interscript 0.1.2 → 0.1.7

data/maps/alalc-hin-Deva-Latn-2011.yaml

@@ -0,0 +1,47 @@
+---
+authority_id: alalc
+id: 2011
+language: iso-639-2:hin
+source_script: Deva
+destination_script: Latn
+name: Hindi Romanization, 2011
+url: https://www.loc.gov/catdir/cpso/romanization/hindi.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Hindi
+
+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 sign ( ◌् ) 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.
+
+  - Anunāsika before guttural, palatal, cerebral, and dental occlusives is transliterated n̐. Before
+    labials, sibilants, semivowels, aspirates, vowels, and in final position it is transliterated m̐.
+
+  - When doubled, avagraha is transliterated by two apostrophes ( ’’ ).
+
+tests:
+  - source: "इस चुनौतीपूर्ण समय में 'वर्क फ्रॉम होम’ सामान्य बन चुका है"
+    expected: "isa caunaăutaīpaūraṇa samaya maeṃ 'varaka pharaôma haoma’ saāmaānaya bana caukaā haai"
+
+map:
+
+  inherit: "alalc-hin-Deva-Latn-1997"

data/maps/alalc-kat-Geok-Latn-1997.yaml

@@ -0,0 +1,111 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:kat
+source_script: Geok
+destination_script: Latn
+name: ALA-LC Georgian System (1997)
+url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+creation_date: 1997
+confirmation_date: 1997
+description: |
+  Values are shown for the Khutsuri alphabet.
+
+notes:
+
+tests:
+
+  - source: ႼႨႢႬႨ
+    expected: CIGNI
+
+  - source: ⴜⴈⴂⴌⴈ
+    expected: cigni
+
+  - source: ႱႭႪႭႫႭႬ
+    expected: SOLOMON
+
+  - source: ⴑⴍⴊⴍⴋⴍⴌ
+    expected: solomon
+
+  - source: ႠႡႰႠჀႠႫ
+    expected: ABRAHAM
+
+map:
+  characters:
+    '\u10a0' : 'A' # Ⴀ
+    '\u10a1' : 'B' # Ⴁ
+    '\u10a2' : 'G' # Ⴂ
+    '\u10a3' : 'D' # Ⴃ
+    '\u10a4' : 'E' # Ⴄ
+    '\u10a5' : 'V' # Ⴅ
+    '\u10a6' : 'Z' # Ⴆ
+    '\u10a7' : 'Tʻ' # Ⴇ
+    '\u10a8' : 'I' # Ⴈ
+    '\u10a9' : 'K' # Ⴉ
+    '\u10aa' : 'L' # Ⴊ
+    '\u10ab' : 'M' # Ⴋ
+    '\u10ac' : 'N' # Ⴌ
+    '\u10ad' : 'O' # Ⴍ
+    '\u10ae' : 'P' # Ⴎ
+    '\u10af' : 'Ž' # Ⴏ
+    '\u10b0' : 'R' # Ⴐ
+    '\u10b1' : 'S' # Ⴑ
+    '\u10b2' : 'T' # Ⴒ
+    '\u10b3' : 'U' # Ⴓ
+    '\u10b4' : 'Pʻ' # Ⴔ
+    '\u10b5' : 'Kʻ' # Ⴕ
+    '\u10b6' : 'Ġ' # Ⴖ
+    '\u10b7' : 'Q' # Ⴗ
+    '\u10b8' : 'Š' # Ⴘ
+    '\u10b9' : 'Čʻ' # Ⴙ
+    '\u10ba' : 'Cʻ' # Ⴚ
+    '\u10bb' : 'Ż' # Ⴛ
+    '\u10bc' : 'C' # Ⴜ
+    '\u10bd' : 'Č' # Ⴝ
+    '\u10be' : 'X' # Ⴞ
+    '\u10bf' : 'J' # Ⴟ
+    '\u10c0' : 'H' # Ⴠ
+    '\u10c1' : 'Ē' # Ⴡ
+    '\u10c2' : 'Y' # Ⴢ
+    '\u10c3' : 'W' # Ⴣ
+    '\u10c4' : 'X̣' # Ⴤ
+    '\u10c5' : 'Ō' # Ⴥ
+
+    '\u2d00' : 'a' # ⴀ
+    '\u2d01' : 'b' # ⴁ
+    '\u2d02' : 'g' # ⴂ
+    '\u2d03' : 'd' # ⴃ
+    '\u2d04' : 'e' # ⴄ
+    '\u2d05' : 'v' # ⴅ
+    '\u2d06' : 'z' # ⴆ
+    '\u2d07' : 'tʻ' # ⴇ
+    '\u2d08' : 'i' # ⴈ
+    '\u2d09' : 'k' # ⴉ
+    '\u2d0a' : 'l' # ⴊ
+    '\u2d0b' : 'm' # ⴋ
+    '\u2d0c' : 'n' # ⴌ
+    '\u2d0d' : 'o' # ⴍ
+    '\u2d0e' : 'p' # ⴎ
+    '\u2d0f' : 'ž' # ⴏ
+    '\u2d10' : 'r' # ⴐ
+    '\u2d11' : 's' # ⴑ
+    '\u2d12' : 't' # ⴒ
+    '\u2d13' : 'u' # ⴓ
+    '\u2d14' : 'pʻ' # ⴔ
+    '\u2d15' : 'kʻ' # ⴕ
+    '\u2d16' : 'ġ' # ⴖ
+    '\u2d17' : 'q' # ⴗ
+    '\u2d18' : 'š' # ⴘ
+    '\u2d19' : 'čʻ' # ⴙ
+    '\u2d1a' : 'cʻ' # ⴚ
+    '\u2d1b' : 'ż' # ⴛ
+    '\u2d1c' : 'c' # ⴜ
+    '\u2d1d' : 'č' # ⴝ
+    '\u2d1e' : 'x' # ⴞ
+    '\u2d1f' : 'j' # ⴟ
+    '\u2d20' : 'h' # ⴠ
+    '\u2d21' : 'ē' # ⴡ
+    '\u2d22' : 'y' # ⴢ
+    '\u2d23' : 'w' # ⴣ
+    '\u2d24' : 'x̣' # ⴤ
+    '\u2d25' : 'ō' # ⴥ

data/maps/alalc-kat-Geor-Latn-1997.yaml

@@ -0,0 +1,150 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:kat
+source_script: Geor
+destination_script: Latn
+name: ALA-LC Georgian System (1997)
+alias:
+  ogc11122:
+    code: kat_Geor2Latn_ALA_1997
+    description: Georgian ALA-Library of Congress 1997 System
+url: https://www.loc.gov/catdir/cpso/romanization/georgian.pdf
+creation_date: 1997
+confirmation_date: 1997
+description: |
+  Values are shown for the older Khutsuri and the modern Mkhedruli alphabets.
+  There are no upper case letters in Mkhedruli.
+
+notes:
+
+tests:
+
+  - source: ხაოფსე
+    expected: xaopʻse
+
+  - source: ჭლოუ
+    expected: člou
+
+  - source: ჩოხულდი
+    expected: čʻoxuldi
+
+  - source: ქვემო ლინდა
+    expected: kʻvemo linda
+
+  - source: ტამკვაჩ იგვავერა
+    expected: tamkvačʻ igvavera
+
+  - source: სვანეთი
+    expected: svanetʻi
+
+  - source: საცხვარისი
+    expected: sacʻxvarisi
+
+  - source: მუხრან-თელეთი
+    expected: muxran-tʻeletʻi
+
+  - source: მუცდი
+    expected: mucʻdi
+
+  - source: ლეჩხუმი
+    expected: lečʻxumi
+
+  - source: ვერხნაია მწარა
+    expected: verxnaia mcara
+
+  - source: ეგრისის ქედი
+    expected: egrisis kʻedi
+
+  - source: დოჩარიფშა
+    expected: dočʻaripʻša
+
+  - source: ბოლოკო
+    expected: boloko
+
+  - source: აჭანდარა
+    expected: ačandara
+
+  - source: აუალიცა
+    expected: aualicʻa
+
+  - source: აკალამრა
+    expected: akalamra
+
+  - source: ლასილი
+    expected: lasili
+
+  - source: გუბაზეული
+    expected: gubazeuli
+
+  - source: ბაყაყი
+    expected: baqaqi
+
+  - source: ძროხა
+    expected: żroxa
+
+  - source: ჰაერი
+    expected: haeri
+
+  - source: ჟოლო
+    expected: žolo
+
+  - source: ჯართი
+    expected: jartʻi
+
+  - source: ღრმაღელე
+    expected: ġrmaġele
+
+map:
+  characters:
+    '\u10d0' : 'a' # ა
+    '\u10d1' : 'b' # ბ
+    '\u10d2' : 'g' # გ
+    '\u10d3' : 'd' # დ
+    '\u10d4' : 'e' # ე
+    '\u10d5' : 'v' # ვ
+    '\u10d6' : 'z' # ზ
+
+    '\u10f1' : 'ē' # ჱ
+
+    '\u10d7' : 'tʻ' # თ
+    '\u10d8' : 'i' # ი
+    '\u10d9' : 'k' # კ
+    '\u10da' : 'l' # ლ
+    '\u10db' : 'm' # მ
+    '\u10dc' : 'n' # ნ
+
+    '\u10f2' : 'y' # ჲ
+
+    '\u10dd' : 'o' # ო
+    '\u10de' : 'p' # პ
+    '\u10df' : 'ž' # ჟ
+    '\u10e0' : 'r' # რ
+    '\u10e1' : 's' # ს
+    '\u10e2' : 't' # ტ
+
+    '\u10f3' : 'w' # ჳ
+
+    '\u10e3' : 'u' # უ
+    '\u10e4' : 'pʻ' # ფ
+    '\u10e5' : 'kʻ' # ქ
+    '\u10e6' : 'ġ' # ღ
+    '\u10e7' : 'q' # ყ
+    '\u10e8' : 'š' # შ
+    '\u10e9' : 'čʻ' # ჩ
+    '\u10ea' : 'cʻ' # ც
+    '\u10eb' : 'ż' # ძ
+    '\u10ec' : 'c' # წ
+    '\u10ed' : 'č' # ჭ
+    '\u10ee' : 'x' # ხ
+
+    '\u10f4' : 'x̣' # ჴ
+
+    '\u10ef' : 'j' # ჯ
+    '\u10f0' : 'h' # ჰ
+
+    '\u10f5' : 'ō' # ჵ
+
+    '\u10f6' : 'f' # ჶ
+    '\u10f7' : 'ĕ' # ჷ
+    '\u10f8' : 'ʻ' # ჸ

data/maps/alalc-kor-Hang-Latn-1997.yaml

@@ -0,0 +1,98 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:kor
+source_script: Hang
+destination_script: Latn
+name: ALA-LC Romanization Table -- Korean (1997)
+alias:
+  ogc11122:
+    code: kor_Hang2Latn_ALA_1997
+    description: Korean ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/korean.pdf
+creation_date: 1997
+adoption_date:
+description:
+  "1. General Practice
+The Library of Congress will continue to follow the McCune-Reischauer system
+to romanize Korean with the exceptions noted in this document. See:
+Romanization of the Korean Language: Based upon its Phonetic Structure by
+G.M. McCune and E.O. Reischauer ([S.l.: s.n., 1939?), reprinted from the
+Transactions of the Korea Branch of the Royal Asiatic Society. Full text of the
+original document is available online from the National Library of Australia Web
+site: http://www.nla.gov.au/librariesaustralia/cjk/download/ras_1939.pdf"
+
+notes:
+
+
+tests:
+  - source: 은하-리
+    expected: "Ŭnha-ri"
+  - source: 은중-리
+    expected: "Ŭnjung-ni"
+  - source: 은장-령
+    expected: "Ŭnjang-nyŏng"
+  - source: 은혜-동
+    expected: "Ŭnhye-dong"
+  - source: 은호-리
+    expected: "Ŭnho-ri"
+  - source: 은행정
+    expected: "Ŭnhaengjŏng"
+  - source: 은행-동
+    expected: "Ŭnhaeng-dong"
+  - source: 은행-촌
+    expected: "Ŭnhaeng-ch’on"
+  - source: 원수
+    expected: "Wŏnsu"
+  - source: 원소리-고개
+    expected: "Wŏnsori-gogae"
+  - source: 원소참
+    expected: "Wŏnsoch’am"
+  - source: 원소-리
+    expected: "Wŏnso-ri"
+  - source: 원신-리
+    expected: "Wŏnsil-li"
+  - source: 난곡
+    expected: "Nan’gok"
+  - source: 난산-리
+    expected: "Nansal-li"
+  - source: 난직
+    expected: "Nanjik"
+  - source: 영곡
+    expected: "Yŏnggok"
+  - source: 윗두밀
+    expected: "Wittumil"
+  - source: 윗도심이
+    expected: "Wittosimi"
+  - source: 둔지
+    expected: "Tunji"
+  - source: 서승
+    expected: "Sŏsŭng"
+  # - source: 신촌
+  #   expected: "Sinch’on"
+  - source: 비암덕
+    expected: "Piamdŏk"
+  - source: 바위안
+    expected: "Pawian"
+  - source: 오송평
+    expected: "Osongp’yŏng"
+  - source: 그물목
+    expected: "Kŭmulmok"
+  - source: 구원정
+    expected: "Kuwŏnjŏng"
+  - source: 일하
+    expected: "Irha"
+  - source: 황우
+    expected: "Hwangu"
+  - source: 자작보
+    expected: "Chajakpo"
+  # - source: 비파1-동
+  #   expected: "Pip’a Il-tong"
+  - source: 문암 오-동
+    expected: "Munam O-dong"
+
+map:
+  character_separator: ""
+  word_separator: " "
+  title_case: True
+  inherit: "var-kor-Hang-Latn-mr-1939"

data/maps/alalc-mal-Mlym-Latn-1997.yaml

@@ -0,0 +1,303 @@
+---
+authority_id: alalc
+id: 1997
+language: iso-639-2:mal
+source_script: Mlym
+destination_script: Latn
+name: Malayalam Romanization, 1997
+alias:
+  ogc11122:
+    code: mal_Mlym2Latn_ALA_1997
+    description: Malayalam ALA-Library of Congress 1997 System
+url: http://catdir.loc.gov/catdir/cpso/romanization/malayala.pdf
+creation_date: 1997
+description: |
+  ALA-LC Romanization table for Malayalam
+
+
+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.
+
+  - When  ് is used in combination with the vowel u (ഉ്), the combination is also transliterated ȧ.
+
+  - |
+    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
+    b) when the absence of any vowel is indicated by the superscript sign  ് (also used for the vowel ȧ); and
+    c) when the following modified consonantal forms are used:
+      ൿ  k
+      ൻ  n
+      ൾ  ḷ
+      ൺ  ṇ
+      ൽ  l
+      ർ   r
+  - When റ റ appears as a subscript in a cluster (റ്റ), it is transliterated ta.
+
+  - |
+    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.
+
+tests:
+  - source: "ചൈനയ്ക്കെതിരെ ലഡാക്കിൽ സദാസജ്ജം; യുഎസിൽനിന്ന് ൭൨,൫൦൦ സിഗ്–൧൬ റൈഫിൾ"
+    expected: "cainayŭkŭketire lad̂ākŭkil sadāsajŭjaṃ; yuesilninŭnŭ 72,500 sigŭ–16 ṟaiphiḷ"
+  - source: "സർഗഭൂമിക’യ്ക്കില്ല; ലളിതച്ചേച്ചി അങ്ങനെ പറഞ്ഞിട്ടുണ്ടാവില്ല: ആർഎൽവി രാമകൃഷ്ണൻ"
+    expected: "sargabhūmika’yŭkŭkilŭla; laḷitacŭcēcŭci aṅŭṅane paṟañŭñiṭŭṭuṇŭṭāvilŭla: ārelvi rāmakṛṣŭṇan"
+  - source: "സ്വർണക്കടത്ത്‌: ഫൈസൽ ഫരീദും റബിന്‍സും ദുബായിൽ അറസ്റ്റിലായെന്ന്‌ എന്‍ഐഎ"
+    expected: "sŭvarṇakŭkaṭatŭtŭ: phaisal pharīduṃ ṟabinŭsuṃ dubāyil aṟasŭṟŭṟilāyenŭnŭ enŭaie"
+  - source: "വരുമോ ചൈനയുടെ വാക്സീൻ?; ആഗോള ഉപയോഗത്തിന് ഡബ്ല്യുഎച്ച്ഒയുമായി ചർച്ച"
+    expected: "varumō cainayuṭe vākŭsīn?; āgōḷa upayōgatŭtinŭ d̂abŭlŭyuecŭcŭoyumāyi carcŭca"
+  - source: "കുട്ടികളുടെ മാനസിക പിരിമുറുക്കം മാറ്റാൻ പരിശീലനം; ക്ലാസുമായി പോക്സോ പ്രതി"
+    expected: "kuṭŭṭikaḷuṭe mānasika pirimuṟukŭkaṃ māṟŭṟān pariśīlanaṃ; kŭlāsumāyi pōkŭsō pŭrati"
+  - source: "ആദ്യം അമിത് ഷാ, ഇപ്പോൾ മോദി; ബിജെപിയെ പുണരാൻ ജഗൻ; ആന്ധ്രയിലെ കരുനീക്കങ്ങൾ"
+    expected: "ādŭyaṃ amitŭ ṣā, ipŭpōḷ mōdi; bijepiye puṇarān jagan; ānŭdhŭrayile karunīkŭkaṅŭṅaḷ"
+  - source: "ലഹരിമരുന്ന് കേസ്: ബിനീഷ് കോടിയേരിയെ ഇഡി 6 മണിക്കൂർ ചോദ്യം ചെയ്തു"
+    expected: "laharimarunŭnŭ kēsŭ: binīṣŭ kōṭiyēriye id̂i 6 maṇikŭkūr cōdŭyaṃ ceyŭtu"
+  - source: "ഈന്തപ്പഴം വിതരണം ചെയ്തത് ശിവശങ്കര്‍ പറഞ്ഞതു പ്രകാരം: ടി.വി അനുപമയുടെ മൊഴി"
+    expected: "īnŭtapŭpaḻaṃ vitaraṇaṃ ceyŭtatŭ śivaśaṅŭkarŭ paṟañŭñatu pŭrakāraṃ: ṭi.vi anupamayuṭe moḻi"
+  - source: "൫൦൦൦ മണിക്കൂർ കാത്തിരിക്കാൻ തയാറെന്ന് രാഹുൽ: ഒടുവിൽ വഴങ്ങി ഹരിയാന"
+    expected: "5000 maṇikŭkūr kātŭtirikŭkān tayāṟenŭnŭ rāhul: oṭuvil vaḻaṅŭṅi hariyāna"
+  - source: "കാരണം ഷോര്‍ട്ട്‌സര്‍ക്യൂട്ടല്ല; കത്തിയത് ഫയല്‍ മാത്രം, സാനിറ്റൈസര്‍ ഉള്‍പ്പെടെ കത്തിയില്ല"
+    expected: "kāraṇaṃ ṣōrŭṭŭṭŭsarŭkŭyūṭŭṭalŭla; katŭtiyatŭ phayalŭ mātŭraṃ, sāniṟŭṟaisarŭ uḷŭpŭpeṭe katŭtiyilŭla"
+  - source: "വിമൺ സയൻറിസ്റ്റ്സ് സ്കീം"
+    expected: "vimaṇ sayanṟisŭṟŭṟŭsŭ sŭkīṃ"
+
+map:
+
+  rules:
+    # note[5]
+    - pattern: \u0DCA(?=[കഖഗഘങ])
+      result: ṅ
+    - pattern: \u0DCA(?=[ചഛജഝഞ])
+      result: ñ
+    - pattern: \u0DCA(?=[ടഠഡഢണ])
+      result: ṇ
+    - pattern: \u0DCA(?=[തഥദധന])
+      result: n
+
+    # note[3(a,b)]
+    - pattern: (['ക']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'k'
+    - pattern: (['ഖ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'kh'
+    - pattern: (['ഗ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'g'
+    - pattern: (['ഘ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'gh'
+    - pattern: (['ങ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṅ'
+    - pattern: (['ച']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'c'
+    - pattern: (['ഛ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ch'
+    - pattern: (['ജ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'j'
+    - pattern: (['ഝ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'jh'
+    - pattern: (['ഞ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ñ'
+    - pattern: (['ട']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṭ'
+    - pattern: (['ഠ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṭh'
+    - pattern: (['ഡ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'd̂'
+    - pattern: (['ഢ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḍh'
+    - pattern: (['ണ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṇ'
+    - pattern: (['ത']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 't'
+    - pattern: (['ഥ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'th'
+    - pattern: (['ദ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'd'
+    - pattern: (['ധ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'dh'
+    - pattern: (['ന']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'n'
+    - pattern: (['പ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'p'
+    - pattern: (['ഫ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ph'
+    - pattern: (['ബ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'b'
+    - pattern: (['ഭ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'bh'
+    - pattern: (['മ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'm'
+    - pattern: (['യ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'y'
+    - pattern: (['ര']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'r'
+    - pattern: (['റ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṟ'
+    - pattern: (['ല']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'l'
+    - pattern: (['ള']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḷ'
+    - pattern: (['ഴ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ḻ'
+    - pattern: (['വ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'v'
+    - pattern: (['ശ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ś'
+    - pattern: (['ഷ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṣ'
+    - pattern: (['സ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 's'
+    - pattern: (['ഩ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'ṉ'
+    - pattern: (['ഹ']=?)(?=[\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d])
+      result: 'h'
+    
+
+
+  characters:
+
+    'അ': 'a'
+    'ആ': 'ā'
+    'ഇ': 'i'
+    'ഈ': 'ī'
+    'ഉ': 'u'
+    'ഊ': 'ū'
+    'ഋ': "ṛ"
+    'ൠ': "ṝ"
+    'ഌ': "ḷ"
+    'ൡ': "ḹ"
+
+    'എ': 'e'
+    'ഏ': 'ē'
+    'ഐ': 'ai'
+
+    'ഒ': 'o'
+    'ഓ': 'ō'
+    'ഔ': 'au'
+
+    # Consonants
+    # Gutturals
+    'ക': 'ka'
+    'ഖ': 'kha'
+    'ഗ': 'ga'
+    'ഘ': 'gha'
+    'ങ': 'ṅa'
+
+    # Palatals
+    'ച': 'ca'
+    'ഛ': 'cha'
+    'ജ': 'ja'
+    'ഝ': 'jha'
+    'ഞ': 'ña'
+
+    # Cerebrals
+    'ട':  'ṭa'
+    'ഠ':  'ṭha'
+    'ഡ': 'd̂a'
+    'ഢ':  'ḍha'
+    'ണ':  'ṇa'
+
+    # Dentals
+    'ത': 'ta'
+    'ഥ': 'tha'
+    'ദ': 'da'
+    'ധ': 'dha'
+    'ന': 'na'
+
+    # Labials
+    'പ': 'pa'
+    'ഫ': 'pha'
+    'ബ': 'ba'
+    'ഭ': 'bha'
+    'മ': 'ma'
+
+    # Semivowels
+    'യ': 'ya'
+    'ര': 'ra'
+    'റ': 'ṟa'
+    'റ്റ': 'ṯṯa' # (see Note 4)
+    'ല': 'la'
+    'ള': 'ḷa'
+    'ഴ': 'ḻa'
+    # Sibilants
+    'വ': 'va'
+    'ശ': 'śa'
+    'ഷ': 'ṣa'
+    'സ': 'sa'
+    'ഩ': 'ṉa'
+
+
+    # Aspirate
+    'ഹ': 'ha'
+
+    # Bisarga
+    'ഃ': 'ḥ'
+
+    # Anusvāra
+    'ം': 'ṃ'
+
+
+    # Abagraha
+    'ഽ': ':’' # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    'ാ': 'ā'
+    'ി': 'i'
+    'ീ': 'ī'
+    'ു': 'u'
+    'ൂ': 'ū'
+    '്': 'ŭ'
+    'ൃ': "ṛ"
+    'ൄ': "ṝ"
+    '\u0D62': "ḷ"
+    '\u0D63': "ḹ"
+    'െ': "e"
+    'േ': "ē"
+    'ൈ': "ai"
+    'ൊ': 'o'
+    'ോ': 'ō'
+    'ൌ': 'au'
+
+    '्': ''
+    '़': ''
+    'ൗ': ''
+    "‍": '' # no need for zero with joiner
+    "‌": '' # no need for zero with non joiner
+
+
+    # numbers
+    '൦': '0'
+    '൧': '1'
+    '൨': '2'
+    '൩': '3'
+    '൪': '4'
+    '൫': '5'
+    '൬': '6'
+    '൭': '7'
+    '൮': '8'
+    '൯': '9'
+    '൰': '10'
+    '൱': '100'
+    '൲': '1000'
+
+
+    # Note 3(c)
+
+    'ൿ': 'k'
+    'ൺ': 'ṇ'
+    'ൻ': 'n'
+    'ൽ': 'l'
+    'ൾ': 'ḷ'
+    'ർ': 'r'
+    'ഉ്': 'ū'
+
+    # extended and ancient forms
+
+    'ഺ': 'ṯa'