interscript-maps 2.0.5

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

@@ -0,0 +1,215 @@
+metadata {
+  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 {
+  test "पूर्णमदः पूर्णमिदं पूर्णात् पूर्ण्मुदच्यते", "paūraṇamadaḥ paūraṇamaidaṁ paūraṇaāta paūraṇamaudacayatae"
+  test "पूर्णस्य पूर्णमादाय पूर्णमेवावशिष्यते", "paūraṇasaya paūraṇamaādaāya paūraṇamaevaāvaśaiṣayatae"
+  test "यथा चतुर्भिः कनकं परीक्ष्यते निर्घषणच्छेदन तापताडनैः", "yathaā cataurabhaiḥ kanakaṁ paraīkaṣayatae nairaghaṣaṇacachaedana taāpataāḍanaaiḥ"
+  test "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा", "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+  test "यो न हृष्यति न द्वेष्टि न शोचति न काङ्‍क्षति", "yao na haṛṣayatai na davaeṣaṭai na śaocatai na kaāṅakaṣatai"
+  test "शुभाशुभपरित्यागी भक्तिमान्यः स मे प्रियः", "śaubhaāśaubhaparaitayaāgaī bhakataimaānayaḥ sa mae paraiyaḥ"
+  test "सत्य -सत्यमेवेश्वरो लोके सत्ये धर्मः सदाश्रितः", "sataya -satayamaevaeśavarao laokae satayae dharamaḥ sadaāśaraitaḥ"
+  test "सत्यमूलनि सर्वाणि सत्यान्नास्ति परं पदम्", "satayamaūlanai saravaāṇai satayaānanaāsatai paraṁ padama"
+  test "पिता माताग्निरात्मा च गुरुश्च भरतर्षभ", "paitaā maātaāganairaātamaā ca gaurauśaca bharataraṣabha"
+  test "पल्यालँ", "palayaām̐la"
+  test "दुसूलँ", "dausaūm̐la"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+
+    # I. Vowels and Diphthongs (see Note 1)
+
+    sub "अ", "a"
+    sub "आ", "ā"
+    sub "इ", "i"
+    sub "ई", "ī"
+    sub "उ", "u"
+    sub "ऊ", "ū"
+    sub "ऋ", "ṛ"
+    sub "ॠ", "ṝ"
+    sub "ऌ", "ḷ"
+    sub "ॡ", "ḹ"
+    sub "ए", "e"
+    sub "ऐ", "ai"
+    sub "ओ", "o"
+    sub "औ", "au"
+    sub "ऍ", "ê"
+    sub "ऑ", "ô"
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    sub "क", "ka"
+    sub "ख", "kha"
+    sub "ग", "ga"
+    sub "घ", "gha"
+    sub "ङ", "ṅa"
+
+    # Palatals
+    sub "च", "ca"
+    sub "छ", "cha"
+    sub "ज", "ja"
+    sub "झ", "jha"
+    sub "ञ", "ña"
+
+    # Cerebrals
+    sub "ट", "ṭa"
+    sub "ठ", "ṭha"
+    sub "ड", "ḍa"
+    sub "ढ", "ḍha"
+    sub "ण", "ṇa"
+
+    # Dentals
+    sub "त", "ta"
+    sub "थ", "tha"
+    sub "द", "da"
+    sub "ध", "dha"
+    sub "न", "na"
+
+    # Labials
+    sub "प", "pa"
+    sub "फ", "pha"
+    sub "ब", "ba"
+    sub "भ", "bha"
+    sub "म", "ma"
+
+    # Semivowels
+    sub "य", "ya"
+    sub "र", "ra"
+    sub "ल", "la"
+    sub "ळ", "ḷa"
+    sub "व", "va"
+
+    # Sibilants
+    sub "श", "śa"
+    sub "ष", "ṣa"
+    sub "स", "sa"
+
+    # Aspirate
+    sub "ह", "ha"
+
+    sub "ᳵ", "ẖ"
+    sub "ᳶ", "ḫ"
+
+
+    # Anusvāra
+    sub "ं", "ṁ"
+
+    # Bisarga
+    sub "ः", "ḥ"
+
+    # candrabindu
+    sub "ँ", "m̐"
+
+    # Abagraha
+    sub "ऽ", ":’" # (apostrophe)
+
+
+    # Medials # Needed for connecting constants
+    sub "ा", "ā"
+    sub "ि", "i"
+    sub "ी", "ī"
+    sub "ु", "u"
+    sub "ू", "ū"
+    sub "ॢ", "ḷ"
+    sub "ॣ", "ḹ"
+    sub "ृ", "ṛ"
+    sub "ॄ", "ṝ"
+    sub "े", "e"
+    sub "ै", "ai"
+    sub "ो", "o"
+    sub "ौ", "au"
+    sub "ॉ", "ô"
+    sub "ॅ", "ê"
+
+    sub "्", ""
+    sub "‍", "" # Used for joining
+
+
+    # for semivowel rule no. 5
+
+    sub "यँ", "m̐ya"
+    sub "रँ", "m̐ra"
+    sub "लँ", "m̐la"
+    sub "ळँ", "m̐ḷa"
+    sub "वँ", "m̐va"
+
+
+    # digits
+
+    sub "०", "0"
+    sub "१", "1"
+    sub "२", "2"
+    sub "३", "3"
+    sub "४", "4"
+    sub "५", "5"
+    sub "६", "6"
+    sub "७", "7"
+    sub "८", "8"
+    sub "९", "9"
+
+    # Perso-Arabic characters
+
+    sub "स़", "s̱a"
+    sub "ह़", "ẓa"
+    sub "ख़", "k͟ha"
+    sub "ज़", "za"
+    sub "त़", "t̤a"
+    sub "ग़", "ġa"
+    sub "फ़", "fa"
+    sub "क़", "qa"
+    sub "व़", "wa"
+    sub "ड़", "ṛa"
+    sub "ढ़", "ṛha"
+  }
+
+  compose
+}

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

@@ -0,0 +1,153 @@
+metadata {
+  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 {
+  test "கார்த்திகேயன்", "kaāratataikaēyaṉa"
+  test "௲", "1000"
+  test "இளைஞர்களின் உறுதியான மனநிலையை பிரதிபலிக்கிறது: நீட் தேர்வில் ௮௫-௯௦ சதவீத மாணவர்கள் பங்கேற்பு - ரமேஷ் பொக்ரியால்", "iḷaaiñarakaḷaiṉa uṟautaiyaāṉa maṉanailaaiyaai pairataipalaikakaiṟatau: naīṭa taēravaila 85-9௦ catavaīta maāṇavarakaḷa paṅakaēṟapau - ramaēṣa paokaraiyaāla"
+  test "நாடாளுமன்றத்தில் 4 மசோதாக்களை எதிர்க்க காங்கிரஸ் முடிவு - ஜெயராம் ரமேஷ்", "naāṭaāḷaumaṉaṟatataila 4 macaōtaākakaḷaai etairakaka kaāṅakairasa mauṭaivau - jaeyaraāma ramaēṣa"
+  test "கர்நாடகாவில் மேலும் 9,894 பேருக்கு கொரோனா தொற்று உறுதி", "karanaāṭakaāvaila maēlauma 9,894 paēraukakau kaoraōṉaā taoṟaṟau uṟautai"
+  test "ஐதராபாத்துக்கு கைகொடுக்குமா அதிரடி?", "aitaraāpaātataukakau kaaikaoṭaukakaumaā atairaṭai?"
+  test "அமெரிக்க ஓபன் டென்னிஸ்: இறுதிப்போட்டியில் டொமினிக்-ஸ்வெரேவ்", "amaeraikaka ōpaṉa ṭaeṉaṉaisa: iṟautaipapaōṭaṭaiyaila ṭaomaiṉaika-savaeraēva"
+  test "ஐ.பி.எல். கிரிக்கெட்டில் களம் இறங்கும் அமெரிக்க வீரர்", "ai.pai.ela. kairaikakaeṭaṭaila kaḷama iṟaṅakauma amaeraikaka vaīrara"
+  test "அமெரிக்க ஓபன் டென்னிஸ்; நவோமி ஒசாகா சாம்பியன் பட்டம் வென்றார்", "amaeraikaka ōpaṉa ṭaeṉaṉaisa; navaōmai ocaākaā caāmapaiyaṉa paṭaṭama vaeṉaṟaāra"
+  test "புதிய கல்விக்கொள்கைக்கு எதிர்ப்பு: முன்னாள் துணைவேந்தர்கள் 20 பேர் பிரதமருக்கு கடிதம்", "pautaiya kalavaikakaoḷakaaikakau etairapapau: mauṉaṉaāḷa tauṇaaivaēnatarakaḷa 20 paēra pairatamaraukakau kaṭaitama"
+  test "இந்த ஆண்டு ஐ.பி.எல். கோப்பையை எந்த அணி வெல்லும்? - கெவின் பீட்டர்சன் கணிப்பு", "inata āṇaṭau ai.pai.ela. kaōpapaaiyaai enata aṇai vaelalauma? - kaevaiṉa paīṭaṭaracaṉa kaṇaipapau"
+  test "இந்திய எண்ணெய் கப்பலில் தீ: விபத்து குறித்த எச்சரிக்கையை கப்பல் அதிகாரிகள் புறக்கணித்தனர் - இலங்கை கோர்ட்டு தகவல்", "inataiya eṇaṇaeya kapapalaila taī: vaipatatau kauṟaitata ecacaraikakaaiyaai kapapala ataikaāraikaḷa pauṟakakaṇaitataṉara - ilaṅakaai kaōraṭaṭau takavala"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "அ", "a"
+    sub "ஆ", "ā"
+    sub "ா", "ā"
+
+    sub "இ", "i"
+    sub "ி", "i"
+
+    sub "ஈ", "ī"
+    sub "ீ", "ī"
+
+    sub "உ", "u"
+    sub "ு", "u"
+
+    sub "ஊ", "ū"
+    sub "ூ", "ū"
+
+    sub "ெ", "e"
+    sub "எ", "e"
+
+    sub "ே", "ē"
+    sub "ஏ", "ē"
+
+    sub "ஐ", "ai"
+    sub "ை", "ai"
+
+    sub "ஒ", "o"
+    sub "ொ", "o"
+
+    sub "ோ", "ō"
+    sub "ஓ", "ō"
+
+    sub "ஔ", "au"
+    sub "ௌ", "au"
+
+
+    sub "க", "ka"
+    sub "ங", "ṅa"
+    sub "ஃ", "ḵ"
+    sub "ச", "ca"
+    sub "ஞ", "ña"
+    sub "ட", "ṭa"
+    sub "ண", "ṇa"
+    sub "த", "ta"
+    sub "ந", "na"
+    sub "ப", "pa"
+    sub "ம", "ma"
+    sub "ய", "ya"
+    sub "ர", "ra"
+    sub "ல", "la"
+    sub "ள", "ḷa"
+    sub "ழ", "ḻa"
+    sub "வ", "va"
+    sub "ற", "ṟa"
+    sub "ன", "ṉa"
+    sub "ஜ", "ja"
+    sub "ஶ", "śa"
+    sub "ஷ", "ṣa"
+    sub "ஸ", "sa"
+    sub "ஹ", "ha"
+
+    # Digits
+    sub "௧", "1"
+    sub "௨", "2"
+    sub "௩", "3"
+    sub "௪", "4"
+    sub "௫", "5"
+    sub "௬", "6"
+    sub "௭", "7"
+    sub "௮", "8"
+    sub "௯", "9"
+    sub "௰", "10"
+    sub "௱", "100"
+    sub "௲", "1000"
+
+
+
+    sub "்", ""
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+  }
+
+  compose
+}

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

@@ -0,0 +1,214 @@
+metadata {
+  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 {
+  test "ఇప్పుడు ఇదే కోవలో టాలీవుడ్‌లో మరో మల్టీస్టారర్‌ రూపొందనుందని సినీ వర్గాల్లో వార్తలు వినిపిస్తున్నాయి", "ipapauḍau idaē kaōvalaō ṭaālaīvauḍalaō maraō malaṭaīsaṭaārara raūpaoṁdanauṁdanai sainaī varagaālalaō vaāratalau vainaipaisataunanaāyai"
+  test "అంటే ఉంటాయి, అయితే అవి చాలా పెద్దవై ఉండాల్సిన అవసరం లేదు అంటున్నారు మమ్ముట్టి", "aṁṭaē uṁṭaāyai, ayaitaē avai caālaā paedadavaai uṁḍaālasaina avasaraṁ laēdau aṁṭaunanaārau mamamauṭaṭai"
+  test "ఆ సంతోషాన్ని అభిమానులతో పంచుకున్నారు", "ā saṁtaōṣaānanai abhaimaānaulataō paṁcaukaunanaārau"
+  test "కెమెరాను అన్‌బాక్స్‌ చేసే వీడియోను సోషల్‌ మీడియాలో అభిమానులతో పంచుకున్నారు", "kaemaeraānau anabaākasa caēsaē vaīḍaiyaōnau saōṣala maīḍaiyaālaō abhaimaānaulataō paṁcaukaunanaārau"
+  test "ఇన్నాళ్లకు నిజమయింది. ఇక ఇప్పటి నుంచి దీంతో ఫొటోలు క్లిక్‌ మనిపిస్తా’’ అని ఆ వీడియోలో పేర్కొన్నారు", "inanaāḷalakau naijamayaiṁdai. ika ipapaṭai nauṁcai daīṁtaō phaoṭaōlau kalaika manaipaisataā’’ anai ā vaīḍaiyaōlaō paērakaonanaārau"
+  test "గవర్నర్‌తో కంగనా భేటీ", "gavaranarataō kaṁganaā bhaēṭaī"
+  test "శ్రియ సినిమా సెట్‌లో అడుగుపెట్టి ఆరు నెలలు కావొస్తోంది", "śaraiya sainaimaā saeṭalaō aḍaugaupaeṭaṭai ārau naelalau kaāvaosataōṁdai"
+  test "ఇప్పుడు తను కోరుకున్న కెమెరా చేతికి రావడంతో త్వరలో మమ్ముట్టి నుంచి స్టన్నింగ్‌ ఫొటోస్‌ రావడం ఖాయం అంటున్నారు ఆయన అభిమానులు", "ipapauḍau tanau kaōraukaunana kaemaeraā caētaikai raāvaḍaṁtaō tavaralaō mamamauṭaṭai nauṁcai saṭananaiṁga phaoṭaōsa raāvaḍaṁ khaāyaṁ aṁṭaunanaārau āyana abhaimaānaulau"
+  test "ఇప్పుడు ఆ వీడియో వైరల్‌ అయింది. ‘ఆ కెమెరాను కొనాలనేది చాలాకాలంగా నా కల.", "ipapauḍau ā vaīḍaiyaō vaairala ayaiṁdai. ‘ā kaemaeraānau kaonaālanaēdai caālaākaālaṁgaā naā kala."
+  test "మరో వైపు ఎన్టీఆర్‌, రామ్‌చరణ్‌ కలిసి ట్రిపుల్‌ ఆర్‌ సినిమాలో నటిస్తున్నారు", "maraō vaaipau enaṭaīāra, raāmacaraṇa kalaisai ṭaraipaula āra sainaimaālaō naṭaisataunanaārau"
+  test "౪౬౨౬౯", "46269"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "అ", "a"
+    sub "ఆ", "ā"
+    sub "ఇ", "i"
+    sub "ఈ", "ī"
+    sub "ఉ", "u"
+    sub "ఊ", "ū"
+    sub "ఋ", "ṛ"
+    sub "ౠ", "ṝ"
+    sub "ఌ", "ḻ"
+    sub "ౡ", "ḹ"
+    sub "ఎ", "e"
+    sub "ఏ", "ē"
+    sub "ఐ", "ai"
+    sub "ఒ", "o"
+    sub "ఓ", "ō"
+    sub "ఔ", "au"
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals  క ఖ గ ఘ ఙ
+    sub "క", "ka"
+    sub "ఖ", "kha"
+    sub "గ", "ga"
+    sub "ఘ", "gha"
+    sub "ఙ", "ṅa"
+
+    # Palatals చ ఛ జ ఝ ఞ
+    sub "చ", "ca"
+    sub "ఛ", "cha"
+    sub "జ", "ja"
+    sub "ఝ", "jha"
+    sub "ఞ", "ña"
+
+    # Cerebrals ట ఠ డ ఢ ణ
+    sub "ట", "ṭa"
+    sub "ఠ", "ṭha"
+    sub "డ", "ḍa"
+    sub "ఢ", "ḍha"
+    sub "ణ", "ṇa"
+
+    # Dentals త థ ద ధ న
+    sub "త", "ta"
+    sub "థ", "tha"
+    sub "ద", "da"
+    sub "ధ", "dha"
+    sub "న", "na"
+
+    # Labials ప ఫ బ భ మ
+    sub "ప", "pa"
+    sub "ఫ", "pha"
+    sub "బ", "ba"
+    sub "భ", "bha"
+    sub "మ", "ma"
+
+    # Semivowels య ర ల వ
+    sub "య", "ya"
+    sub "ర", "ra"
+    sub "ఱ", "ṛa"
+    sub "ల", "la"
+    sub "ళ", "ḷa"
+    sub "వ", "va"
+
+    # Sibilants శ ష స హ
+    sub "శ", "śa"
+    sub "ష", "ṣa"
+    sub "స", "sa"
+
+
+
+    # Aspirate
+    sub "హ", "ha"
+
+    sub "ౙ", "za"
+    sub "ౘ", "ĉa"
+    sub "ౚ", "ṟa"
+    sub "\u0C34", "ḻa"
+
+
+    # Chandrabindu
+    sub "ঁ", "m̐"
+
+    # Bisarga
+    sub "ః", "ḥ"
+
+    # Anusvāra
+    sub "ం", "ṁ"
+
+    # Medials # Needed for connecting constants
+
+    sub "ా", "ā"
+    sub "ి", "i"
+    sub "ీ", "ī"
+    sub "ు", "u"
+    sub "ూ", "ū"
+    sub "ృ", "ṛ"
+    sub "ౄ", "ṝ"
+    sub " ౢ", "ḷ" # \u0C62
+    sub " ౣ", "ḹ" # \u0C63
+    sub "ె", "e"
+    sub "ే", "ē"
+    sub "ై", "ai"
+    sub "ొ", "o"
+    sub "ో", "ō"
+    sub "ౌ", "au"
+    sub "ఁ", "ň"
+
+
+    # Abagraha
+    sub "ఽ", ":’" # (apostrophe)
+
+
+    sub "\u0c4d", "" #verma sign for halanta
+    sub "ౕ\t", ""
+    sub "ౖ\t", ""
+    sub "्", ""
+    sub "़", ""
+    sub "\u09CD", "" # Used for joining
+    sub "‍", "" # Used for joining
+    sub "‌", "" # Used for non joining
+
+
+    sub "యঁ", "m̐ya"
+    sub "రঁ", "m̐ra"
+    sub "ఱঁ", "m̐ṛa"
+    sub "లঁ", "m̐la"
+    sub "ళঁ", "m̐ḷa"
+    sub "వঁ", "m̐va"
+
+
+    # numbers
+
+    sub "౦", "0"
+    sub "౧", "1"
+    sub "౨", "2"
+    sub "౩", "3"
+    sub "౪", "4"
+    sub "౫", "5"
+    sub "౬", "6"
+    sub "౭", "7"
+    sub "౮", "8"
+    sub "౯", "9"
+  }
+
+  compose
+}