interscript 0.1.3 → 0.1.9

data/maps/alalc-ben-Beng-Latn-2017.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 2017
-language: ben
+language: iso-639-2:ben
 source_script: Beng
 destination_script: Latn
 name: Bengali Romanization, 2017

data/maps/alalc-bul-Cyrl-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: bul
+language: iso-639-2:bul
 source_script: Cyrl
 destination_script: Latn
 name: ALA-LC Romanization Table -- Bulgarian (1997)
+alias:
+  ogc11122:
+    code: bul_Cyrl2Latn_ALA_1997
+    description: Bulgarian ALA-Library of Congress Bulgarian 1997 System
 url: http://www.rechtertie.nl/databases/judd/downloads/Bulgarian.pdf
 creation_date: 1997
 

data/maps/alalc-div-Thaa-Latn-1997.yaml

@@ -0,0 +1,211 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:div
+source_script: Thaa
+destination_script: Latn
+name: ALA-Library of Congress Divehi Romanization 1997 System
+alias:
+  ogc11122:
+    code: div_Thaa2Latn_ALA_1997
+    description: Divehi ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/divehi.pdf
+creation_date: 1997
+description: |
+  ALA-Library of Congress Divehi Romanization 1997 System
+
+notes:
+
+  - |
+    Romanize ށް as ḫ when it doubles the following consonant or is used as a glottal stop.
+      aḫvana	އަށްވަނަ
+      maśaḫ	މަށަށް
+  - |
+    When used in medial position without ް (sukūn), romanize ނ as ṁ.
+      aṁga	އަނގަ
+      haṁdu	ހަނދު
+  - |
+    Romanization of އ.
+    (a) When used in the initial position with any vowel sign, do not romanize.
+      ata	އަތަ
+      idu	އިދު
+      umuru	އުމުރު
+      egahugi	އެގަހުގި
+    (b) When used in the medial position with any vowel sign, romanize as ’.
+      ha’hūnu	ހައިހޫނު
+      fa’isa	ފައިސަ
+      k’īn	ކްއީން
+    (c) When a consonant follows އް in medial position, double it in romanization.
+      cappalu	ޗައްޕަލު
+      appacci	އައްޕައްޗި
+    (d) When used in final position with ް (sukūn), romanize as h.
+      boh	ބޮއް
+      biheh	ބިހެއް
+  - |
+    Romanize ތް followed by another ތ as  t̤ .
+     at̤teri   އަތްތެރި
+  - |
+    Only the vowel forms that appear at the beginning of a syllable are listed.
+    When the vowels follow a consonant, އ is not used and the vowel signs are added to the consonant forms.
+    Do not distinguish between the two in romanization.
+  - |
+    ް (called sukūn) generally indicates omission of an inherent vowel associated with a consonant.
+    For its other uses, see Notes 1, 3, and 4.
+
+tests:
+  - source: "މަށަށް"
+    expected: "maśaḫ"
+  - source: "އަނގަ"
+    expected: "aṁga"
+  - source: "ހަނދު"
+    expected: "haṁdu"
+  - source: "އަތަ"
+    expected: "ata"
+  - source: "އިދު"
+    expected: "idu"
+  - source: "އުމުރު"
+    expected: "umuru"
+  - source: "އެގަހުގި"
+    expected: "egahugi"
+  - source: "ފައިސަ"
+    expected: "faʼisa"
+  - source: "ބޮއް"
+    expected: "boh"
+  - source: "ބިހެއް"
+    expected: "biheh"
+  - source: "އަތްތެރި"
+    expected: "at̤teri"
+  - source: "ޗައްޕަލު"
+    expected: "cappalu"
+  - source: "އައްޕައްޗި"
+    expected: "appacci"
+
+map:
+
+  rules:
+    # note[1]
+    - pattern: (?<=)\u0781\u07b0(?=\b)
+      result: "ḫ"
+    # note[2]
+    - pattern: (?<!\b)\u0782\u07b0(?<!\b)  # medial position with sukun
+      result: "n"
+    - pattern: (?<!\b)\u0782(?<!\b)  # medial position without sukun
+      result: "ṁ"
+    # note[3(a)]
+    - pattern: \b(\u0787=?)(?=[\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af]) # initial position with any vowel sign
+      result:  ''
+    # note[3(c)]  a consonant follows އް in medial position
+    - pattern: (?<!\b)\u0787\u07b0(?=[ހ])
+      result: "h"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ށ])
+      result: "ś"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ނ])
+      result: "n"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ރ])
+      result: "r"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ބ])
+      result: "b"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޅ])
+      result: "ḷ"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ކ])
+      result: "k"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ވ])
+      result: "v"
+    - pattern: (?<!\b)\u0787\u07b0(?=[މ])
+      result: "m"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ފ])
+      result: "f"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ދ])
+      result: "d"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ތ])
+      result: "t"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ލ])
+      result: "l"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ގ])
+      result: "g"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޏ])
+      result: "ñ"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ސ])
+      result: "s"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޑ])
+      result: "ḍ"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޖ])
+      result: "j"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޗ])
+      result: "c"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޒ])
+      result: "z"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޓ])
+      result: "ṭ"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޕ])
+      result: "p"
+    - pattern: (?<!\b)\u0787\u07b0(?=[ޔ])
+      result: "y"
+    # note[3(d)]
+    - pattern: (?<!\b)\u0787\u07b0(?=\b) # final position with sukun
+      result:  'h'
+    # note[3(b)]
+    - pattern: (?<!\b)\u0787(?=[\u07a6\u07a7\u07a8\u07a9\u07aa\u07ab\u07ac\u07ad\u07ae\u07af]) # medial position with any vowel sign
+      result:  'ʼ'
+    # note[4]
+    - pattern: \u078c\u07b0\u078c
+      result:  't̤t'
+
+
+  characters:
+
+  # Vowels
+
+    "\u07a6" : "a"
+    "\u07a7" : "ā"
+    "\u07a8" : "i"
+    "\u07a9" : "ī"
+    "\u07aa" : "u"
+    "\u07ab" : "ū"
+    "\u07ac" : "e"
+    "\u07ad" : "ē"
+    "\u07ae" : "o"
+    "\u07af" : "ō"
+    "\u07B0" : "" # omit (see Note 6)
+
+
+   # Consonants
+    "ހ": "h"
+    "ށ": "ś" # or ḫ (see Note 1)
+    "ނ": "n" # see Note 2
+    "ރ": "r"
+    "ބ": "b"
+    "ޅ": "ḷ"
+    "ކ": "k"
+    "އ": "" # ʼ or h or omit (see Note 3)
+    "ވ": "v"
+    "މ": "m"
+    "ފ": "f"
+    "ދ": "d"
+    "ތ": "t" # see Note 4
+    "ލ": "l"
+    "ގ": "g"
+    "ޏ": "ñ"
+    "ސ": "s"
+    "ޑ": "ḍ"
+    "ޖ": "j"
+    "ޗ": "c"
+    "ޒ": "z"
+    "ޓ": "ṭ"
+    "ޕ": "p"
+    "ޔ": "y"
+
+    # Divehi Equivalents to Represent Arabic Letters
+
+    "ޘ": "th"
+    "ޙ": "ḥ"
+    "ޚ": "kh"
+    "ޛ": "dh"
+    "ޝ": "sh"
+    "ޞ": "ṣ"
+    "ޟ": "ḏ"
+    "ޠ": "t̤"
+    "ޡ": "ẓ"
+    "ޢ": "ʻ"
+    "ޣ": "gh"
+    "ޤ": "q"

data/maps/alalc-ell-Grek-Latn-1997.yaml

@@ -1,10 +1,14 @@
 ---
 authority_id: alalc
 id: 1997
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: Greek Romanization, 1997
+alias:
+  ogc11122:
+    code: ell_Grek2Latn_ALA_1997
+    description: Greek ALA-Library of Congress 1997 System
 url: http://catdir.loc.gov/catdir/cpso/romanization/greek.pdf
 creation_date: 1997
 description: |
@@ -15,7 +19,7 @@ note:
   - This table presupposes monotonic accentuation; rough breathings are accordingly not addressed.
   - The diphthong definition for upsilon is taken from the 2010 version
   - Generalised gramma digraph rule to capitals
-    
+
 tests:
 
   - source: |
@@ -25,7 +29,7 @@ tests:
 
     expected: |
         Ena prama monon me parakinēse ki emena na grapsō oti toutēn tēn patrida tēn echomen oloi mazi, kai sophoi ki amatheis kai plousioi kai phtōchoi kai politikoi kai stratiōtikoi kai oi pleon mikroteroi anthrōpoi; osoi agōnistēkamen, analogōs o katheis, echomen na zēsomen edō. To loipon doulepsamen oloi mazi, na tēn phylamen ki oloi mazi kai na mēn legei oute o dynatos «egō» oute o adynatos. Xerete pote na legei o katheis «egō»? Otan agōnistei monos tou kai phkiasei ē chalasei, na legei «egō»; otan omōs agōnizontai polloi kai phkianoun, tote na lene «emeis». Eimaste eis to «emeis» ki ochi eis to «egō». Kai eis to exēs na mathomen gnōsē, an thelomen na phkiasomen chōrion, na zēsomen oloi mazi.
-       
+
         Giannēs Makrygiannēs.
 
 
@@ -622,4 +626,3 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
-

data/maps/alalc-ell-Grek-Latn-2010.yaml

@@ -1,7 +1,7 @@
 ---
 authority_id: alalc
 id: 2010
-language: ell
+language: iso-639-2:ell
 source_script: Grek
 destination_script: Latn
 name: Greek Romanization, 2010
@@ -14,7 +14,7 @@ note:
   - Applies to texts after 1453 (Modern Greek)
   - This table presupposes monotonic accentuation; rough breathings are accordingly not addressed.
   - Generalised gramma digraph rule to capitals
-    
+
 tests:
 
   - source: |
@@ -24,9 +24,8 @@ tests:
 
     expected: |
         Ena prama monon me parakinēse ki emena na grapsō oti toutēn tēn patrida tēn echomen oloi mazi, kai sophoi ki amatheis kai plousioi kai phtōchoi kai politikoi kai stratiōtikoi kai oi pleon mikroteroi anthrōpoi; osoi agōnistēkamen, analogōs o katheis, echomen na zēsomen edō. To loipon doulepsamen oloi mazi, na tēn phylamen ki oloi mazi kai na mēn legei oute o dynatos «egō» oute o adynatos. Xerete pote na legei o katheis «egō»? Otan agōnistei monos tou kai phkiasei ē chalasei, na legei «egō»; otan omōs agōnizontai polloi kai phkianoun, tote na lene «emeis». Eimaste eis to «emeis» ki ochi eis to «egō». Kai eis to exēs na mathomen gnōsē, an thelomen na phkiasomen chōrion, na zēsomen oloi mazi.
-       
-        Giannēs Makrygiannēs.
 
+        Giannēs Makrygiannēs.
 
   - source: ΑΘΗΝΑ
     expected: ATHĒNA
@@ -625,4 +624,3 @@ map:
 
     "\u0387": ";"   # ·
     "\u00B7": ";"   # ·
-

data/maps/alalc-guj-Gujr-Latn-1997.yaml

@@ -0,0 +1,266 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:guj
+source_script: Gujr
+destination_script: Latn
+name: Gujarati Romanization, 1997
+alias:
+  ogc11122:
+    code: guj_Gujr2Latn_ALA_1997
+    description: Gujarati ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/gujarati.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Gujarati
+
+notes:
+
+  - Only the vowel forms that appear at the beginning of a syllable are listed; the forms used for
+    vowels following a consonant can be found in grammars; no distinction between the two is
+    made in transliteration.
+
+  - |
+    The vowel a is implicit after all consonants and consonant clusters and is supplied in
+    transliteration, with the following exceptions:
+    a) when another vowel is indicated by its appropriate sign and
+    b) when the absence of any vowel is indicated by the subscript symbol ( ્ ) called halanta or
+    virāma.
+
+  - |
+    Exception: Anusvāra is transliterated by:
+    a) ṅ before gutturals,
+    b) ñ before palatals,
+    c) ṇ before cerebrals,
+    d) n before dentals, and
+    e) m before labials.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "અમિત શાહનો કોરોના રિપોર્ટ ૨ ઓગસ્ટે પોઝિટિવ આવ્યો હતો, ત્યારથી તેમનું સ્વાસ્થ્ય સારું નથી"
+    expected: "amita śāhanȏ kȏrȏnā ripȏrṭa 2 ȏgasṭȇ pȏjhiṭiva āvyȏ hatȏ, tyārathī tȇmanuṃ svāsthya sāruṃ nathī"
+  - source: "મેદાંતા હોસ્પિટલમાં તેમનો ઇલાજ ચાલી રહ્યો હતો"
+    expected: "mȇdāntā hȏspiṭalamāṃ tȇmanȏ ilāja cālī rahyȏ hatȏ"
+  - source: "ભારતના વિશ્વનાથન આનંદે શેનયાનમાં પહેલો ફિડે શતરંજ વિશ્વ કપ જીત્યો"
+    expected: "bhāratanā viśvanāthana ānandȇ śȇnayānamāṃ pahȇlȏ phiḍȇ śatarañja viśva kapa jītyȏ"
+  - source: "ભારતીય વડા પ્રધાન જવાહરલાલ નેહરુએ ૪૦ લાખ હિન્દુઓ અને મુસલમાનોના પારસ્પરિક સ્થાનાંતરણનું સૂચન આપ્યું"
+    expected: "bhāratīya vaḍā pradhāna javāharalāla nȇharuȇ 40 lākha hinduȏ anȇ musalamānȏnā pārasparika sthānāntaraṇanuṃ sūcana āpyuṃ"
+  - source: "લિબિયાના એલ અજિજિયામાં ધરતી પર સૌથી વધુ તાપમાન નોંધાયું. એ વખતે છાયામાં નોંધવામાં આવેલું તાપમાન ૫૮ ડિગ્રી સેલ્સિયસ હતું."
+    expected: "libiyānā ȇla ajijiyāmāṃ dharatī para sauthī vadhu tāpamāna nȏndhāyuṃ. ȇ vakhatȇ chāyāmāṃ nȏndhavāmāṃ āvȇluṃ tāpamāna 58 ḍigrī sȇlsiyasa hatuṃ."
+  - source: "પ્રથમ વિશ્વયુદ્ધઃ જર્મની અને ફ્રાન્સ વચ્ચે એસ્નેની લડાઈ શરૂ થઈ હતી"
+    expected: "prathama viśvayuddhaḥ jarmanī anȇ phrānsa vaccȇ ȇsnȇnī laḍāī śarū thaī hatī"
+  - source: "એન્ગ્લો-મિસ્ત્ર યુદ્ધઃ તેલ અલ કેબિરનું યુદ્ધ લડવામાં આવ્યું હતું."
+    expected: "ȇnglȏ-mistra yuddhaḥ tȇla ala kȇbiranuṃ yuddha laḍavāmāṃ āvyuṃ hatuṃ."
+  - source: "પુરાવા ન હતા, એ જ કારણે કેસ ચાલ્યો નહીં, પણ તેમને નજરકેદ રાખવામાં આવ્યા"
+    expected: "purāvā na hatā, ȇ ja kāraṇȇ kȇsa cālyȏ nahīṃ, paṇa tȇmanȇ najarakȇda rākhavāmāṃ āvyā"
+  - source: "સરદાર પટેલે નક્કી કર્યું હતું કે કાશ્મીર ભારતનો હિસ્સો બનશે; ૯૧ વર્ષ પહેલાં લાહોર જેલમાં ભૂખહડતાળ દરમિયાન શહીદ થયા હતા જતીન દાસ"
+    expected: "saradāra paṭȇlȇ nakkī karyuṃ hatuṃ kȇ kāśmīra bhāratanȏ hissȏ banaśȇ; 91 varsha pahȇlāṃ lāhȏra jȇlamāṃ bhūkhahaḍatāḷa daramiyāna śahīda thayā hatā jatīna dāsa"
+  - source: "કોરોના પ્રોટોકોલ વચ્ચે આજે મેડિકલ પ્રવેશ પરીક્ષા લેવાશેઃ એન્ટ્રી ટચ ફ્રી રહેશે, એડમિટ કાર્ડ બાર કોડથી ચેક થશે"
+    expected: "kȏrȏnā prȏṭȏkȏla vaccȇ ājȇ mȇḍikala pravȇśa parīkshā lȇvāśȇḥ ȇnṭrī ṭaca phrī rahȇśȇ, ȇḍamiṭa kārḍa bāra kȏḍathī cȇka thaśȇ"
+  - source: "અલ્ ક઼`ઇદ્ માં હવામાન"
+    expected: "al ka`id māṃ havāmāna"
+  - source: "મંત્રાલય તથા ખ઼.ય ના વિ૨ષ્ઠ અધિકા૨ીઓ ઉપસ્થિત ૨હ્યા હતા"
+    expected: "mantrālaya tathā kha.ya nā vi2shṭha adhikā2īȏ upasthita 2hyā hatā"
+
+
+map:
+
+  rules:
+    # note 3
+    - pattern: \u0A82(?=[કખગઘઙ])
+      result: ṅ
+    - pattern: \u0A82(?=[ચછજઝઞ])
+      result: ñ
+    - pattern: \u0A82(?=[ટઠડઢણ])
+      result: ṇ
+    - pattern: \u0A82(?=[તથદધન])
+      result: n
+    - pattern: \u0A82(?=[પફબભમ])
+      result: m
+
+    # note[2(a,b)]
+    - pattern: ([ક]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'k'    
+    - pattern: ([ખ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'kh'   
+    - pattern: ([ગ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'g'    
+    - pattern: ([ઘ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'gh'   
+    - pattern: ([ઙ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ṅ'   
+    - pattern: ([ચ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'c'    
+    - pattern: ([છ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ch'   
+    - pattern: ([જ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'j'    
+    - pattern: ([ઝ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'jh'   
+    - pattern: ([ઞ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ñ'   
+    - pattern: ([ટ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṭ'  
+    - pattern: ([ઠ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṭh' 
+    - pattern: ([ડ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ḍ'  
+    - pattern: ([ઢ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ḍh' 
+    - pattern: ([ણ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result:  'ṇ'  
+    - pattern: ([ત]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 't'    
+    - pattern: ([થ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'th'   
+    - pattern: ([દ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'd'    
+    - pattern: ([ધ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'dh'   
+    - pattern: ([ન]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'n'    
+    - pattern: ([પ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'p'    
+    - pattern: ([ફ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ph'   
+    - pattern: ([બ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'b'    
+    - pattern: ([ભ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'bh'   
+    - pattern: ([મ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'm'    
+    - pattern: ([ય]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'y'    
+    - pattern: ([ર]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'r'    
+    - pattern: ([લ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'l'    
+    - pattern: ([ળ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ḷ'    
+    - pattern: ([વ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'v'    
+    - pattern: ([શ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'ś'   
+    - pattern: ([ષ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'sh'   
+    - pattern: ([સ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 's'    
+    - pattern: ([હ]=?)(?=[\u0abe\u0abf\u0ac0\u0ac1\u0ac2\u0ac3\u0ac5\u0ac7\u0ac8\u0ac9\u0acb\u0acc\u0acd])  
+      result: 'h'    
+
+
+  characters:
+
+    'અ': 'a'
+    'આ': 'ā'
+    'ઇ': 'i'
+    'ઈ': 'ī'
+    'ઉ': 'u'
+    'ઊ': 'ū'
+    'ઋ': 'ṛ'
+
+    'ઍ': 'e'
+    'એ': 'ȇ'
+    'ઐ': 'ai'
+
+    'ઑ': 'o'
+    'ઓ': 'ȏ'
+    'ઔ': 'au'
+
+    # II. Consonants (see Note 2)
+    # Gutturals
+    'ક': 'ka'
+    'ખ': 'kha'
+    'ગ': 'ga'
+    'ઘ': 'gha'
+    'ઙ': 'ṅa'
+
+    # Palatals
+    'ચ': 'ca'
+    'છ': 'cha'
+    'જ': 'ja'
+    'ઝ': 'jha'
+    'ઞ': 'ña'
+
+    # Cerebrals
+    'ટ':  'ṭa'
+    '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': 'sha'
+    'સ': 'sa'
+
+
+    # Aspirate
+    'હ': 'ha'
+
+    # Bisarga
+    'ઃ': 'ḥ'
+
+    # Anusvāra
+    'ં': 'ṃ'
+
+    # Abagraha  (see Note 4)
+    'ઽ': '’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    'ા': 'ā'
+    'િ': 'i'
+    'ી': 'ī'
+    'ુ': 'u'
+    'ૂ': 'ū'
+    'ૃ': 'ṛ'
+    'ૅ': 'e'
+    'ે': 'ȇ'
+    'ૈ': 'ai'
+    'ૉ': 'o'
+    'ો': 'ȏ'
+    'ૌ': 'au'
+
+    # digits
+
+    '૦': '0'
+    '૧': '1'
+    '૨': '2'
+    '૩': '3'
+    '૪': '4'
+    '૫': '5'
+    '૬': '6'
+    '૭': '7'
+    '૮': '8'
+    '૯': '9'
+
+
+
+    '્': ''
+    '઼': ''
+    '।': '.'
+    '\u09CD': '' # Used for joining
+    "‍": ''# Used for joining