interscript-maps 2.4.3 → 2.5.0

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

@@ -0,0 +1,202 @@
+system "ISO:pan-Guru:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pan
+  source_script Guru
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Panjabi)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "Inherent a with a consonant shall always be transliterated."
+    note "anusvara (including Vedic anusvara) shall be transliterated as ṁ"
+    note "candrabindu shall be transliterated as m̐"
+    note "Bindi shall be transliterated as ṃ and Tippi as ṁ ."
+    note "When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated\n with a semivowel, it shall be placed before the semivowel."
+    note "Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.\n Indic punctuation is outside the scope of this International Standard."
+    note "The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the\n independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent\n shall be attached to the second vowel."
+    note "      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n      follows.\n       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.\n       - Removal of ambiguity in the limited character set option. Tamil perii:i:iya, “really big”, separating the vowels.\n       - Gurmukhi Adhik before a vowel, as in bac: ā (not bacā without Adhik).\n       - Gurmukhi Bindi or Tippi written before the vowel ī (instead of after the vowel) in old orthography, transliterated\n      as ī:ṃ or ī:ṁ , respectively.\n       - Gurmukhi hala making a conjunct h in old orthography, as in tum:ha formed with hala (not tumha formed with the usual subscript h)."
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+    note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
+  }
+}
+
+tests {
+   "ਪੰਜਾਬ 'ਚ ਵਧ ਰਿਹਾ ਖ਼ੁਦਕੁਸ਼ੀਆਂ ਦਾ ਰੁਝਾਨ" ->  "paṁjaāba 'ca vadha raihaā ḵẖaudakauśaīāṃ daā raujhaāna"
+   "ਲੱਖ ਤੋਂ ਪਾਰ ਪੁੱਜਾ ਸਰਗਰਮ ਕੇਸਾਂ ਦਾ ਅੰਕੜਾ, ਦਿੱਲੀ 'ਚ ਦੋ ਲੱਖ ਤੋਂ ਪਾਰ ਇਨਫੈਕਟਿਡ" ->  "lakha taoṃ paāra paujaā saragarama kaesaāṃ daā aṁkaṛaā, dailaī 'ca dao lakha taoṃ paāra inaphaaikaṭaiḍa"
+   "ਪਰਿਵਾਰਕ ਸਮੱਸਿਆਵਾਂ ਅਤੇ ਵਿਆਹ ਵੀ ਹੈ ਹੋਰ ਅਹਿਮ ਕਾਰਨ" ->  "paraivaāraka samasaiāvaāṃ atae vaiāha vaī haai haora ahaima kaārana"
+   "ਮਰਦਾਂ 'ਚ ਔਰਤਾਂ ਨਾਲੋਂ ਵੱਧ ਹੈ ਖ਼ੁਦਕੁਸ਼ੀ ਦਾ ਰੁਝਾਨ" ->  "maradaāṃ 'ca aurataāṃ naālaoṃ vadha haai ḵẖaudakauśaī daā raujhaāna"
+   "ਰਾਸ਼ਟਰੀ ਪੱਧਰ 'ਤੇ ਪੰਜਾਬ ਦੀ ਸਥਿਤੀ ਕਾਫ਼ੀ ਸੂਬਿਆਂ ਤੋਂ ਬਿਹਤਰ" ->  "raāśaṭaraī padhara 'tae paṁjaāba daī sathaitaī kaāfaī saūbaiāṃ taoṃ baihatara"
+   "ਚੀਨੀ ਸੈਨਾ ਨੇ ਲਾਪਤਾ ਅਰੁਣਾਚਲ ਦੇ 5 ਨੌਜਵਾਨਾਂ ਬਾਰੇ ਦੱਸਿਆ" ->  "caīnaī saainaā nae laāpataā arauṇaācala dae 5 naaujavaānaāṃ baārae dasaiā"
+   "ਸਾਖਰਤਾ ਦੇ ਮਾਮਲੇ 'ਚ ਦੇਸ਼ 'ਚ 7ਵੇਂ ਨੰਬਰ 'ਤੇ ਪੰਜਾਬ" ->  "saākharataā dae maāmalae 'ca daeśa 'ca 7vaeṃ naṁbara 'tae paṁjaāba"
+   "ਦਿੱਲੀ ਕਮੇਟੀ ਦੇ ਮੈਂਬਰ ਸ਼ੰਟੀ ਨੇ ਅਕਾਲੀ ਦਲ ਤੋਂ ਦਿੱਤਾ ਅਸਤੀਫ਼ਾ" ->  "dailaī kamaeṭaī dae maaiṃbara śaṁṭaī nae akaālaī dala taoṃ daitaā asataīfaā"
+   "੧੦੨ ਹੋਰ ਕੋਰੋਨਾ ਪਾਜ਼ੀਟਿਵ ਮਰੀਜ਼ਾਂ ਦੀ ਪੁਸ਼ਟੀ, ਇਕ ਦੀ ਮੌਤ" ->  "102 haora kaoraonaā paāzaīṭaiva maraīzaāṃ daī pauśaṭaī, ika daī maauta"
+   "ਸੜਕ ਹਾਦਸੇ ਦੌਰਾਨ ਇਕ ਦੀ ਮੌਤ" ->  "saṛaka haādasae daauraāna ika daī maauta"
+   "ਅਸੀਂ ਲੁੱਕ ਛੁੱਪ ਕ਼ ਆਪਣੀ ਜਾਨ" ->  "asaīṃ lauka chaupa qa āpaṇaī jaāna"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+
+    # Vowels
+
+    sub "ਅ" "a"
+    sub "ਆ" "ā"
+    sub "ਇ" "i"
+    sub "ਈ" "ī"
+    sub "ਉ" "u"
+    sub "ਊ" "ū"
+    sub "ਏ" "e"
+    sub "ਐ" "ai"
+    sub "ਓ" "o"
+    sub "ਔ" "au"
+
+    # Consonants
+    # Gutturals
+    sub "ਕ" "ka"
+    sub "ਖ" "kha"
+    sub "ਗ" "ga"
+    sub "ਘ" "gha"
+    sub "ਙ" "ṅa"
+
+    # Palatals
+    sub "ਚ" "ca"
+    sub "ਛ" "cha"
+    sub "ਜ" "ja"
+    sub "ਝ" "jha"
+    sub "ਞ" "ña"
+
+    # Cerebrals
+    sub "ਟ" "ṭa"
+    sub "ਠ" "ṭha"
+    sub "ਡ" "ḍa"
+    sub "ਢ" "ḍha"
+    sub "ਣ" "ṇa"
+
+    # Dentals
+    sub "ਤ" "ta"
+    sub "ਥ" "tha"
+    sub "ਦ" "da"
+    sub "ਧ" "dha"
+    sub "ਨ" "na"
+
+    # Labials
+    sub "ਪ" "pa"
+    sub "ਫ" "pha"
+    sub "ਬ" "ba"
+    sub "ਭ" "bha"
+    sub "ਮ" "ma"
+
+    # Semivowels
+    sub "ਯ" "ya"
+    sub "ਰ" "ra"
+    sub "ਲ" "la"
+    sub "ਲ਼" "ḷa"
+    sub "ਵ" "va"
+    sub "ੜ" "ṛa"
+
+    # Sibilants
+    sub "ਸ" "sa"
+
+    # Aspirate
+    sub "ਹ" "ha"
+
+    # Bindī
+    sub "ਂ" "ṃ"
+
+    # Ṭippī
+    sub "ੰ" "ṁ"
+
+    # Bisarga
+    sub "ਃ" "ḥ"
+
+    # candrabindu
+    sub "\u0A01" "m̐"
+
+
+    # Medials # Needed for connecting constants
+    sub "ਾ" "ā"
+    sub "ਿ" "i"
+    sub "ੀ" "ī"
+    sub "ੁ" "u"
+    sub "ੂ" "ū"
+    sub "ੇ" "e"
+    sub "ੈ" "ai"
+    sub "ੋ" "o"
+    sub "ੌ" "au"
+    sub "ੱ" ""
+
+    # For adhik before a vowel rule 9 exception
+
+    sub "ੱਅ" ":a"
+    sub "ੱਆ" ":ā"
+    sub "ੱਇ" ":i"
+    sub "ੱਈ" ":ī"
+    sub "ੱਉ" ":u"
+    sub "ੱਊ" ":ū"
+    sub "ੱਏ" ":e"
+    sub "ੱਐ" ":ai"
+    sub "ੱਓ" ":o"
+    sub "ੱਔ" ":au"
+
+    sub "ੱਾ" ":ā"
+    sub "ੱਿ" ":i"
+    sub "ੱੀ" ":ī"
+    sub "ੱੁ" ":u"
+    sub "ੱੂ" ":ū"
+    sub "ੱੇ" ":e"
+    sub "ੱੈ" ":ai"
+    sub "ੱੋ" ":o"
+    sub "ੱੌ" ":au"
+
+
+    # rule 9 exception for bindi and tippi
+
+    sub "ਂਈ" "ī:ṃ"
+    sub "ੰਈ" "ī:ṁ"
+
+
+    # digits
+
+    sub "੦" "0"
+    sub "੧" "1"
+    sub "੨" "2"
+    sub "੩" "3"
+    sub "੪" "4"
+    sub "੫" "5"
+    sub "੬" "6"
+    sub "੭" "7"
+    sub "੮" "8"
+    sub "੯" "9"
+
+
+    # Perso-Arabic Characters
+
+    sub "ਖ਼" "ḵẖa"
+    sub "ਕ਼" "qa"
+    sub "ਗ਼" "ġa"
+    sub "ਫ਼" "fa"
+    sub "ਸ਼" "śa"
+    sub "ਜ਼" "za"
+  }
+
+  compose
+}
+}

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

@@ -0,0 +1,56 @@
+system "ISO:pli-Beng:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pli
+  source_script Beng
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Pali in Bengali)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "Inherent a with a consonant shall always be transliterated."
+    note "anusvara (including Vedic anusvara) shall be transliterated as ṁ"
+    note "candrabindu shall be transliterated as m̐"
+    note "When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated\n with a semivowel, it shall be placed before the semivowel."
+    note "Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.\n Indic punctuation is outside the scope of this International Standard."
+    note "The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the\n independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent\n shall be attached to the second vowel."
+    note "      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n      follows.\n       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule."
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+    note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
+  }
+}
+
+tests {
+   "তেন সমযেন বুদ্ধো ভগৰা ৰেরঞ্জাযং ৰিহরতি নল়েরুপুচিমন্দমূলে মহতা ভিক্খুসঙ্ঘেন সদ্ধিং পঞ্চমত্তেহি ভিক্খুসতেহি" ->  "taena samayaena baudadhao bhagavaā vaerañajaāyaṁ vaiharatai nala়eraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ pañacamatataehai bhaikakhausataehai"
+   "অস্সোসি খো ৰেরঞ্জো ব্রাহ্মণো" ->  "asasaosai khao vaerañajao baraāhamaṇao"
+   "সমণো খলু, ভো, গোতমো সক্যপুত্তো সক্যকুলা পব্বজিতো ৰেরঞ্জাযং ৰিহরতি" ->  "samaṇao khalau, bhao, gaotamao sakayapautatao sakayakaulaā pababajaitao vaerañajaāyaṁ vaiharatai"
+   "নল়েরুপুচিমন্দমূলে মহতা ভিক্খুসঙ্ঘেন সদ্ধিং পঞ্চমত্তেহি ভিক্খুসতেহি" ->  "nala়eraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ pañacamatataehai bhaikakhausataehai"
+   "তং খো পন ভৰন্তং গোতমং এৰং কল্যাণো কিত্তিসদ্দো অব্ভুগ্গতো" ->  "taṁ khao pana bhavanataṁ gaotamaṁ evaṁ kalayaāṇao kaitataisadadao ababhaugagatao"
+   "সো ইমং লোকং সদেৰকং সমারকং সব্রহ্মকং সস্সমণব্রাহ্মণিং পজং সদেৰমনুস্সং সযং অভিঞ্ঞা সচ্ছিকত্ৰা পৰেদেতি" ->  "sao imaṁ laokaṁ sadaevakaṁ samaārakaṁ sabarahamakaṁ sasasamaṇabaraāhamaṇaiṁ pajaṁ sadaevamanausasaṁ sayaṁ abhaiñañaā sacachaikatavaā pavaedaetai"
+   "অরসরূপো সমণো গোতমো’তি, নো চ খো যং ত্ৰং সন্ধায ৰদেসী’’তি" ->  "arasaraūpao samaṇao gaotamao’tai, nao ca khao yaṁ tavaṁ sanadhaāya vadaesaī’’tai"
+   "অরসরূপো ভৰং গোতমো’’তি?" ->  "arasaraūpao bhavaṁ gaotamao’’tai?"
+   "অত্থি খ্ৰেস, ব্রাহ্মণ, পরিযাযো যেন মং পরিযাযেন সম্মা ৰদমানো ৰদেয্য" ->  "atathai khavaesa, baraāhamaṇa, paraiyaāyao yaena maṁ paraiyaāyaena samamaā vadamaānao vadaeyaya"
+   "অরসরূপো সমণো গোতমো’তি" ->  "arasaraūpao samaṇao gaotamao’tai"
+}
+
+dependency "iso-asm-Beng-Latn-15919-2001" as benglatn
+
+stage main {
+  run  map.benglatn.stage.main
+}
+}

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

@@ -0,0 +1,56 @@
+system "ISO:pli-Deva:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pli
+  source_script Deva
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Pali in Devanagari)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "Inherent a with a consonant shall always be transliterated."
+    note "anusvara (including Vedic anusvara) shall be transliterated as ṁ"
+    note "candrabindu shall be transliterated as m̐"
+    note "When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated\n with a semivowel, it shall be placed before the semivowel."
+    note "Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.\n Indic punctuation is outside the scope of this International Standard."
+    note "The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the\n independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent\n shall be attached to the second vowel."
+    note "      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n      follows.\n       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule.\n       -  Vowel hiatus, not digraph transliteration of diphthongs; as in Sanskrit pra:uga (not prauga), “yoke”;\n       -  Absence of aspiration, as in the Nepali plural form vid:harū (not vidharū )"
+
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+    note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
+  }
+}
+
+tests {
+   "तेन खो पन समयेन वेसालिया अविदूरे कलन्दगामो नाम अत्थि" ->  "taena khao pana samayaena vaesaālaiyaā avaidaūrae kalanadagaāmao naāma atathai"
+   "तत्थ सुदिन्‍नो नाम कलन्दपुत्तो सेट्ठिपुत्तो होति" ->  "tatatha saudainanao naāma kalanadapautatao saeṭaṭhaipautatao haotai"
+   "अथ खो सुदिन्‍नो कलन्दपुत्तो सम्बहुलेहि" ->  "atha khao saudainanao kalanadapautatao samabahaulaehai"
+   "तथा चतुर्भिः पुरुषः परीक्ष्यते त्यागेन शीलेन गुणेन कर्मणा" ->  "tathaā cataurabhaiḥ paurauṣaḥ paraīkaṣayatae tayaāgaena śaīlaena gauṇaena karamaṇaā"
+   "अथ खो सुदिन्‍नो कलन्दपुत्तो अचिरवुट्ठिताय परिसाय येन भगवा तेनुपसङ्कमि; उपसङ्कमित्वा भगवन्तं अभिवादेत्वा एकमन्तं निसीदि" ->  "atha khao saudainanao kalanadapautatao acairavauṭaṭhaitaāya paraisaāya yaena bhagavaā taenaupasaṅakamai; upasaṅakamaitavaā bhagavanataṁ abhaivaādaetavaā ekamanataṁ naisaīdai"
+   "अथ खो सुदिन्‍नस्स कलन्दपुत्तस्स मातापितरो सुदिन्‍नं कलन्दपुत्तं एतदवोचुं" ->  "atha khao saudainanasasa kalanadapautatasasa maātaāpaitarao saudainanaṁ kalanadapautataṁ etadavaocauṁ"
+   "त्वं खोसि, तात सुदिन्‍न, अम्हाकं एकपुत्तको पियो मनापो सुखेधितो सुखपरिहतो" ->  "tavaṁ khaosai, taāta saudainana, amahaākaṁ ekapautatakao paiyao manaāpao saukhaedhaitao saukhaparaihatao"
+   "न त्वं, तात सुदिन्‍न, किञ्‍चि दुक्खस्स जानासि" ->  "na tavaṁ, taāta saudainana, kaiñacai daukakhasasa jaānaāsai"
+   "अनुञ्‍ञातोम्हि किर मातापितूहि अगारस्मा अनगारियं पब्बज्‍जाया’’ति, हट्ठो उदग्गो पाणिना गत्तानि परिपुञ्छन्तो वुट्ठासि" ->  "anauñañaātaomahai kaira maātaāpaitaūhai agaārasamaā anagaāraiyaṁ pababajajaāyaā’’tai, haṭaṭhao udagagao paāṇainaā gatataānai paraipauñachanatao vauṭaṭhaāsai"
+}
+
+dependency "iso-san-Deva-Latn-15919-2001" as devalatn
+
+stage main {
+  run  map.devalatn.stage.main
+}
+}

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

@@ -0,0 +1,199 @@
+system "ISO:pli-Sinh:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pli
+  source_script Sinh
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Pali in Sinhala)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "Inherent a with a consonant shall always be transliterated."
+    note "anusvara (including Vedic anusvara) shall be transliterated as ṁ"
+    note "candrabindu shall be transliterated as m̐"
+    note "When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated\n with a semivowel, it shall be placed before the semivowel."
+    note "Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.\n Indic punctuation is outside the scope of this International Standard."
+    note "The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the\n independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent\n shall be attached to the second vowel."
+    note "      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n      follows.\n       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule."
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+    note "When the half-nasal in Telugu script is used for modern nasalization in writing Hindi or\n any other language, it shall be transliterated as a tilde above the transliterated vowel. In the case of the digraphs ai,\n au, the tilde shall be attached to the second vowel"
+    note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
+  }
+}
+
+tests {
+   "තෙන සමයෙන බුද්‌ධො භගවා වෙරඤ්‌ජායං විහරති නළෙරුපුචිමන්‌දමූලෙ මහතා භික්‌ඛුසඞ්‌ඝෙන සද්‌ධිං" ->  "taena samayaena baudadhao bhagavaā vaerañajaāyaṁ vaiharatai naḷaeraupaucaimanadamaūlae mahataā bhaikakhausaṅaghaena sadadhaiṁ"
+   "පඤ්‌චමත්‌තෙහි භික්‌ඛුසතෙහි. අස්‌සොසි ඛො වෙරඤ්‌ජො බ්‍රාහ්‌මණො" ->  "pañacamatataehai bhaikakhausataehai. asasaosai khao vaerañajao baraāhamaṇao"
+   "අථ ඛො වෙරඤ්‌ජො බ්‍රාහ්‌මණො යෙන භගවා තෙනුපසඞ්‌කමි;" ->  "atha khao vaerañajao baraāhamaṇao yaena bhagavaā taenaupasaṅakamai;"
+   "උපසඞ්‌කමිත්‌වා භගවතා සද්‌ධිං සම්‌මොදි." ->  "upasaṅakamaitavaā bhagavataā sadadhaiṁ samamaodai."
+   "නිබ්‌භොගො භවං ගොතමො" ->  "naibabhaogao bhavaṁ gaotamao"
+   "අකිරියවාදො භවං ගොතමො" ->  "akairaiyavaādao bhavaṁ gaotamao"
+   "උච්‌ඡෙදවාදො භවං ගොතමො" ->  "ucachaedavaādao bhavaṁ gaotamao"
+   "ජෙගුච්‌ඡී භවං ගොතමො" ->  "jaegaucachaī bhavaṁ gaotamao"
+   "අහොසි අසල්‌ලීනං, උපට්‌ඨිතා සති අසම්‌මුට්‌ඨා‍" ->  "ahaosai asalalaīnaṁ, upaṭaṭhaitaā satai asamamauṭaṭhaā"
+   "අත්‌ථි ඛ්‌වෙස, බ්‍රාහ්‌මණ, පරියායො යෙන මං පරියායෙන සම්‌මා වදමානො වදෙය්‍" ->  "atathai khavaesa, baraāhamaṇa, paraiyaāyao yaena maṁ paraiyaāyaena samamaā vadamaānao vadaeya"
+}
+
+stage main {
+
+  # CHARACTERS
+  parallel {
+
+    sub "අ" "a"
+    sub "ආ" "ā"
+    sub "ඇ" "æ"
+    sub "ඈ" "ǣ"
+    sub "ඉ" "i"
+    sub "ඊ" "ī"
+    sub "උ" "u"
+    sub "ඌ" "ū"
+    sub "ඍ" "ṛ"
+    sub "ඎ" "ṝ"
+    sub "ඏ" "ḻ"
+    sub "ඐ" "ḹ"
+    sub "එ" "e"
+    sub "ඒ" "ē"
+    sub "ඓ" "ai"
+    sub "ඔ" "o"
+    sub "ඕ" "ō"
+    sub "ඖ" "au"
+
+    sub "ා" "ā"
+    sub "ැ" "æ"
+    sub "ෑ" "ǣ"
+    sub "ි" "i"
+    sub "ී" "ī"
+    sub "ු" "u"
+    sub "ූ" "ū"
+    sub "ෘ" "ṛ"
+    sub "ෲ" "ṝ"
+    sub "ෟ" "ḻ"
+    sub "ෳ" "ḹ"
+    sub "ෙ" "e"
+    sub "ේ" "ē"
+    sub "ෛ" "ai"
+    sub "ො" "o"
+    sub "ෝ" "ō"
+    sub "ෞ" "au"
+
+
+    # II. Consonants (see Note 2)
+    # Gutturals  క ఖ గ ఘ ఙ
+    sub "ක" "ka"
+    sub "ඛ" "kha"
+    sub "ග" "ga"
+    sub "ඝ" "gha"
+    sub "ඞ" "ṅa"
+    sub "ඟ" "ṅga"
+
+    # Palatals చ ఛ జ ఝ ఞ
+    sub "ච" "ca"
+    sub "ඡ" "cha"
+    sub "ජ" "ja"
+    sub "ඣ" "jha"
+    sub "ඤ" "ña"
+    sub "ඦ" "ñja"
+
+
+    # Cerebrals ట ఠ డ ఢ ణ
+    sub "ට" "ṭa"
+    sub "ඨ" "ṭha"
+    sub "ඩ" "ḍa"
+    sub "ඪ" "ḍha"
+    sub "ණ" "ṇa"
+    sub "ඬ" "ṇḍa"
+
+    # Dentals త థ ద ధ న
+    sub "ත" "ta"
+    sub "ථ" "tha"
+    sub "ද" "da"
+    sub "ධ" "dha"
+    sub "න" "na"
+    sub "ඳ" "nda"
+
+    # Labials ప ఫ బ భ మ
+    sub "ප" "pa"
+    sub "ඵ" "pha"
+    sub "බ" "ba"
+    sub "භ" "bha"
+    sub "ම" "ma"
+    sub "ඹ" "mba"
+
+    # Semivowels య ర ల వ
+    sub "ය" "ya"
+    sub "ර" "ra"
+    sub "ල" "la"
+    sub "ළ" "ḷa"
+    sub "ව" "va"
+
+    # Sibilants శ ష స హ
+    sub "ශ" "śa"
+    sub "ෂ" "ṣa"
+    sub "ස" "sa"
+
+
+
+    # Aspirate
+    sub "හ" "ha"
+
+    sub "ෆ" "fa"
+
+    # Chandrabindu
+    sub "ઁ" "m̐"
+
+    # Bisarga
+    sub "ඃ" "ḥ"
+
+    # Anusvāra
+    sub "ං" "ṁ"
+
+
+    # numbers
+
+    sub "\u0DE6" "0"
+    sub "\u0DE7" "1"
+    sub "\u0DE8" "2"
+    sub "\u0DE9" "3"
+    sub "\u0DEA" "4"
+    sub "\u0DEB" "5"
+    sub "\u0DEC" "6"
+    sub "\u0DED" "7"
+    sub "\u0DEE" "8"
+    sub "\u0DEF" "9"
+
+
+    # semivowel chandrabindu rule
+
+    # Semivowels య ర ల వ
+    sub "යઁ" "m̐ya"
+    sub "රઁ" "m̐ra"
+    sub "ලઁ" "m̐la"
+    sub "ළઁ" "m̐ḷa"
+    sub "වઁ" "m̐va"
+
+
+
+    sub "\u09CD" ""
+    sub "‍" ""
+    sub "‌" ""
+    sub "්" ""
+  }
+
+  compose
+}
+}

data/maps/iso-pli-Thai-Latn-15919-2001.isc

@@ -0,0 +1,49 @@
+system "ISO:pli-Thai:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pli
+  source_script Thai
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Pali in Thai)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+  }
+}
+
+tests {
+   "โย กปฺปโกฏีหิปิ อปฺปเมยฺยํ;" ->  "oy kp–̥pokṭīh̄ipi xp–̥pemy–̥ẙ;"
+   "ตตฺถ ตํ วณฺณยิสฺสํ วินยนฺติ วุตฺตตฺตา วินโย ตาว ววตฺถเปตพฺโพฯ เตเนตํ วุจฺจติ" ->  "tt–̥t̄h t̊ wṇ–̥ṇyis̄–̥s̄̊ winyn–̥ti wut–̥tt–̥tā winoy tāw wwt–̥t̄heptph–̥ophǂ etent̊ wuc–̥cti"
+   "วุตฺตํ เยน ยทา ยสฺมา, ธาริตํ เยน จาภตํ; ยตฺถปฺปติฏฺฐิตเจตเมตํ วตฺวา วิธิํ ตโตฯ" ->  "wut–̥t̊ eyn ythā ys̄–̥mā, ṭhārit̊ eyn cāp̣ht̊; yt–̥t̄hp–̥ptiṭ–̥ṭ̄hitectemt̊ wt–̥wā wiṭhi̊ totǂ"
+   "เตนาติอาทิปาฐสฺส, อตฺถํ นานปฺปการโต; ทสฺสยนฺโต กริสฺสามิ, วินยสฺสตฺถวณฺณนนฺติฯ" ->  "etnātixāthipāṭ̄hs̄–̥s̄, xt–̥t̄h̊ nānp–̥pkārot; ths̄–̥s̄yn–̥ot kris̄–̥s̄āmi, winys̄–̥s̄t–̥t̄hwṇ–̥ṇnn–̥tiǂ"
+   "ยํนูนาหํ ธมฺมญฺจ วินยญฺจ สงฺคาเยยฺยํ, ยถยิทํ สาสนํ อทฺธนิยํ อสฺส จิรฏฺฐิติกํฯ" ->  "ẙnūnāh̄̊ ṭhm–̥mỵ–̥c winyỵ–̥c s̄ng–̥khāeyy–̥ẙ, yt̄hyith̊ s̄ās̄n̊ xth–̥ṭhniẙ xs̄–̥s̄ cirṭ–̥ṭ̄hitik̊ǂ"
+   "ธาเรสฺสสิ ปน เม ตฺวํ, กสฺสป, สาณานิ ปํสุกูลานิ นิพฺพสนานี’ติ วตฺวา จีวเร สาธารณปริโภเคน เจว" ->  "ṭhāers̄–̥s̄s̄i pn em t–̥ẘ, ks̄–̥s̄p, s̄āṇāni p̊s̄ukūlāni niph–̥phs̄nānī’ti wt–̥wā cīwer s̄āṭhārṇpriop̣hekhn ecw"
+   "อถ โข อายสฺมา มหากสฺสโป ภิกฺขู อามนฺเตสิ" ->  "xt̄h ok̄h xāys̄–̥mā mh̄āks̄–̥s̄op p̣hik–̥k̄hū xāmn–̥ets̄i"
+   "อกาโล โข, มาณวก, อตฺถิ เม อชฺช เภสชฺชมตฺตา ปีตา, อปฺเปว นาม สฺเวปิ อุปสงฺกเมยฺยามา" ->  "xkāol ok̄h, māṇwk, xt–̥t̄hi em xch–̥ch ep̣hs̄ch–̥chmt–̥tā pītā, xp–̥epw nām s̄–̥ewpi xups̄ng–̥kemy–̥yāmā"
+   "สฺเว สนฺนิปาโต, น โข ปน เมตํ ปติรูปํ ยฺวาหํ เสกฺโข สมาโน สนฺนิปาตํ คจฺเฉยฺย" ->  "s̄–̥ew s̄n–̥nipāot, n ok̄h pn emt̊ ptirūp̊ y–̥wāh̄̊ es̄k–̥ok̄h s̄māon s̄n–̥nipāt̊ khc–̥ec̄hy–̥y"
+   "สุณาตุ เม, ภนฺเต, สงฺโฆฯ ยทิ สงฺฆสฺส ปตฺตกลฺลํ, อหํ อายสฺมตา มหากสฺสเปน วินยํ ปุฏฺโฐ วิสฺสชฺเชยฺย" ->  "s̄uṇātu em, p̣hn–̥et, s̄ng–̥oḳhǂ ythi s̄ng–̥ḳhs̄–̥s̄ pt–̥tkl–̥l̊, xh̄̊ xāys̄–̥mtā mh̄āks̄–̥s̄epn winẙ puṭ–̥oṭ̄h wis̄–̥s̄ch–̥echy–̥y"
+   "สุณาตุ เม, อาวุโส, สงฺโฆฯ ยทิ สงฺฆสฺส ปตฺตกลฺลํ, อหํ อานนฺทํ ธมฺมํ ปุจฺเฉยฺย" ->  "s̄uṇātu em, xāwuos̄, s̄ng–̥oḳhǂ ythi s̄ng–̥ḳhs̄–̥s̄ pt–̥tkl–̥l̊, xh̄̊ xānn–̥th̊ ṭhm–̥m̊ puc–̥ec̄hy–̥y"
+}
+
+dependency "iso-tha-Thai-Latn-11940-1998" as thailatn
+
+stage main {
+  run  map.thailatn.stage.main
+}
+}

data/maps/iso-pra-Deva-Latn-15919-2001.isc

@@ -0,0 +1,50 @@
+system "ISO:pra-Deva:Latn:15919-2001" {
+
+metadata {
+  authority_id iso
+  id 15919-2001
+  language iso-639-2:pra
+  source_script Deva
+  destination_script Latn
+  name "ISO 15919:2001 Information and documentation -- Transliteration of Devanagari and related Indic scripts into Latin characters (Prakrit)"
+  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 {
+
+    note "All transliterations made using this International Standard shall be case-insensitive."
+    note "Inherent a with a consonant shall always be transliterated."
+    note "anusvara (including Vedic anusvara) shall be transliterated as ṁ"
+    note "candrabindu shall be transliterated as m̐"
+    note "When m̐, ṃ or ṁ are associated with a vowel, they shall be placed after the vowel. When m̐ is associated\n with a semivowel, it shall be placed before the semivowel."
+    note "Latin punctuation signs and Hindu-Arabic numerals shall remain unchanged in transliteration.\n Indic punctuation is outside the scope of this International Standard."
+    note "The Vedic accent Udatta shall be transliterated as an acute accent over the transliterated vowel, and the\n independent Svarita as a grave accent over the transliterated vowel. In the case of the digraphs ai, au, the accent\n shall be attached to the second vowel."
+    note "      A colon: before a Latin character shall be used to resolve ambiguity. Some normative cases are as\n      follows.\n       -  :’ for avagraha in modern text. (The apostrophe in modern text remains unchanged in accordance with previous rule."
+
+    note "If a character in an Indic script is defined in such a way as to be equivalent to another character in any\n script, where the second character has a transliteration in this International Standard, then the first character shall\n be transliterated in the same way as the second character."
+    note "Where it is desired to show the Vedic accent Anudatta, it should be transliterated as an underscore. In the case of\n the digraphs ai, au, both Latin vowels should be underscored.\n Where word boundaries are not shown in the original text (as happens commonly in Sanskrit) and a word ends in a\n consonant, the transliteration should show word division by a space; but when phonological processes result in two\n words sharing a common vowel, no attempt should be made to separate them. This will require a good knowledge\n of the language in question."
+  }
+}
+
+tests {
+   "सृष्टिस्थितिविनाशानां शक्तिभूते सनातनि" ->  "saṛṣaṭaisathaitaivainaāśaānaāṁ śakataibhaūtae sanaātanai"
+   "गुणाश्रये गुणमये नारायणि नमोऽस्तु ते" ->  "gauṇaāśarayae gauṇamayae naāraāyaṇai namao:’satau tae"
+   "तेन समयेन बुद्धो भगवा सावत्थियं विहरति जेतवने अनाथपिण्डिकस्स आरामे" ->  "taena samayaena baudadhao bhagavaā saāvatathaiyaṁ vaiharatai jaetavanae anaāthapaiṇaḍaikasasa āraāmae"
+}
+
+dependency "iso-san-Deva-Latn-15919-2001" as devalatn
+
+stage main {
+  run  map.devalatn.stage.main
+}
+}