interscript 0.1.3 → 0.1.9

data/maps/iso-rus-Cyrl-Latn-9-1995.yaml

@@ -1,10 +1,10 @@
 ---
 authority_id: iso
 id: 9-1995
-language: rus
+language: iso-639-2:rus
 source_script: Cyrl
 destination_script: Latn
-name: ISO 9
+name: "ISO 9:1995 Information and documentation — Transliteration of Cyrillic characters into Latin characters — Slavic and non-Slavic languages"
 url: https://www.iso.org/standard/3589.html
 creation_date: 1995
 description: |
@@ -13,8 +13,8 @@ description: |
   languages. Table 3 includes in a single sequence, listed in the
   Cyrillic alphabetic order, the 118 single or diacritic-carrying
   characters that appear in one or another of the considered alphabets.
-tests:
 
+tests:
 
 map:
   characters:
@@ -269,4 +269,3 @@ map:
     "\u04c0": "\u2021"                         # Ӏ	=> ‡
     "\u02bc": "\u0060"                         # ʼ	=> `
     "\u02ee": "\u00a8"                         # ˮ => ¨
-

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

@@ -0,0 +1,220 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:san
+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”;
+  - 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: "पूर्णमदः पूर्णमिदं पूर्णात् पूर्ण्मुदच्यते"
+    expected: "paūraṇamadaḥ paūraṇamaidaṁ paūraṇaāta paūraṇamaudacayatae"
+  - source: "पूर्णस्य पूर्णमादाय पूर्णमेवावशिष्यते"
+    expected: "paūraṇasaya paūraṇamaādaāya paūraṇamaevaāvaśaiṣayatae"
+  - source: "यथा चतुर्भिः कनकं परीक्ष्यते निर्घषणच्छेदन तापताडनैः"
+    expected: "yathaā cataurabhaiḥ kanakaṁ 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 paraṁ padama"
+  - source: "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ"
+    expected: "paitaā maātaāganairaātamaā ca gaurauśaca bharataraṣabha"
+  - source: "पल्यालँ"
+    expected: "palayaām̐la"
+  - source: "दुसूलँ"
+    expected: "dausaūm̐la"
+
+map:
+
+  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'
+    'ॡ': 'ḹ'
+    'ए': 'e'
+    'ऐ': 'ai'
+    'ओ': 'o'
+    'औ': 'au'
+    'ऍ': 'ê'
+    'ऑ': 'ô'
+
+    # 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': 'ḷa'
+    'व': 'va'
+
+    # Sibilants
+    'श': 'śa'
+    'ष': 'ṣa'
+    'स': 'sa'
+
+    # Aspirate
+    'ह': 'ha'
+
+    'ᳵ': 'ẖ'
+    'ᳶ': 'ḫ'
+
+
+    # Anusvāra
+    'ं': 'ṁ'
+
+    # Bisarga
+    'ः': 'ḥ'
+
+    # candrabindu
+    'ँ': 'm̐'
+
+    # Abagraha
+    'ऽ': ':’' # (apostrophe)
+
+
+    # Medials # Needed for connecting constants
+    'ा': "ā"
+    'ि': "i"
+    'ी': "ī"
+    'ु': "u"
+    'ू': "ū"
+    'ॢ': "ḷ"
+    'ॣ': "ḹ"
+    'ृ': "ṛ"
+    'ॄ': "ṝ"
+    'े': "e"
+    'ै': "ai"
+    'ो': "o"
+    'ौ': "au"
+    'ॉ': 'ô'
+    'ॅ': "ê"
+
+    '्': ""
+    '‍': ''# Used for joining
+
+
+    # for semivowel rule no. 5
+
+    'यँ': 'm̐ya'
+    'रँ': 'm̐ra'
+    'लँ': 'm̐la'
+    'ळँ': 'm̐ḷa'
+    'वँ': 'm̐va'
+
+
+    # digits
+
+    '०': '0'
+    '१': '1'
+    '२': '2'
+    '३': '3'
+    '४': '4'
+    '५': '5'
+    '६': '6'
+    '७': '7'
+    '८': '8'
+    '९': '9'
+
+    # Perso-Arabic characters
+
+    'स़': 's̱a'
+    'ह़': 'ẓa'
+    'ख़': 'k͟ha'
+    'ज़': 'za'
+    'त़': 't̤a'
+    'ग़': 'ġa'
+    'फ़': 'fa'
+    'क़': 'qa'
+    'व़': 'wa'
+    'ड़': 'ṛa'
+    'ढ़': 'ṛha'

data/maps/iso-tam-Taml-Latn-15919-2001.yaml

@@ -0,0 +1,159 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:tam
+source_script: Taml
+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.
+     - Removal of ambiguity in the limited character set option. Tamil perii:i:iya, “really big”, separating the vowels.
+  - 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.
+  - Numerals in Tamil scripts shall be converted into decimal notation on transliteration, where
+    necessary.
+  - 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: "கார்த்திகேயன்"
+    expected: "kaāratataikaēyaṉa"
+  - source: "௲"
+    expected: "1000"
+  - source: "இளைஞர்களின் உறுதியான மனநிலையை பிரதிபலிக்கிறது: நீட் தேர்வில் ௮௫-௯௦ சதவீத மாணவர்கள் பங்கேற்பு - ரமேஷ் பொக்ரியால்"
+    expected: "iḷaaiñarakaḷaiṉa uṟautaiyaāṉa maṉanailaaiyaai pairataipalaikakaiṟatau: naīṭa taēravaila 85-9௦ catavaīta maāṇavarakaḷa paṅakaēṟapau - ramaēṣa paokaraiyaāla"
+  - source: "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்"
+    expected: "naāṭaāḷaumaṉaṟatataila 4 macaōtaākakaḷaai etairakaka kaāṅakairasa mauṭaivau - jaeyaraāma ramaēṣa"
+  - source: "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி"
+    expected: "karanaāṭakaāvaila maēlauma 9,894 paēraukakau kaoraōṉaā taoṟaṟau uṟautai"
+  - source: "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?"
+    expected: "aitaraāpaātataukakau kaaikaoṭaukakaumaā atairaṭai?"
+  - source: "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்"
+    expected: "amaeraikaka ōpaṉa ṭaeṉaṉaisa: iṟautaipapaōṭaṭaiyaila ṭaomaiṉaika-savaeraēva"
+  - source: "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்"
+    expected: "ai.pai.ela. kairaikakaeṭaṭaila kaḷama iṟaṅakauma amaeraikaka vaīrara"
+  - source: "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்"
+    expected: "amaeraikaka ōpaṉa ṭaeṉaṉaisa; navaōmai ocaākaā caāmapaiyaṉa paṭaṭama vaeṉaṟaāra"
+  - source: "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்"
+    expected: "pautaiya kalavaikakaoḷakaaikakau etairapapau: mauṉaṉaāḷa tauṇaaivaēnatarakaḷa 20 paēra pairatamaraukakau kaṭaitama"
+  - source: "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு"
+    expected: "inata āṇaṭau ai.pai.ela. kaōpapaaiyaai enata aṇai vaelalauma? - kaevaiṉa paīṭaṭaracaṉa kaṇaipapau"
+  - source: "இந்திய எண்ணெய் கப்பலில் தீ: விபத்து குறித்த எச்சரிக்கையை கப்பல் அதிகாரிகள் புறக்கணித்தனர் - இலங்கை கோர்ட்டு தகவல்"
+    expected: "inataiya eṇaṇaeya kapapalaila taī: vaipatatau kauṟaitata ecacaraikakaaiyaai kapapala ataikaāraikaḷa pauṟakakaṇaitataṉara - ilaṅakaai kaōraṭaṭau takavala"
+
+map:
+
+  characters:
+    'அ': 'a'
+    'ஆ': 'ā'
+    'ா': 'ā'
+
+    'இ': 'i'
+    'ி': 'i'
+
+    'ஈ': 'ī'
+    'ீ': 'ī'
+
+    'உ': 'u'
+    'ு': 'u'
+
+    'ஊ': 'ū'
+    'ூ': 'ū'
+
+    'ெ': "e"
+    'எ': 'e'
+
+    'ே': "ē"
+    'ஏ': 'ē'
+
+    'ஐ': 'ai'
+    'ை': "ai"
+
+    'ஒ': 'o'
+    'ொ': 'o'
+
+    'ோ': 'ō'
+    'ஓ': 'ō'
+
+    'ஔ': 'au'
+    'ௌ': 'au'
+
+
+    'க': 'ka'
+    'ங': 'ṅa'
+    'ஃ': 'ḵ'
+    'ச': 'ca'
+    'ஞ': 'ña'
+    'ட': 'ṭa'
+    'ண': 'ṇa'
+    'த': 'ta'
+    'ந': 'na'
+    'ப': 'pa'
+    'ம': 'ma'
+    'ய': 'ya'
+    'ர': 'ra'
+    'ல': 'la'
+    'ள': 'ḷa'
+    'ழ': 'ḻa'
+    'வ': 'va'
+    'ற': 'ṟa'
+    'ன': 'ṉa'
+    'ஜ': 'ja'
+    'ஶ': 'śa'
+    'ஷ': 'ṣa'
+    'ஸ': 'sa'
+    'ஹ': 'ha'
+
+    # Digits
+    '௧': '1'
+    '௨': '2'
+    '௩': '3'
+    '௪': '4'
+    '௫': '5'
+    '௬': '6'
+    '௭': '7'
+    '௮': '8'
+    '௯': '9'
+    '௰': '10'
+    '௱': '100'
+    '௲': '1000'
+
+
+
+    '்' : ''
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner

data/maps/iso-tel-Telu-Latn-15919-2001.yaml

@@ -0,0 +1,220 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:tel
+source_script: Telu
+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: "ఇప్పుడు ఇదే కోవలో టాలీవుడ్‌లో మరో మల్టీస్టారర్‌ రూపొందనుందని సినీ వర్గాల్లో వార్తలు వినిపిస్తున్నాయి"
+    expected: "ipapauḍau idaē kaōvalaō ṭaālaīvauḍalaō maraō malaṭaīsaṭaārara raūpaoṁdanauṁdanai sainaī varagaālalaō vaāratalau vainaipaisataunanaāyai"
+  - source: "అంటే ఉంటాయి, అయితే అవి చాలా పెద్దవై ఉండాల్సిన అవసరం లేదు అంటున్నారు మమ్ముట్టి"
+    expected: "aṁṭaē uṁṭaāyai, ayaitaē avai caālaā paedadavaai uṁḍaālasaina avasaraṁ laēdau aṁṭaunanaārau mamamauṭaṭai"
+  - source: "ఆ సంతోషాన్ని అభిమానులతో పంచుకున్నారు"
+    expected: "ā saṁtaōṣaānanai abhaimaānaulataō paṁcaukaunanaārau"
+  - source: "కెమెరాను అన్‌బాక్స్‌ చేసే వీడియోను సోషల్‌ మీడియాలో అభిమానులతో పంచుకున్నారు"
+    expected: "kaemaeraānau anabaākasa caēsaē vaīḍaiyaōnau saōṣala maīḍaiyaālaō abhaimaānaulataō paṁcaukaunanaārau"
+  - source: "ఇన్నాళ్లకు నిజమయింది. ఇక ఇప్పటి నుంచి దీంతో ఫొటోలు క్లిక్‌ మనిపిస్తా’’ అని ఆ వీడియోలో పేర్కొన్నారు"
+    expected: "inanaāḷalakau naijamayaiṁdai. ika ipapaṭai nauṁcai daīṁtaō phaoṭaōlau kalaika manaipaisataā’’ anai ā vaīḍaiyaōlaō paērakaonanaārau"
+  - source: "గవర్నర్‌తో కంగనా భేటీ"
+    expected: "gavaranarataō kaṁganaā bhaēṭaī"
+  - source: "శ్రియ సినిమా సెట్‌లో అడుగుపెట్టి ఆరు నెలలు కావొస్తోంది"
+    expected: "śaraiya sainaimaā saeṭalaō aḍaugaupaeṭaṭai ārau naelalau kaāvaosataōṁdai"
+  - source: "ఇప్పుడు తను కోరుకున్న కెమెరా చేతికి రావడంతో త్వరలో మమ్ముట్టి నుంచి స్టన్నింగ్‌ ఫొటోస్‌ రావడం ఖాయం అంటున్నారు ఆయన అభిమానులు"
+    expected: "ipapauḍau tanau kaōraukaunana kaemaeraā caētaikai raāvaḍaṁtaō tavaralaō mamamauṭaṭai nauṁcai saṭananaiṁga phaoṭaōsa raāvaḍaṁ khaāyaṁ aṁṭaunanaārau āyana abhaimaānaulau"
+  - source: "ఇప్పుడు ఆ వీడియో వైరల్‌ అయింది. ‘ఆ కెమెరాను కొనాలనేది చాలాకాలంగా నా కల."
+    expected: "ipapauḍau ā vaīḍaiyaō vaairala ayaiṁdai. ‘ā kaemaeraānau kaonaālanaēdai caālaākaālaṁgaā naā kala."
+  - source: "మరో వైపు ఎన్టీఆర్‌, రామ్‌చరణ్‌ కలిసి ట్రిపుల్‌ ఆర్‌ సినిమాలో నటిస్తున్నారు"
+    expected: "maraō vaaipau enaṭaīāra, raāmacaraṇa kalaisai ṭaraipaula āra sainaimaālaō naṭaisataunanaārau"
+  - source: "౪౬౨౬౯"
+    expected: "46269"
+
+map:
+
+
+  characters:
+    'అ': 'a'
+    'ఆ': 'ā'
+    'ఇ': 'i'
+    'ఈ': 'ī'
+    'ఉ': 'u'
+    'ఊ': 'ū'
+    'ఋ': 'ṛ'
+    'ౠ': 'ṝ'
+    'ఌ': 'ḻ'
+    'ౡ': 'ḹ'
+    'ఎ': 'e'
+    'ఏ': 'ē'
+    'ఐ': 'ai'
+    'ఒ': 'o'
+    'ఓ': 'ō'
+    'ఔ': 'au'
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals  క ఖ గ ఘ ఙ
+    'క': 'ka'
+    'ఖ': 'kha'
+    'గ': 'ga'
+    'ఘ': 'gha'
+    'ఙ': 'ṅa'
+
+    # Palatals చ ఛ జ ఝ ఞ
+    'చ': 'ca'
+    'ఛ': 'cha'
+    'జ': 'ja'
+    'ఝ': 'jha'
+    'ఞ': 'ña'
+
+    # Cerebrals ట ఠ డ ఢ ణ
+    'ట':  'ṭa'
+    'ఠ':  'ṭha'
+    'డ':  'ḍa'
+    'ఢ':  'ḍha'
+    'ణ':  'ṇa'
+
+    # Dentals త థ ద ధ న
+    'త': 'ta'
+    'థ': 'tha'
+    'ద': 'da'
+    'ధ': 'dha'
+    'న': 'na'
+
+    # Labials ప ఫ బ భ మ
+    'ప': 'pa'
+    'ఫ': 'pha'
+    'బ': 'ba'
+    'భ': 'bha'
+    'మ': 'ma'
+
+    # Semivowels య ర ల వ
+    'య': 'ya'
+    'ర': 'ra'
+    'ఱ': 'ṛa'
+    'ల': 'la'
+    'ళ': 'ḷa'
+    'వ': 'va'
+
+    # Sibilants శ ష స హ
+    'శ': 'śa'
+    'ష': 'ṣa'
+    'స': 'sa'
+
+
+
+    # Aspirate
+    'హ': 'ha'
+
+    'ౙ': 'za'
+    'ౘ': 'ĉa'
+    'ౚ': 'ṟa'
+    '\u0C34': 'ḻa'
+
+
+    # Chandrabindu
+    'ঁ': 'm̐'
+
+    # Bisarga
+    'ః': 'ḥ'
+
+    # Anusvāra
+    'ం': 'ṁ'
+
+    # Medials # Needed for connecting constants
+
+    'ా': 'ā'
+    'ి': 'i'
+    'ీ': 'ī'
+    'ు': 'u'
+    'ూ': 'ū'
+    'ృ': 'ṛ'
+    'ౄ': "ṝ"
+    ' ౢ': "ḷ" # \u0C62
+    ' ౣ': "ḹ" # \u0C63
+    'ె': 'e'
+    'ే': 'ē'
+    'ై': 'ai'
+    'ొ': 'o'
+    'ో': 'ō'
+    'ౌ': 'au'
+    'ఁ': 'ň'
+
+
+    # Abagraha
+    'ఽ': ':’' # (apostrophe)
+
+
+    '\u0c4d': '' #verma sign for halanta
+    'ౕ	': ''
+    'ౖ	': ''
+    '्': ''
+    '़': ''
+    '\u09CD': '' # Used for joining
+    "‍": ''# Used for joining
+    "‌": ''# Used for non joining
+
+
+    'యঁ': 'm̐ya'
+    'రঁ': 'm̐ra'
+    'ఱঁ': 'm̐ṛa'
+    'లঁ': 'm̐la'
+    'ళঁ': 'm̐ḷa'
+    'వঁ': 'm̐va'
+
+
+    # numbers
+
+    '౦': '0'
+    '౧': '1'
+    '౨': '2'
+    '౩': '3'
+    '౪': '4'
+    '౫': '5'
+    '౬': '6'
+    '౭': '7'
+    '౮': '8'
+    '౯': '9'