interscript-maps 2.0.5

data/maps/alalc-kan-Kana-Latn-2011.imp

@@ -0,0 +1,58 @@
+metadata {
+  authority_id: alalc
+  id: 2011
+  language: iso-639-2:kan
+  source_script: Kana
+  destination_script: Latn
+  name: Kannada Romanization, 2011
+  url: http://catdir.loc.gov/catdir/cpso/romanization/kannada.pdf
+  creation_date: 2011
+  description: |
+    ALA-LC Romanization table for Kannada
+
+  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 superscript sign (◌್).
+
+    - |
+      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 {
+  test "ಕರ್ಣಾಟಕ", "karṇāṭaka"
+  test "ಬೆಂಗಳೂರು", "beṅgaḷūru"
+  test "ಭಾರತದಲ್ಲಿ ಗಾಳಿ ಕಲುಷಿತವಾಗಿದೆ: ಹವಾಮಾನ ಬದಲಾವಣೆ ಸಮರ್ಥನೆಗೆ ಭಾರತವನ್ನು ಟೀಕಿಸಿದ ಟ್ರಂಪ್", "bhāratadalli gāḷi kaluṣitavāgide: havāmāna badalāvaṇe samarthanege bhāratavannu ṭīkisida ṭraṃp"
+  test "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ ಅಂತಿಮ ಚರ್ಚೆ: ಭಾರತದ ವಿರುದ್ಧ ಟ್ರಂಪ್ ಆರೋಪವೇನು?!", "amerika adhyakṣīya cunāvaṇe aṃtima carce: bhāratada viruddha ṭraṃp ārōpavēnu?!"
+  test "ಹೇಗಿದೆ ಅಮೆರಿಕನ್‌ ಚುನಾವಣ ಕಣ?", "hēgide amerikan cunāvaṇa kaṇa?"
+  test "ಫ್ರೀಜರ್ ನಲ್ಲಿಟ್ಟ ನೂಡಲ್ಸ್ ತಿಂದು ಒಂದೇ ಕುಟುಂಬದ ೯ ಮಂದಿ ಸಾವು: ೩ ಮಕ್ಕಳು ಅಪಾಯದಿಂದ ಪಾರು", "phrījar nalliṭṭa nūḍals tiṃdu oṃdē kuṭuṃbada 9 maṃdi sāvu: 3 makkaḷu apāyadinda pāru"
+  test "ಉಡುಪಿಯಲ್ಲಿ ಪ್ರಪ್ರಥಮ ಬಾರಿಗೆ ಪ್ರಾರಂಭವಾಗಿರುವ ದೇಶಿ ಉತ್ಪನ್ನಗಳ ಮಳಿಗೆ", "uḍupiyalli praprathama bārige prāraṃbhavāgiruva dēśi utpannagaḷa maḷige"
+  test "ಚಿಕ್ಕಮಗಳೂರು : ಪುಷ್ಪ ಸಮರ್ಪಣೆ ವೇಳೆ ಮಗಳನ್ನ ನೆನೆದು ಕಣ್ಣೀರಿಟ್ಟ ಮೃತ ಪೇದೆ ತಾಯಿ", "cikkamagaḷūru : puṣpa samarpaṇe vēḷe magaḷanna nenedu kaṇṇīriṭṭa mṛta pēde tāyi"
+  test "ಸಮಂಗಳೂರು: ಡ್ರಗ್ಸ್ ಜಾಗೃತಿ ಬರಹದಿಂದ ಗಮನಸೆಳೆಯುತ್ತಿದೆ ಸಿಟಿ ಬಸ್", "samaṅgaḷūru: ḍrags jāgṛti barahadinda gamanaseḷeyuttide siṭi bas"
+  test "ಪುರಸಭೆ, ಪಪಂ ಅಧ್ಯಕ್ಷ-ಉಪಾಧ್ಯಕ್ಷ ಚುನಾವಣೆಗೆ ಹೈಕೋರ್ಟ್‌ ಅಸ್ತು", "purasabhe, papaṃ adhyakṣa-upādhyakṣa cunāvaṇege haikōrṭ astu"
+  test "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ ಅಂತಿಮ ಚರ್ಚೆ: ಭಾರತದ ವಿರುದ್ಧ ಟ್ರಂಪ್ ಆರೋಪವೇನು?", "amerika adhyakṣīya cunāvaṇe aṃtima carce: bhāratada viruddha ṭraṃp ārōpavēnu?"
+  test "ಮನೆ ಕುಸಿದು ತಂದೆ ಮತ್ತು ಮಗ ಸಾವು, ಇನ್ನಿಬ್ಬರಿಗೆ ಗಾಯ: ಸ್ಥಳಕ್ಕೆ ಶಾಸಕರ ಭೇಟಿ", "mane kusidu taṃde mattu maga sāvu, innibbarige gāya: sthaḷakke śāsakara bhēṭi"
+}
+
+dependency "alalc-kan-Kana-Latn-1997", as: kanalatn
+
+stage {
+
+  run map.kanalatn.stage.main
+
+}
+

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

@@ -0,0 +1,109 @@
+metadata {
+  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 {
+  test "ႼႨႢႬႨ", "CIGNI"
+  test "ⴜⴈⴂⴌⴈ", "cigni"
+  test "ႱႭႪႭႫႭႬ", "SOLOMON"
+  test "ⴑⴍⴊⴍⴋⴍⴌ", "solomon"
+  test "ႠႡႰႠჀႠႫ", "ABRAHAM"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u10a0", "A" # Ⴀ
+    sub "\u10a1", "B" # Ⴁ
+    sub "\u10a2", "G" # Ⴂ
+    sub "\u10a3", "D" # Ⴃ
+    sub "\u10a4", "E" # Ⴄ
+    sub "\u10a5", "V" # Ⴅ
+    sub "\u10a6", "Z" # Ⴆ
+    sub "\u10a7", "Tʻ" # Ⴇ
+    sub "\u10a8", "I" # Ⴈ
+    sub "\u10a9", "K" # Ⴉ
+    sub "\u10aa", "L" # Ⴊ
+    sub "\u10ab", "M" # Ⴋ
+    sub "\u10ac", "N" # Ⴌ
+    sub "\u10ad", "O" # Ⴍ
+    sub "\u10ae", "P" # Ⴎ
+    sub "\u10af", "Ž" # Ⴏ
+    sub "\u10b0", "R" # Ⴐ
+    sub "\u10b1", "S" # Ⴑ
+    sub "\u10b2", "T" # Ⴒ
+    sub "\u10b3", "U" # Ⴓ
+    sub "\u10b4", "Pʻ" # Ⴔ
+    sub "\u10b5", "Kʻ" # Ⴕ
+    sub "\u10b6", "Ġ" # Ⴖ
+    sub "\u10b7", "Q" # Ⴗ
+    sub "\u10b8", "Š" # Ⴘ
+    sub "\u10b9", "Čʻ" # Ⴙ
+    sub "\u10ba", "Cʻ" # Ⴚ
+    sub "\u10bb", "Ż" # Ⴛ
+    sub "\u10bc", "C" # Ⴜ
+    sub "\u10bd", "Č" # Ⴝ
+    sub "\u10be", "X" # Ⴞ
+    sub "\u10bf", "J" # Ⴟ
+    sub "\u10c0", "H" # Ⴠ
+    sub "\u10c1", "Ē" # Ⴡ
+    sub "\u10c2", "Y" # Ⴢ
+    sub "\u10c3", "W" # Ⴣ
+    sub "\u10c4", "X̣" # Ⴤ
+    sub "\u10c5", "Ō" # Ⴥ
+    
+    sub "\u2d00", "a" # ⴀ
+    sub "\u2d01", "b" # ⴁ
+    sub "\u2d02", "g" # ⴂ
+    sub "\u2d03", "d" # ⴃ
+    sub "\u2d04", "e" # ⴄ
+    sub "\u2d05", "v" # ⴅ
+    sub "\u2d06", "z" # ⴆ
+    sub "\u2d07", "tʻ" # ⴇ
+    sub "\u2d08", "i" # ⴈ
+    sub "\u2d09", "k" # ⴉ
+    sub "\u2d0a", "l" # ⴊ
+    sub "\u2d0b", "m" # ⴋ
+    sub "\u2d0c", "n" # ⴌ
+    sub "\u2d0d", "o" # ⴍ
+    sub "\u2d0e", "p" # ⴎ
+    sub "\u2d0f", "ž" # ⴏ
+    sub "\u2d10", "r" # ⴐ
+    sub "\u2d11", "s" # ⴑ
+    sub "\u2d12", "t" # ⴒ
+    sub "\u2d13", "u" # ⴓ
+    sub "\u2d14", "pʻ" # ⴔ
+    sub "\u2d15", "kʻ" # ⴕ
+    sub "\u2d16", "ġ" # ⴖ
+    sub "\u2d17", "q" # ⴗ
+    sub "\u2d18", "š" # ⴘ
+    sub "\u2d19", "čʻ" # ⴙ
+    sub "\u2d1a", "cʻ" # ⴚ
+    sub "\u2d1b", "ż" # ⴛ
+    sub "\u2d1c", "c" # ⴜ
+    sub "\u2d1d", "č" # ⴝ
+    sub "\u2d1e", "x" # ⴞ
+    sub "\u2d1f", "j" # ⴟ
+    sub "\u2d20", "h" # ⴠ
+    sub "\u2d21", "ē" # ⴡ
+    sub "\u2d22", "y" # ⴢ
+    sub "\u2d23", "w" # ⴣ
+    sub "\u2d24", "x̣" # ⴤ
+    sub "\u2d25", "ō" # ⴥ
+  }
+
+}
+

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

@@ -0,0 +1,104 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:kat
+  source_script: Geor
+  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 older Khutsuri and the modern Mkhedruli alphabets.
+    There are no upper case letters in Mkhedruli.
+  
+  notes:
+}
+
+tests {
+  test "ხაოფსე", "xaopʻse"
+  test "ჭლოუ", "člou"
+  test "ჩოხულდი", "čʻoxuldi"
+  test "ქვემო ლინდა", "kʻvemo linda"
+  test "ტამკვაჩ იგვავერა", "tamkvačʻ igvavera"
+  test "სვანეთი", "svanetʻi"
+  test "საცხვარისი", "sacʻxvarisi"
+  test "მუხრან-თელეთი", "muxran-tʻeletʻi"
+  test "მუცდი", "mucʻdi"
+  test "ლეჩხუმი", "lečʻxumi"
+  test "ვერხნაია მწარა", "verxnaia mcara"
+  test "ეგრისის ქედი", "egrisis kʻedi"
+  test "დოჩარიფშა", "dočʻaripʻša"
+  test "ბოლოკო", "boloko"
+  test "აჭანდარა", "ačandara"
+  test "აუალიცა", "aualicʻa"
+  test "აკალამრა", "akalamra"
+  test "ლასილი", "lasili"
+  test "გუბაზეული", "gubazeuli"
+  test "ბაყაყი", "baqaqi"
+  test "ძროხა", "żroxa"
+  test "ჰაერი", "haeri"
+  test "ჟოლო", "žolo"
+  test "ჯართი", "jartʻi"
+  test "ღრმაღელე", "ġrmaġele"
+}
+
+stage {
+
+  # CHARACTERS
+  parallel {
+    sub "\u10d0", "a" # ა
+    sub "\u10d1", "b" # ბ
+    sub "\u10d2", "g" # გ
+    sub "\u10d3", "d" # დ
+    sub "\u10d4", "e" # ე
+    sub "\u10d5", "v" # ვ
+    sub "\u10d6", "z" # ზ
+    
+    sub "\u10f1", "ē" # ჱ
+    
+    sub "\u10d7", "tʻ" # თ
+    sub "\u10d8", "i" # ი
+    sub "\u10d9", "k" # კ
+    sub "\u10da", "l" # ლ
+    sub "\u10db", "m" # მ
+    sub "\u10dc", "n" # ნ
+    
+    sub "\u10f2", "y" # ჲ
+    
+    sub "\u10dd", "o" # ო
+    sub "\u10de", "p" # პ
+    sub "\u10df", "ž" # ჟ
+    sub "\u10e0", "r" # რ
+    sub "\u10e1", "s" # ს
+    sub "\u10e2", "t" # ტ
+    
+    sub "\u10f3", "w" # ჳ
+    
+    sub "\u10e3", "u" # უ
+    sub "\u10e4", "pʻ" # ფ
+    sub "\u10e5", "kʻ" # ქ
+    sub "\u10e6", "ġ" # ღ
+    sub "\u10e7", "q" # ყ
+    sub "\u10e8", "š" # შ
+    sub "\u10e9", "čʻ" # ჩ
+    sub "\u10ea", "cʻ" # ც
+    sub "\u10eb", "ż" # ძ
+    sub "\u10ec", "c" # წ
+    sub "\u10ed", "č" # ჭ
+    sub "\u10ee", "x" # ხ
+    
+    sub "\u10f4", "x̣" # ჴ
+    
+    sub "\u10ef", "j" # ჯ
+    sub "\u10f0", "h" # ჰ
+    
+    sub "\u10f5", "ō" # ჵ
+    
+    sub "\u10f6", "f" # ჶ
+    sub "\u10f7", "ĕ" # ჷ
+    sub "\u10f8", "ʻ" # ჸ
+  }
+
+}
+

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

@@ -0,0 +1,68 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:kor
+  source_script: Hang
+  destination_script: Latn
+  name: ALA-LC Romanization Table -- Korean (1997)
+  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 {
+  test "은하-리", "Ŭnha-ri"
+  test "은중-리", "Ŭnjung-ni"
+  test "은장-령", "Ŭnjang-nyŏng"
+  test "은혜-동", "Ŭnhye-dong"
+  test "은호-리", "Ŭnho-ri"
+  test "은행정", "Ŭnhaengjŏng"
+  test "은행-동", "Ŭnhaeng-dong"
+  test "은행-촌", "Ŭnhaeng-ch’on"
+  test "원수", "Wŏnsu"
+  test "원소리-고개", "Wŏnsori-gogae"
+  test "원소참", "Wŏnsoch’am"
+  test "원소-리", "Wŏnso-ri"
+  test "원신-리", "Wŏnsil-li"
+  test "난곡", "Nan’gok"
+  test "난산-리", "Nansal-li"
+  test "난직", "Nanjik"
+  test "영곡", "Yŏnggok"
+  test "윗두밀", "Wittumil"
+  test "윗도심이", "Wittosimi"
+  test "둔지", "Tunji"
+  test "서승", "Sŏsŭng"
+  # - source: 신촌
+  #   expected: "Sinch’on"
+  test "비암덕", "Piamdŏk"
+  test "바위안", "Pawian"
+  test "오송평", "Osongp’yŏng"
+  test "그물목", "Kŭmulmok"
+  test "구원정", "Kuwŏnjŏng"
+  test "일하", "Irha"
+  test "황우", "Hwangu"
+  test "자작보", "Chajakpo"
+  # - source: 비파1-동
+  #   expected: "Pip’a Il-tong"
+  test "문암 오-동", "Munam O-dong"
+}
+
+dependency "var-kor-Hang-Latn-mr-1939", as: hanglatn
+
+stage {
+
+  run map.hanglatn.stage.main
+  compose
+  title_case
+}

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

@@ -0,0 +1,260 @@
+metadata {
+  authority_id: alalc
+  id: 1997
+  language: iso-639-2:mal
+  source_script: Mlym
+  destination_script: Latn
+  name: Malayalam Romanization, 1997
+  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 {
+  test "ചൈനയ്ക്കെതിരെ ലഡാക്കിൽ സദാസജ്ജം; യുഎസിൽനിന്ന് ൭൨,൫൦൦ സിഗ്–൧൬ റൈഫിൾ", "cainayŭkŭketire lad̂ākŭkil sadāsajŭjaṃ; yuesilninŭnŭ 72,500 sigŭ–16 ṟaiphiḷ"
+  test "സർഗഭൂമിക’യ്ക്കില്ല; ലളിതച്ചേച്ചി അങ്ങനെ പറഞ്ഞിട്ടുണ്ടാവില്ല: ആർഎൽവി രാമകൃഷ്ണൻ", "sargabhūmika’yŭkŭkilŭla; laḷitacŭcēcŭci aṅŭṅane paṟañŭñiṭŭṭuṇŭṭāvilŭla: ārelvi rāmakṛṣŭṇan"
+  test "സ്വർണക്കടത്ത്‌: ഫൈസൽ ഫരീദും റബിന്‍സും ദുബായിൽ അറസ്റ്റിലായെന്ന്‌ എന്‍ഐഎ", "sŭvarṇakŭkaṭatŭtŭ: phaisal pharīduṃ ṟabinŭsuṃ dubāyil aṟasŭṟŭṟilāyenŭnŭ enŭaie"
+  test "വരുമോ ചൈനയുടെ വാക്സീൻ?; ആഗോള ഉപയോഗത്തിന് ഡബ്ല്യുഎച്ച്ഒയുമായി ചർച്ച", "varumō cainayuṭe vākŭsīn?; āgōḷa upayōgatŭtinŭ d̂abŭlŭyuecŭcŭoyumāyi carcŭca"
+  test "കുട്ടികളുടെ മാനസിക പിരിമുറുക്കം മാറ്റാൻ പരിശീലനം; ക്ലാസുമായി പോക്സോ പ്രതി", "kuṭŭṭikaḷuṭe mānasika pirimuṟukŭkaṃ māṟŭṟān pariśīlanaṃ; kŭlāsumāyi pōkŭsō pŭrati"
+  test "ആദ്യം അമിത് ഷാ, ഇപ്പോൾ മോദി; ബിജെപിയെ പുണരാൻ ജഗൻ; ആന്ധ്രയിലെ കരുനീക്കങ്ങൾ", "ādŭyaṃ amitŭ ṣā, ipŭpōḷ mōdi; bijepiye puṇarān jagan; ānŭdhŭrayile karunīkŭkaṅŭṅaḷ"
+  test "ലഹരിമരുന്ന് കേസ്: ബിനീഷ് കോടിയേരിയെ ഇഡി 6 മണിക്കൂർ ചോദ്യം ചെയ്തു", "laharimarunŭnŭ kēsŭ: binīṣŭ kōṭiyēriye id̂i 6 maṇikŭkūr cōdŭyaṃ ceyŭtu"
+  test "ഈന്തപ്പഴം വിതരണം ചെയ്തത് ശിവശങ്കര്‍ പറഞ്ഞതു പ്രകാരം: ടി.വി അനുപമയുടെ മൊഴി", "īnŭtapŭpaḻaṃ vitaraṇaṃ ceyŭtatŭ śivaśaṅŭkarŭ paṟañŭñatu pŭrakāraṃ: ṭi.vi anupamayuṭe moḻi"
+  test "൫൦൦൦ മണിക്കൂർ കാത്തിരിക്കാൻ തയാറെന്ന് രാഹുൽ: ഒടുവിൽ വഴങ്ങി ഹരിയാന", "5000 maṇikŭkūr kātŭtirikŭkān tayāṟenŭnŭ rāhul: oṭuvil vaḻaṅŭṅi hariyāna"
+  test "കാരണം ഷോര്‍ട്ട്‌സര്‍ക്യൂട്ടല്ല; കത്തിയത് ഫയല്‍ മാത്രം, സാനിറ്റൈസര്‍ ഉള്‍പ്പെടെ കത്തിയില്ല", "kāraṇaṃ ṣōrŭṭŭṭŭsarŭkŭyūṭŭṭalŭla; katŭtiyatŭ phayalŭ mātŭraṃ, sāniṟŭṟaisarŭ uḷŭpŭpeṭe katŭtiyilŭla"
+  test "വിമൺ സയൻറിസ്റ്റ്സ് സ്കീം", "vimaṇ sayanṟisŭṟŭṟŭsŭ sŭkīṃ"
+}
+
+aliases {
+  def_alias mlym_chars_1, any("\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d4d\u0d43\u0d44\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0D62\u0D63\u0d4d")
+}
+
+stage {
+
+  # RULES
+  # note[5]
+    sub "\u0DCA", "ṅ", after: any("കഖഗഘങ")
+    sub "\u0DCA", "ñ", after: any("ചഛജഝഞ")
+    sub "\u0DCA", "ṇ", after: any("ടഠഡഢണ")
+    sub "\u0DCA", "n", after: any("തഥദധന")
+
+  # note[3(a,b)]
+    sub "ക", "k", after: mlym_chars_1
+    sub "ഖ", "kh", after: mlym_chars_1
+    sub "ഗ", "g", after: mlym_chars_1
+    sub "ഘ", "gh", after: mlym_chars_1
+    sub "ങ", "ṅ", after: mlym_chars_1
+    sub "ച", "c", after: mlym_chars_1
+    sub "ഛ", "ch", after: mlym_chars_1
+    sub "ജ", "j", after: mlym_chars_1
+    sub "ഝ", "jh", after: mlym_chars_1
+    sub "ഞ", "ñ", after: mlym_chars_1
+    sub "ട", "ṭ", after: mlym_chars_1
+    sub "ഠ", "ṭh", after: mlym_chars_1
+    sub "ഡ", "d̂", after: mlym_chars_1
+    sub "ഢ", "ḍh", after: mlym_chars_1
+    sub "ണ", "ṇ", after: mlym_chars_1
+    sub "ത", "t", after: mlym_chars_1
+    sub "ഥ", "th", after: mlym_chars_1
+    sub "ദ", "d", after: mlym_chars_1
+    sub "ധ", "dh", after: mlym_chars_1
+    sub "ന", "n", after: mlym_chars_1
+    sub "പ", "p", after: mlym_chars_1
+    sub "ഫ", "ph", after: mlym_chars_1
+    sub "ബ", "b", after: mlym_chars_1
+    sub "ഭ", "bh", after: mlym_chars_1
+    sub "മ", "m", after: mlym_chars_1
+    sub "യ", "y", after: mlym_chars_1
+    sub "ര", "r", after: mlym_chars_1
+    sub "റ", "ṟ", after: mlym_chars_1
+    sub "ല", "l", after: mlym_chars_1
+    sub "ള", "ḷ", after: mlym_chars_1
+    sub "ഴ", "ḻ", after: mlym_chars_1
+    sub "വ", "v", after: mlym_chars_1
+    sub "ശ", "ś", after: mlym_chars_1
+    sub "ഷ", "ṣ", after: mlym_chars_1
+    sub "സ", "s", after: mlym_chars_1
+    sub "ഩ", "ṉ", after: mlym_chars_1
+    sub "ഹ", "h", after: mlym_chars_1
+
+
+
+
+  # CHARACTERS
+  parallel {
+
+    sub "അ", "a"
+    sub "ആ", "ā"
+    sub "ഇ", "i"
+    sub "ഈ", "ī"
+    sub "ഉ", "u"
+    sub "ഊ", "ū"
+    sub "ഋ", "ṛ"
+    sub "ൠ", "ṝ"
+    sub "ഌ", "ḷ"
+    sub "ൡ", "ḹ"
+
+    sub "എ", "e"
+    sub "ഏ", "ē"
+    sub "ഐ", "ai"
+
+    sub "ഒ", "o"
+    sub "ഓ", "ō"
+    sub "ഔ", "au"
+
+    # Consonants
+    # Gutturals
+    sub "ക", "ka"
+    sub "ഖ", "kha"
+    sub "ഗ", "ga"
+    sub "ഘ", "gha"
+    sub "ങ", "ṅa"
+
+    # Palatals
+    sub "ച", "ca"
+    sub "ഛ", "cha"
+    sub "ജ", "ja"
+    sub "ഝ", "jha"
+    sub "ഞ", "ña"
+
+    # Cerebrals
+    sub "ട", "ṭa"
+    sub "ഠ", "ṭha"
+    sub "ഡ", "d̂a"
+    sub "ഢ", "ḍha"
+    sub "ണ", "ṇa"
+
+    # Dentals
+    sub "ത", "ta"
+    sub "ഥ", "tha"
+    sub "ദ", "da"
+    sub "ധ", "dha"
+    sub "ന", "na"
+
+    # Labials
+    sub "പ", "pa"
+    sub "ഫ", "pha"
+    sub "ബ", "ba"
+    sub "ഭ", "bha"
+    sub "മ", "ma"
+
+    # Semivowels
+    sub "യ", "ya"
+    sub "ര", "ra"
+    sub "റ", "ṟa"
+    sub "റ്റ", "ṯṯa" # (see Note 4)
+    sub "ല", "la"
+    sub "ള", "ḷa"
+    sub "ഴ", "ḻa"
+    # Sibilants
+    sub "വ", "va"
+    sub "ശ", "śa"
+    sub "ഷ", "ṣa"
+    sub "സ", "sa"
+    sub "ഩ", "ṉa"
+
+
+    # Aspirate
+    sub "ഹ", "ha"
+
+    # Bisarga
+    sub "ഃ", "ḥ"
+
+    # Anusvāra
+    sub "ം", "ṃ"
+
+
+    # Abagraha
+    sub "ഽ", ":’" # (apostrophe)
+
+    # Medials # Needed for connecting constants
+
+    sub "ാ", "ā"
+    sub "ി", "i"
+    sub "ീ", "ī"
+    sub "ു", "u"
+    sub "ൂ", "ū"
+    sub "്", "ŭ"
+    sub "ൃ", "ṛ"
+    sub "ൄ", "ṝ"
+    sub "\u0D62", "ḷ"
+    sub "\u0D63", "ḹ"
+    sub "െ", "e"
+    sub "േ", "ē"
+    sub "ൈ", "ai"
+    sub "ൊ", "o"
+    sub "ോ", "ō"
+    sub "ൌ", "au"
+
+    sub "्", ""
+    sub "़", ""
+    sub "ൗ", ""
+    sub "‍", "" # no need for zero with joiner
+    sub "‌", "" # no need for zero with non joiner
+
+
+    # numbers
+    sub "൦", "0"
+    sub "൧", "1"
+    sub "൨", "2"
+    sub "൩", "3"
+    sub "൪", "4"
+    sub "൫", "5"
+    sub "൬", "6"
+    sub "൭", "7"
+    sub "൮", "8"
+    sub "൯", "9"
+    sub "൰", "10"
+    sub "൱", "100"
+    sub "൲", "1000"
+
+
+    # Note 3(c)
+
+    sub "ൿ", "k"
+    sub "ൺ", "ṇ"
+    sub "ൻ", "n"
+    sub "ൽ", "l"
+    sub "ൾ", "ḷ"
+    sub "ർ", "r"
+    sub "ഉ്", "ū"
+
+    # extended and ancient forms
+
+    sub "ഺ", "ṯa"
+  }
+
+  compose
+}
+