interscript 0.1.3 → 0.1.9

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

@@ -0,0 +1,75 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:asm
+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: "অসমীয়া কবিতা"
+    expected: "asamaīẏaā kabaitaā"
+  - source: "কবিৰ আজি জন্মদিন"
+    expected: "kabaiva ājai janamadaina"
+  - source: "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড"
+    expected: "baevauṭata emaāhava paāchatae paunava bhaya়ṁkava aganaikaāṇaḍa"
+  - source: "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ"
+    expected: "bhaṅaāva baivaudadhae āraedana daākhaila kaṁganaāva"
+  - source: "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি"
+    expected: "āpaunai paṙhai bhaāla paāba pavaā baātavai"
+  - source: "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক"
+    expected: "śavaīvaāmapauvata gavaubhavatai ṭavaāka jabada, daujanaka āṭaka"
+  - source: "কেনে আছে প্ৰাক্তন"
+    expected: "kaenae āchae pavaākatana"
+  - source: "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ"
+    expected: "kamaumabaāiva maeẏavava daehata kaobhaiḍa pajaiṭaibha"
+  - source: "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা"
+    expected: "ṭauiṭaāvayaogae khaoda sadavaī kavae ei kathaā"
+  - source: "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়"
+    expected: "lakhaimapauva jailaāva naāvaāẏaṇapauvava bavapathaāvata ājai pavaśaānatai dhaāma naāmaevae ekhana baṛdadhaāśavamava śaubhaāvamabha kavaā haẏa"
+
+map:
+  inherit: 'iso-ben-Beng-Latn-15919-2001'
+
+  characters:
+    'ৰ': 'va'
+    'ৱ': 'ra'

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

@@ -0,0 +1,175 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:ben
+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.
+     -  Vowel hiatus, not digraph transliteration of diphthongs; as in Bengali ba:i (not bai), “book”.
+     -  Unexpected use of secondary ya/ẏa , as in Bengali r:yāpāra , English “wrapper” (using full r); a:yā (not ayā ).
+  - 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: "আগুয়েরোর হাঁটুর চোট"
+    expected: "āgauẏaeraora haām̐ṭaura caoṭa"
+  - source: "তঅস্ত্রোপচারের আশ্রয় নিতে হবে এ তারকাকে, তাই দলে জায়গা পাননি"
+    expected: "taasataraopacaāraera āśaraẏa naitae habae e taārakaākae, taāi dalae jaāẏagaā paānanai"
+  - source: "ওদিকে সদ্য করোনা থেকে ফিরে এসে দাপটের সঙ্গে পিএসজির হয়ে খেলে যাওয়া দি মারিয়া কেন ডাক পাননি, কেউ জানে না"
+    expected: "odaikae sadaya karaonaā thaekae phairae esae daāpaṭaera saṅagae paiesajaira haẏae khaelae yaāoẏaā dai maāraiẏaā kaena ḍaāka paānanai, kaeu jaānae naā"
+  - source: "তিন বিভাগে শনিবার থেকে ভারী বৃষ্টি, কমবে তাপমাত্রা"
+    expected: "taina baibhaāgae śanaibaāra thaekae bhaāraī baṛṣaṭai, kamabae taāpamaātaraā"
+  - source: "ফেসবুকে সময় নষ্ট না করে মায়ের সঙ্গে আড্ডা ভালোবাসেন তিনি"
+    expected: "phaesabaukae samaẏa naṣaṭa naā karae maāẏaera saṅagae āḍaḍaā bhaālaobaāsaena tainai"
+  - source: "এখনই আর্জেন্টিনার জার্সি খুলো না—দি মারিয়াকে কোচ"
+    expected: "ekhanai ārajaenaṭainaāra jaārasai khaulao naā—dai maāraiẏaākae kaoca"
+  - source: "প্রিয় তারকার আওয়াজ শুনে কোমা থেকে জেগে উঠলেন তিনি"
+    expected: "paraiẏa taārakaāra āoẏaāja śaunae kaomaā thaekae jaegae uṭhalaena tainai"
+  - source: "সুয়ারেজকে ‘বের করে দেওয়া’য় বার্সাকে ধুয়ে দিলেন মেসি"
+    expected: "sauẏaāraejakae ‘baera karae daeoẏaā’ẏa baārasaākae dhauẏae dailaena maesai"
+  - source: "আমি না থাকলে আর্জেন্টিনা দলে মেসিরও থাকার যোগ্যতা নেই"
+    expected: "āmai naā thaākalae ārajaenaṭainaā dalae maesairao thaākaāra yaogayataā naei"
+  - source: "তবে, নিয়মিত মুখগুলোর মধ্যে দলে নেই মেসির দুই ‘প্রিয় বন্ধু’ পিএসজির মিডফিল্ডার আনহেল দি মারিয়া ও ম্যানচেস্টার সিটির সার্জিও আগুয়েরো"
+    expected: "tabae, naiẏamaita maukhagaulaora madhayae dalae naei maesaira daui ‘paraiẏa banadhau’ paiesajaira maiḍaphailaḍaāra ānahaela dai maāraiẏaā o mayaānacaesaṭaāra saiṭaira saārajaio āgauẏaerao"
+
+map:
+  characters:
+
+    #vowel characters
+
+    'অ': 'a'
+    'আ': 'ā'
+    'ই': 'i'
+    'ঈ': 'ī'
+    'উ': 'u'
+    'ঊ': 'ū'
+    'ঋ': 'ṛ'
+    'ৠ': 'ṝ'
+    'ঌ': 'ḻ'
+    'ৡ': 'ḹ'
+    'এ': 'e'
+    'ঐ': 'ai'
+    'ও': 'o'
+    'ঔ': 'au'
+
+    'া': 'ā'
+    'ি': 'i'
+    'ী': 'ī'
+    'ু': 'u'
+    'ূ': 'ū'
+    'ৃ': 'ṛ'
+    'ৄ': 'ṝ'
+    'ৢ': 'ḻ'
+    'ৣ': 'ḹ'
+    'ে': 'e'
+    'ৈ': 'ai'
+    'ো': 'o'
+    'ৌ': 'au'
+
+
+    'ং':	'ṁ'
+    'ঁ':	'm̐'
+    'ঃ':	'ḥ'
+
+    # Consonant characters
+
+    'ক': 'ka'
+    'খ': 'kha'
+    'গ': 'ga'
+    'ঘ': 'gha'
+    'ঙ': 'ṅa'
+    'চ': 'ca'
+    'ছ': 'cha'
+    'জ': 'ja'
+    'ঝ': 'jha'
+    'ঞ': 'ña'
+    'ট': 'ṭa'
+    'ঠ': 'ṭha'
+    'ড': 'ḍa'
+    'ঢ': 'ḍha'
+    'ণ': 'ṇa'
+    'ত': 'ta'
+    'থ': 'tha'
+    'দ': 'da'
+    'ধ': 'dha'
+    'ন': 'na'
+    'প': 'pa'
+    'ফ': 'pha'
+    'ব': 'ba'
+    'ভ': 'bha'
+    'ম': 'ma'
+    'য': 'ya'
+    'র': 'ra'
+    'ল': 'la'
+    'শ': 'śa'
+    'ষ': 'ṣa'
+    'স': 'sa'
+    'হ': 'ha'
+
+    'ড়': 'ṙa'
+    'ঢ়': 'ṙha'
+    'য়': 'ẏa'
+
+
+    # for semivowel rule no. 5
+
+    'যঁ': 'm̐ya'
+    'রঁ': 'm̐ra'
+    'লঁ': 'm̐la'
+    'বঁ': 'm̐va'
+
+    'ৎ': 't'
+    '্': ''
+
+
+   # numbers
+
+    '১': '1' 
+    '২': '2'
+    '৩': '3'
+    '৪': '4'
+    '৫': '5'
+    '৬': '6'
+    '৭': '7'
+    '৮': '8'
+    '৯': '9'
+    '০': '0'
+

data/maps/iso-ell-Grek-Latn-843-1997-t1.yaml

@@ -1,14 +1,18 @@
 ---
 authority_id: iso
 id: 1997
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
-name: ISO 843:1997
-url: 
+name: "ISO 843:1997 Information and documentation — Conversion of Greek characters into Latin characters"
+url: https://www.iso.org/standard/5215.html
 creation_date: 1997
 description: |
-  ISO Transliteration table for Greek
+  Establishes a system for the transliteration and/or transcription 
+  of Greek characters into Latin characters. This system applies to
+  the characters of the Greek script, independent of the period in
+  which it is or was used, i.e. scripts from all periods of Classic
+  or Modern Greek. Replaces ISO/R 843.
 
 note:
   - Transliteration of Greek into Latin: Type 1, Clause 3 Table 1
@@ -25,7 +29,7 @@ tests:
 
     expected: |
         Éna práma mónon me parakínīse ki eména na grápsō óti toútīn tīn patrída tīn échomen óloi mazí, kai sofoí ki amatheís kai ploúsioi kai ftōchoí kai politikoí kai stratiōtikoí kai oi pléon mikróteroi ánthrōpoi; ósoi agōnistī́kamen, analógōs o katheís, échomen na zī́somen edṓ. To loipón doulépsamen óloi mazí, na tīn fylámen ki óloi mazí kai na mīn légei oúte o dynatós «egṓ» oúte o adýnatos. Xérete póte na légei o katheís «egṓ»? Ótan agōnisteí mónos tou kai fkiásei ī́ chalásei, na légei «egṓ»; ótan ómōs agōnízontai polloí kai fkiánoun, tóte na léne «emeís». Eímaste eis to «emeís» ki óchi eis to «egṓ». Kai eis to exī́s na máthomen gnṓsī, an thélomen na fkiásomen chōrión, na zī́somen óloi mazí.
-       
+
         Giánnīs Makrygiánnīs.
 
 
@@ -73,7 +77,7 @@ tests:
     expected: Taÿ́getos
   - source: σπρέυ
     expected: spréy
-    
+
   - source: Αθήνα
     expected: Athī́na
   - source: Άγιον Όρος
@@ -521,7 +525,7 @@ map:
     - pattern: (?<=[ΑαΕεΟο])\u03C5    # υ (after Α, Ε, Η)
       result: u
     - pattern: (?<=[ΑαΕεΟο])\u03CD    # ύ (after Ο)
-      result: ú      
+      result: ú
     - pattern: \u037E   # ;
       result: "?"
     - pattern: \u003B   # ;
@@ -607,4 +611,3 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
-

data/maps/iso-ell-Grek-Latn-843-1997-t2.yaml

@@ -1,14 +1,18 @@
 ---
 authority_id: iso
 id: 1997
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
-name: ISO 843:1997
-url: 
+name: "ISO 843:1997 Information and documentation — Conversion of Greek characters into Latin characters"
+url: https://www.iso.org/standard/5215.html
 creation_date: 1997
 description: |
-  ISO Transcription table for Greek
+  Establishes a system for the transliteration and/or transcription
+  of Greek characters into Latin characters. This system applies to
+  the characters of the Greek script, independent of the period in
+  which it is or was used, i.e. scripts from all periods of Classic
+  or Modern Greek. Replaces ISO/R 843.
 
 note:
   - Transliteration of Greek into Latin: Type 2, Clause 3 Table 2
@@ -38,4 +42,3 @@ map:
     "\u03F9": "S"   # Ϲ
     "\u03F3": "j"
     "\u037F": "j"
-

data/maps/iso-guj-Gujr-Latn-15919-2001.yaml

@@ -0,0 +1,220 @@
+---
+authority_id: iso
+id: 15919-2001
+language: iso-639-2:guj
+source_script: Gujr
+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: "અમિત શાહનો કોરોના રિપોર્ટ 2 ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
+    expected: "amaita śaāhanao kaoraonaā raipaoratạ 2 ogasatạe paojhaitạiva āvayao hatao, tayaārathaī taemanauṁ savaāsathaya saārauṁ nathaī"
+  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
+    expected: "maedaāṁtaā haosapaitạlamaāṁ taemanao ilaāja caālaī rahayao hatao"
+  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
+    expected: "bhaāratanaā vaiśavanaāthana ānaṁdae śaenayaānamaāṁ pahaelao phaiḍae śataraṁja vaiśava kapa jaītayao"
+  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ 40 લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
+    expected: "bhaārataīya vaḍaā paradhaāna javaāharalaāla naeharaue 40 laākha hainadauo anae mausalamaānaonaā paārasaparaika sathaānaāṁtaraṇanauṁ saūcana āpayauṁ"
+  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન ૫૮ ડિગ્રી સેલ્સિયસ હતું."
+    expected: "laibaiyaānaā ela ajaijaiyaāmaāṁ dharataī para saauthaī vadhau taāpamaāna naoṁdhaāyauṁ. e vakhatae chaāyaāmaāṁ naoṁdhavaāmaāṁ āvaelauṁ taāpamaāna 58 ḍaigaraī saelasaiyasa hatauṁ."
+  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
+    expected: "parathama vaiśavayaudadhaḥ jaramanaī anae pharaānasa vacacae esanaenaī laḍaāī śaraū thaī hataī"
+  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
+    expected: "enagalao-maisatara yaudadhaḥ taela ala kaebairanauṁ yaudadha laḍavaāmaāṁ āvayauṁ hatauṁ."
+  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
+    expected: "pauraāvaā na hataā, e ja kaāraṇae kaesa caālayao nahaīṁ, paṇa taemanae najarakaeda raākhavaāmaāṁ āvayaā"
+  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; 91 વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
+    expected: "saradaāra patạelae nakakaī karayauṁ hatauṁ kae kaāśamaīra bhaāratanao haisasao banaśae; 91 varaṣa pahaelaāṁ laāhaora jaelamaāṁ bhaūkhahaḍataāḷa daramaiyaāna śahaīda thayaā hataā jataīna daāsa"
+  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
+    expected: "kaoraonaā paraotạokaola vacacae ājae maeḍaikala paravaeśa paraīkaṣaā laevaāśaeḥ enatạraī tạca pharaī rahaeśae, eḍamaitạ kaāraḍa baāra kaoḍathaī caeka thaśae"
+  - source: "અલ્ ક઼`ઇદ્ માં હવામાન"
+    expected: "ala qa`ida maāṁ havaāmaāna"
+  - source: "મંત્રાલય તથા ખ઼.ય ના વિ૨ષ્ઠ અધિકા૨ીઓ ઉપસ્થિત ૨હ્યા હતા"
+    expected: "maṁtaraālaya tathaā ḵẖa.ya naā vai2ṣaṭha adhaikaā2īo upasathaita 2hayaā hataā"
+
+map:
+
+  characters:
+
+    'અ': 'a'
+    'આ': 'ā'
+    'ઇ': 'i'
+    'ઈ': 'ī'
+    'ઉ': 'u'
+    'ઊ': 'ū'
+    'ઋ': 'ṛ'
+    'ૠ': 'ṝ'
+    'ઌ': 'ḷ'
+    'ૡ': 'ḹ'
+
+    'ઍ': 'ê'
+    'એ': 'e'
+    'ઐ': 'ai'
+
+    'ઑ': 'ô'
+    'ઓ': 'o'
+    'ઔ': 'au'
+
+    # Gutturals
+    'ક': 'ka'
+    'ખ': 'kha'
+    'ગ': 'ga'
+    'ઘ': 'gha'
+    'ઙ': 'ṅa'
+
+    # Palatals
+    'ચ': 'ca'
+    'છ': 'cha'
+    'જ': 'ja'
+    'ઝ': 'jha'
+    'ઞ': 'ña'
+
+    # Cerebrals
+    'ટ':  'tạ'
+    'ઠ':  'ṭha'
+    'ડ':  'ḍa'
+    'ઢ':  'ḍha'
+    'ણ':  'ṇa'
+
+    # Dentals
+    'ત': 'ta'
+    'થ': 'tha'
+    'દ': 'da'
+    'ધ': 'dha'
+    'ન': 'na'
+
+    # Labials
+    'પ': 'pa'
+    'ફ': 'pha'
+    'બ': 'ba'
+    'ભ': 'bha'
+    'મ': 'ma'
+
+    # Semivowels
+    'ય': 'ya'
+    'ર': 'ra'
+    'લ': 'la'
+    'ળ': 'ḷa'
+    'વ': 'va'
+
+    # Sibilants
+    'શ': 'śa'
+    'ષ': 'ṣa'
+    'સ': 'sa'
+
+
+    # Aspirate
+    'હ': 'ha'
+
+    # Chandrabindu
+    'ઁ': 'm̐'
+
+    # Bisarga
+    'ઃ': 'ḥ'
+
+    # Anusvāra
+    'ં': 'ṁ'
+
+    # Medials # Needed for connecting constants
+
+    'ા': 'ā'
+    'િ': 'i'
+    'ી': 'ī'
+    'ુ': 'u'
+    'ૂ': 'ū'
+    'ૃ': 'ṛ'
+    'ૄ': 'ṝ'
+    '\u0AE2': 'ḷ'  #  ૢ
+    '\u0AE3': 'ḹ'  #  ૣ
+
+    'ૅ': 'ê'
+    'ૉ': 'ô'
+
+    'ે': 'e'
+    'ૈ': 'ai'
+    'ો': 'o'
+    'ૌ': 'au'
+
+    # for semivowel rule no. 5
+
+    'યઁ': 'm̐ya'
+    'રઁ': 'm̐ra'
+    'લઁ': 'm̐la'
+    'ળઁ': 'm̐ḷa'
+    'વઁ': 'm̐va'
+
+
+    # Perso-Arabic Characters
+
+    'ક઼': 'qa'
+    'ખ઼': 'ḵẖa'
+    'ગ઼': 'ġa'
+    'જ઼': 'za'
+    'ફ઼': 'fa'
+
+
+    # Abagraha
+    'ऽ': ':’'
+
+
+
+
+    '\u09CD': '' # Used for joining
+    '્': ''
+    '઼': ''
+    '।': '.'
+    "‍": ''# Used for joining
+
+
+    # digits
+
+    '૦': '0'
+    '૧': '1'
+    '૨': '2'
+    '૩': '3'
+    '૪': '4'
+    '૫': '5'
+    '૬': '6'
+    '૭': '7'
+    '૮': '8'
+    '૯': '9'