, ভো, গোতমো সক্যপুত্তো সক্যকুলা পব্বজিতো ৰেরঞ্জাযং ৰিহরতি"
+    expected: "samaṇao khalau, bhao, gaotamao sakayapautatao sakayakaulaā pababajaitao vaerañajaāyaṁ vaiharatai"
+  - source: "নল়েরুপুচিমন্দমূলে মহতা ভিক্খুসঙ্ঘেন সদ্ধিং পঞ্চমত্তেহি ভিক্খুসতেহি"
+    expected: "nala়eraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ pañacamatataehai bhaikakhausataehai"
+  - source: "তং খো পন ভৰন্তং গোতমং এৰং কল্যাণো কিত্তিসদ্দো অব্ভুগ্গতো"
+    expected: "taṁ khao pana bhavanataṁ gaotamaṁ evaṁ kalayaāṇao kaitataisadadao ababhaugagatao"
+  - source: "সো ইমং লোকং সদেৰকং সমারকং সব্রহ্মকং সস্সমণব্রাহ্মণিং পজং সদেৰমনুস্সং সযং অভিঞ্ঞা সচ্ছিকত্ৰা পৰেদেতি"
+    expected: "sao imaṁ laokaṁ sadaevakaṁ samaārakaṁ sabarahamakaṁ sasasamaṇabaraāhamaṇaiṁ pajaṁ sadaevamanausasaṁ sayaṁ abhaiñañaā sacachaikatavaā pavaedaetai"
+  - source: "অরসরূপো সমণো গোতমো’তি, নো চ খো যং ত্ৰং সন্ধায ৰদেসী’’তি"
+    expected: "arasaraūpao samaṇao gaotamao’tai, nao ca khao yaṁ tavaṁ sanadhaāya vadaesaī’’tai"
+  - source: "অরসরূপো ভৰং গোতমো’’তি?"
+    expected: "arasaraūpao bhavaṁ gaotamao’’tai?"
+  - source: "অত্থি খ্ৰেস, ব্রাহ্মণ, পরিযাযো যেন মং পরিযাযেন সম্মা ৰদমানো ৰদেয্য"
+    expected: "atathai khavaesa, baraāhamaṇa, paraiyaāyao yaena maṁ paraiyaāyaena samamaā vadamaānao vadaeyaya"
+  - source: "অরসরূপো সমণো গোতমো’তি"
+    expected: "arasaraūpao samaṇao gaotamao’tai"
+
+map:
+  inherit: 'iso-asm-Beng-Latn-15919-2001'
+

data/maps/iso-pli-Deva-Latn-15919-2001.yaml

@@ -0,0 +1,74 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pli
+source_script: Deva
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+     -  Vowel hiatus, not digraph transliteration of diphthongs; as in Sanskrit pra:uga (not prauga), “yoke”;
+     -  Absence of aspiration, as in the Nepali plural form vid:harū (not vidharū )
+
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+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 bhagavanataṁ abhaivaādaetavaā ekamanataṁ naisaīdai"
+  - source: "अथ खो सुदिन्‍नस्स कलन्दपुत्तस्स मातापितरो सुदिन्‍नं कलन्दपुत्तं एतदवोचुं"
+    expected: "atha khao saudainanasasa kalanadapautatasasa maātaāpaitarao saudainanaṁ kalanadapautataṁ etadavaocauṁ"
+  - source: "त्वं खोसि, तात सुदिन्‍न, अम्हाकं एकपुत्तको पियो मनापो सुखेधितो सुखपरिहतो"
+    expected: "tavaṁ khaosai, taāta saudainana, amahaākaṁ ekapautatakao paiyao manaāpao saukhaedhaitao saukhaparaihatao"
+  - source: "न त्वं, तात सुदिन्‍न, किञ्‍चि दुक्खस्स जानासि"
+    expected: "na tavaṁ, taāta saudainana, kaiñacai daukakhasasa jaānaāsai"
+  - source: "अनुञ्‍ञातोम्हि किर मातापितूहि अगारस्मा अनगारियं पब्बज्‍जाया’’ति, हट्ठो उदग्गो पाणिना गत्तानि परिपुञ्छन्तो वुट्ठासि"
+    expected: "anauñañaātaomahai kaira maātaāpaitaūhai agaārasamaā anagaāraiyaṁ pababajajaāyaā’’tai, haṭaṭhao udagagao paāṇainaā gatataānai paraipauñachanatao vauṭaṭhaāsai"
+
+map:
+
+  inherit: iso-san-Deva-Latn-15919-2001

data/maps/iso-pli-Sinh-Latn-15919-2001.yaml

@@ -0,0 +1,219 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:pli
+source_script: Sinh
+destination_script: Latn
+name: "Information and documentation — Transliteration of Devanagari and related Indic scripts into Latin characters"
+url: https://www.chatranjali.fr/Scripts/Standards/ISO15919.pdf
+creation_date: 2001
+adoption_date: 2001
+description: |
+  Script conversion is often required for documents such as historical and literary texts, geographical texts (including
+  maps and atlases), bibliographies, catalogues, lists and passports (and other identification documents).
+
+  Text in Devanagari script or other Indic scripts sometimes needs to be shown in Latin script, where users, or
+  equipment that they are using, cannot read or write the text
+
+  This International Standard applies to transliteration of Devanagari, and to Indic scripts related to Devanagari,
+  independent of the period in which it is or was used.
+
+notes:
+
+  - All transliterations made using this International Standard shall be case-insensitive.
+  - Inherent a with a consonant shall always be transliterated.
+  - anusvara (including Vedic anusvara) shall be transliterated as ṁ
+  - candrabindu shall be transliterated as m̐
+  - When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated
+    with a semivowel, it shall be placed before the semivowel.
+  - Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.
+    Indic punctuation is outside the scope of this International Standard.
+  - The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the
+    independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent
+    shall be attached to the second vowel.
+  - |
+    A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as
+    follows.
+     -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.
+  - If a character in an Indic script is defined in such a way as to be equivalent to another character in any
+    script, where the second character has a transliteration in this International Standard, then the first character shall
+    be transliterated in the same way as the second character.
+  - When the half-nasal in Telugu script is used for modern nasalization in writing Hindi or
+    any other language, it shall be transliterated as a tilde above the transliterated vowel. In the case of the digraphs ai,
+    au, the tilde shall be attached to the second vowel
+  - Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of
+    the digraphs ai, au, both Latin vowels should be underscored.
+    Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a
+    consonant, the transliteration should show word division by a space; but when phonological processes result in two
+    words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge
+    of the language in question.
+
+
+tests:
+  - source: "තෙන සමයෙන බුද්‌ධො භගවා වෙරඤ්‌ජායං විහරති නළෙරුපුචිමන්‌දමූලෙ මහතා භික්‌ඛුසඞ්‌ඝෙන සද්‌ධිං"
+    expected: "taena samayaena baudadhao bhagavaā vaerañajaāyaṁ vaiharatai naḷaeraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ"
+  - source: "පඤ්‌චමත්‌තෙහි භික්‌ඛුසතෙහි. අස්‌සොසි ඛො වෙරඤ්‌ජො බ්‍රාහ්‌මණො"
+    expected: "pañacamatataehai bhaikakhausataehai. asasaosai khao vaerañajao baraāhamaṇao"
+  - source: "අථ ඛො වෙරඤ්‌ජො බ්‍රාහ්‌මණො යෙන භගවා තෙනුපසඞ්‌කමි;"
+    expected: "atha khao vaerañajao baraāhamaṇao yaena bhagavaā taenaupasaṅakamai;"
+  - source: "උපසඞ්‌කමිත්‌වා භගවතා සද්‌ධිං සම්‌මොදි."
+    expected: "upasaṅakamaitavaā bhagavataā sadadhaiṁ samamaodai."
+  - source: "නිබ්‌භොගො භවං ගොතමො"
+    expected: "naibabhaogao bhavaṁ gaotamao"
+  - source: "අකිරියවාදො භවං ගොතමො"
+    expected: "akairaiyavaādao bhavaṁ gaotamao"
+  - source: "උච්‌ඡෙදවාදො භවං ගොතමො"
+    expected: "ucachaedavaādao bhavaṁ gaotamao"
+  - source: "ජෙගුච්‌ඡී භවං ගොතමො"
+    expected: "jaegaucachaī bhavaṁ gaotamao"
+  - source: "අහොසි අසල්‌ලීනං, උපට්‌ඨිතා සති අසම්‌මුට්‌ඨා‍"
+    expected: "ahaosai asalalaīnaṁ, upaṭaṭhaitaā satai asamamauṭaṭhaā"
+  - source: "අත්‌ථි ඛ්‌වෙස, බ්‍රාහ්‌මණ, පරියායො යෙන මං පරියායෙන සම්‌මා වදමානො වදෙය්‍"
+    expected: "atathai khavaesa, baraāhamaṇa, paraiyaāyao yaena maṁ paraiyaāyaena samamaā vadamaānao vadaeya"
+
+
+
+map:
+
+
+  characters:
+
+    'අ': 'a'
+    'ආ': 'ā'
+    'ඇ': 'æ'
+    'ඈ': 'ǣ'
+    'ඉ': 'i'
+    'ඊ': 'ī'
+    'උ': 'u'
+    'ඌ': 'ū'
+    'ඍ': 'ṛ'
+    'ඎ': 'ṝ'
+    'ඏ': 'ḻ'
+    'ඐ': 'ḹ'
+    'එ': 'e'
+    'ඒ': 'ē'
+    'ඓ': 'ai'
+    'ඔ': 'o'
+    'ඕ': 'ō'
+    'ඖ': 'au'
+
+    'ා': 'ā'
+    'ැ': 'æ'
+    'ෑ': 'ǣ'
+    'ි': 'i'
+    'ී': 'ī'
+    'ු': 'u'
+    'ූ': 'ū'
+    'ෘ': 'ṛ'
+    'ෲ': 'ṝ'
+    'ෟ': 'ḻ'
+    'ෳ': 'ḹ'
+    'ෙ': 'e'
+    'ේ': 'ē'
+    'ෛ': 'ai'
+    'ො': 'o'
+    'ෝ': 'ō'
+    'ෞ': 'au'
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals  క ఖ గ ఘ ఙ
+    'ක': 'ka'
+    'ඛ': 'kha'
+    'ග': 'ga'
+    'ඝ': 'gha'
+    'ඞ': 'ṅa'
+    'ඟ': 'ṅga'
+
+    # Palatals చ ఛ జ ఝ ఞ
+    'ච': 'ca'
+    'ඡ': 'cha'
+    'ජ': 'ja'
+    'ඣ': 'jha'
+    'ඤ': 'ña'
+    'ඦ': 'ñja'
+
+
+    # Cerebrals ట ఠ డ ఢ ణ
+    'ට':  'ṭa'
+    'ඨ':  'ṭha'
+    'ඩ':  'ḍa'
+    'ඪ':  'ḍha'
+    'ණ':  'ṇa'
+    'ඬ':  'ṇḍa'
+
+    # Dentals త థ ద ధ న
+    'ත': 'ta'
+    'ථ': 'tha'
+    'ද': 'da'
+    'ධ': 'dha'
+    'න': 'na'
+    'ඳ': 'nda'
+
+    # Labials ప ఫ బ భ మ
+    'ප': 'pa'
+    'ඵ': 'pha'
+    'බ': 'ba'
+    'භ': 'bha'
+    'ම': 'ma'
+    'ඹ': 'mba'
+
+    # Semivowels య ర ల వ
+    'ය': 'ya'
+    'ර': 'ra'
+    'ල': 'la'
+    'ළ': 'ḷa'
+    'ව': 'va'
+
+    # Sibilants శ ష స హ
+    'ශ': 'śa'
+    'ෂ': 'ṣa'
+    'ස': 'sa'
+
+
+
+    # Aspirate
+    'හ': 'ha'
+
+    'ෆ': 'fa'
+
+    # Chandrabindu
+    'ઁ': 'm̐'
+
+    # Bisarga
+    'ඃ': 'ḥ'
+
+    # Anusvāra
+    'ං': 'ṁ'
+
+
+    # numbers
+
+    '\u0DE6': '0'
+    '\u0DE7': '1'
+    '\u0DE8': '2'
+    '\u0DE9': '3'
+    '\u0DEA': '4'
+    '\u0DEB': '5'
+    '\u0DEC': '6'
+    '\u0DED': '7'
+    '\u0DEE': '8'
+    '\u0DEF': '9'
+
+
+    # semivowel chandrabindu rule
+
+    # Semivowels య ర ల వ
+    'යઁ': 'm̐ya'
+    'රઁ': 'm̐ra'
+    'ලઁ': 'm̐la'
+    'ළઁ': 'm̐ḷa'
+    'වઁ': 'm̐va'
+
+
+
+    '\u09CD': '' # Used for joining
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+    "්": '' # virama
+