interscript-maps 2.4.2 → 2.5.0

data/maps/un-kan-Kana-Latn-2016.isc

@@ -0,0 +1,354 @@
+system "UN:kan-Kana:Latn:2016" {
+
+metadata {
+  authority_id un
+  id 2016
+  language iso-639-2:kan
+  source_script Kana
+  destination_script Latn
+  name Romanization of Kannada -- UNGEGN 4.0
+  url https://www.eki.ee/wgrs/rom1_kn.pdf
+  creation_date 1972
+  confirmation_date 2016
+  description {    The United Nations recommended system was approved in 1972 (II/11) and amended in 1977
+    (III/12), based on a report prepared by D. N. Sharma. The tables and their corrections were
+    published in volume II of the conference reports
+
+    There is no evidence of the use of the system either in India or in international cartographic
+    products.
+
+    Kannada uses an alphasyllabic script whereby each character represents a syllable rather than
+    one sound. Vowels and diphthongs are marked in two ways: as independent characters (used
+    syllable-initially) and in an abbreviated form, to denote vowels after consonants. The
+    romanization table is unambiguous. The system is mostly reversible but there may exist some
+    ambiguities in the romanization of vowels (independent vs. abbreviated characters) and
+    consonants (combinations with subscript consonants vs. character sequences).
+  }
+
+  notes {
+    note "      While most consonants have a diacritic in the upper right corner of the character (like ಕ),\n      some do not, e.g. ಖ kha, ಜ ja, ನ na, ಬ ba, ಲ la."
+    note "      Combinations with r as the first component are written by adding a special symbol after the\n      second consonant: ರ್ಗ rga."
+  }
+}
+
+tests {
+   "ಕರ್ಣಾಟಕ" ->  "karṇāṭaka"
+   "ಬೆಂಗಳೂರು" ->  "bĕṁgaḷūru"
+   "ಮಹಾರಾಷ್ಟ್ರದ ಯಾವುದೇ ಪ್ರಕರಣದ ತನಿಖೆಗೆ ಇನ್ನು ಸಿಬಿಐ ಪಡೆಯಬೇಕು ಅನುಮತಿ" ->  "mahārāṣhṭrada yāvude prakaraṇada tanikhĕgĕ innu sibiai paḍĕyabeku anumati"
+   "ಹರಕು ಬಾಯಿ: ಈಶ್ವರಪ್ಪಗೆ ಶಾಸಕ ಯತ್ನಾಳ ತಿರುಗೇಟು" ->  "haraku bāyi: īshvarappagĕ shāsaka yatnāḷa tirugeṭu"
+   "ಹಾಥರಸ್‌ ಪ್ರಕರಣ: ೨೯ರಂದು ರಾಷ್ಟ್ರವ್ಯಾಪಿ ಪ್ರತಿಭಟನೆಗೆ ಮಹಿಳಾ ಸಂಘಟನೆಗಳ ಕರೆ" ->  "hātharas prakaraṇa: 29raṁdu rāṣhṭravyāpi pratibhaṭanĕgĕ mahiḷā saṁghaṭanĕgaḷa karĕ"
+   "ಪೊಲೀಸ್‌ ಮಕ್ಕಳ ಶಾಲೆ ಮುಚ್ಚುವ ಯತ್ನಕ್ಕೆ ಹೊರಟ್ಟಿ ತೀವ್ರ ವಿರೋಧ" ->  "pŏlīs makkaḷa shālĕ muchchuva yatnakkĕ hŏraṭṭi tīvra virodha"
+   "ಅಮೆರಿಕ ಅಧ್ಯಕ್ಷೀಯ ಚುನಾವಣೆ: ಟ್ರಂಪ್‌–ಬೈಡನ್‌ ಅಂತಿಮ ಮುಖಾಮುಖಿಗೆ ವೇದಿಕೆ ಸಿದ್ಧ" ->  "amĕrika adhyakṣhīya chunāvaṇĕ: ṭraṁp–baiḍan aṁtima mukhāmukhigĕ vedikĕ siddha"
+   "ಅಂಜನಾದ್ರಿ ಆಂಜನೇಯನ ದರ್ಶನ ಪಡೆದ ಪವರ್ ಸ್ಟಾರ್ ಪುನೀತ್ ರಾಜ್ ಕುಮಾರ್" ->  "aṁjanādri āṁjaneyana darshana paḍĕda pavar sṭār punīt rāj kumār"
+   "ಇನ್ನು ಹಿಂದೂ ದೇವಸ್ಥಾನದ ಧಾರ್ಮಿಕ ಕಾರ್ಯದಲ್ಲಿ ಭಾಗಿಯಾಗಿದ್ದಕ್ಕೆ ಮೋಯಿದ್ದೀನ್ ಬಾವಾಗೆ ಬೆದರಿಕೆ ಒಡ್ಡಲಾಗಿದೆ" ->  "innu hiṁdū devasthānada dhārmika kāryadalli bhāgiyāgiddakkĕ moyiddīn bāvāgĕ bĕdarikĕ ŏḍḍalāgidĕ"
+   "ಇದು ಮೋದಿ ದೇಶ - ದನ ತಿಂದು ಹೋದ್ರೆ ಹುಷಾರ್ : ದೇಗುಲಕ್ಕೆ ಹೋಗಿದ್ದ ಬಾವಾಗೆ ಬೆದರಿಕೆ" ->  "idu modi desha - dana tiṁdu hodrĕ huṣhār : degulakkĕ hogidda bāvāgĕ bĕdarikĕ"
+
+  # Note: UN card expects this to start with an uppercase letter, but that would break other tests
+   "ಕರ್ನಾಟಕ" ->  "karnāṭaka"
+   "ಬೆಂಗಳೂರು" ->  "bĕṁgaḷūru"
+}
+
+aliases {
+  characters_set1 = any("\u0cbe\u0cbf\u0cc0\u0cc1\u0cc2\u0cc3\u0cc6\u0cc7\u0cc8\u0cca\u0ccb\u0ccc\u0ccd")
+}
+
+stage main {
+
+  # RULES
+  # to cover diacritic and vowel less consonants
+  sub {
+    from "ಕ"
+    to "k"
+    after characters_set1
+  }
+  sub {
+    from "ಖ"
+    to "kh"
+    after characters_set1
+  }
+  sub {
+    from "ಗ"
+    to "g"
+    after characters_set1
+  }
+  sub {
+    from "ಘ"
+    to "gh"
+    after characters_set1
+  }
+  sub {
+    from "ಙ"
+    to "ṅ"
+    after characters_set1
+  }
+  sub {
+    from "ಚ"
+    to "ch"
+    after characters_set1
+  }
+  sub {
+    from "ಛ"
+    to "chh"
+    after characters_set1
+  }
+  sub {
+    from "ಜ"
+    to "j"
+    after characters_set1
+  }
+  sub {
+    from "ಝ"
+    to "jh"
+    after characters_set1
+  }
+  sub {
+    from "ಞ"
+    to "ñ"
+    after characters_set1
+  }
+  sub {
+    from "ಟ"
+    to "ṭ"
+    after characters_set1
+  }
+  sub {
+    from "ಠ"
+    to "ṭh"
+    after characters_set1
+  }
+  sub {
+    from "ಡ"
+    to "ḍ"
+    after characters_set1
+  }
+  sub {
+    from "ಢ"
+    to "ḍh"
+    after characters_set1
+  }
+  sub {
+    from "ಣ"
+    to "ṇ"
+    after characters_set1
+  }
+  sub {
+    from "ತ"
+    to "t"
+    after characters_set1
+  }
+  sub {
+    from "ಥ"
+    to "th"
+    after characters_set1
+  }
+  sub {
+    from "ದ"
+    to "d"
+    after characters_set1
+  }
+  sub {
+    from "ಧ"
+    to "dh"
+    after characters_set1
+  }
+  sub {
+    from "ನ"
+    to "n"
+    after characters_set1
+  }
+  sub {
+    from "ಪ"
+    to "p"
+    after characters_set1
+  }
+  sub {
+    from "ಫ"
+    to "ph"
+    after characters_set1
+  }
+  sub {
+    from "ಬ"
+    to "b"
+    after characters_set1
+  }
+  sub {
+    from "ಭ"
+    to "bh"
+    after characters_set1
+  }
+  sub {
+    from "ಮ"
+    to "m"
+    after characters_set1
+  }
+  sub {
+    from "ಯ"
+    to "y"
+    after characters_set1
+  }
+  sub {
+    from "ರ"
+    to "r"
+    after characters_set1
+  }
+  sub {
+    from "ಲ"
+    to "l"
+    after characters_set1
+  }
+  sub {
+    from "ಳ"
+    to "ḷ"
+    after characters_set1
+  }
+  sub {
+    from "ವ"
+    to "v"
+    after characters_set1
+  }
+  sub {
+    from "ಶ"
+    to "sh"
+    after characters_set1
+  }
+  sub {
+    from "ಷ"
+    to "ṣh"
+    after characters_set1
+  }
+  sub {
+    from "ಸ"
+    to "s"
+    after characters_set1
+  }
+  sub {
+    from "ಹ"
+    to "h"
+    after characters_set1
+  }
+
+
+  # CHARACTERS
+  parallel {
+    sub "ಅ" "a"
+    sub "ಆ" "ā"
+    sub "ಇ" "i"
+    sub "ಈ" "ī"
+    sub "ಉ" "u"
+    sub "ಊ" "ū"
+    sub "ಋ" "ṛ"
+
+    sub "ಎ" "ĕ"
+    sub "ಏ" "e"
+    sub "ಐ" "ai"
+
+    sub "ಒ" "ŏ"
+    sub "ಓ" "o"
+    sub "ಔ" "au"
+
+    # Gutturals
+    sub "ಕ" "ka"
+    sub "ಖ" "kha"
+    sub "ಗ" "ga"
+    sub "ಘ" "gha"
+    sub "ಙ" "ṅa"
+
+    # Palatals
+    sub "ಚ" "cha"
+    sub "ಛ" "chha"
+    sub "ಜ" "ja"
+    sub "ಝ" "jha"
+    sub "ಞ" "ña"
+
+    # Cerebrals
+    sub "ಟ" "ṭa"
+    sub "ಠ" "ṭha"
+    sub "ಡ" "ḍa"
+    sub "ಢ" "ḍha"
+    sub "ಣ" "ṇa"
+
+    # Dentals
+    sub "ತ" "ta"
+    sub "ಥ" "tha"
+    sub "ದ" "da"
+    sub "ಧ" "dha"
+    sub "ನ" "na"
+
+    # Labials
+    sub "ಪ" "pa"
+    sub "ಫ" "pha"
+    sub "ಬ" "ba"
+    sub "ಭ" "bha"
+    sub "ಮ" "ma"
+
+    # Semivowels
+    sub "ಯ" "ya"
+    sub "ರ" "ra"
+    sub "ಲ" "la"
+    sub "ಳ" "ḷa"
+
+
+    sub "ವ" "va"
+
+    # Sibilants
+    sub "ಶ" "sha"
+    sub "ಷ" "ṣha"
+    sub "ಸ" "sa"
+
+
+    # Aspirate
+    sub "ಹ" "ha"
+
+
+    # Bisarga
+    sub "ಃ" "ḥ"
+
+    # Anusvāra
+    sub "ಂ" "ṁ"
+
+    sub "\u0cbc" ""
+
+    # Medials # Needed for connecting constants
+    sub "ಾ" "ā"
+    sub "ಿ" "i"
+    sub "ೀ" "ī"
+    sub "ು" "u"
+    sub "ೂ" "ū"
+    sub "ೃ" "ṛ"
+
+
+    sub "ೆ" "ĕ"
+    sub "ೇ" "e"
+    sub "ೈ" "ai"
+
+
+    sub "ೊ" "ŏ"
+    sub "ೋ" "o"
+    sub "ೌ" "au"
+
+
+    sub "्" ""
+    sub "़" ""
+    sub "್" ""
+    sub "‍" ""
+    sub "‌" ""
+
+
+
+    # Digits
+
+    sub "೦" "0"
+    sub "೧" "1"
+    sub "೨" "2"
+    sub "೩" "3"
+    sub "೪" "4"
+    sub "೫" "5"
+    sub "೬" "6"
+    sub "೭" "7"
+    sub "೮" "8"
+    sub "೯" "9"
+  }
+
+  compose
+}
+}

data/maps/un-mal-Mlym-Latn-1972.isc

@@ -0,0 +1,364 @@
+system "UN:mal-Mlym:Latn:1972" {
+
+metadata {
+  authority_id un
+  id 1972
+  language iso-639-2:mal
+  source_script Mlym
+  destination_script Latn
+  name Romanization of Malayalam -- UNGEGN 4.0
+  url https://www.eki.ee/wgrs/rom1_ml.htm
+  creation_date 1972
+  confirmation_date 2016
+  description {    The United Nations recommended system was approved in 1972 (II/11) and amended in 1977 (III/12),
+    based on a report prepared by D. N. Sharma. The tables and their corrections were published in
+    volume II of the conference reports.
+
+    There is no evidence of the use of the system either in India or in international cartographic products.
+
+    Malayalam (Malayāḷam) uses an alphasyllabic script whereby each character represents a syllable rather
+    than one sound. Vowels and diphthongs are marked in two ways: as independent characters (used syllable-initially)
+    and in an abbreviated form, to denote vowels after consonants. The romanization table is unambiguous but now
+    outdated because since the 1970's a new orthography has been introduced and the use of many character
+    combinations and ligatures has been simplified. Nevertheless the user of the romanization table would have to
+    recognize many ligatures not given in the original table. The system is mostly reversible but there exist some
+    ambiguities in the romanization of vowels (independent vs. abbreviated characters) and
+    consonants (ligatures vs. character sequences), particularly in the case of older orthography.
+  }
+
+  notes {
+    note "      ടു For traditional script forms ഖു khu, മു mu, etc., exceptionally കു ku (ക്കു kku, ങ്കു ṅku), ഗു gu, ഛു chhu, ജു ju, ണു ṇu, തു tu, നു nu (ന്നു nnu), ഭു bhu, രു ru, ശു shu, ഹു hu"
+    note "      ടൂ For traditional script forms ഖൂ khū, മൂ mū, etc., exceptionally കൂ kū, ഗൂ gū, ഛൂ chhū, ജൂ jū, ണൂ ṇū, തൂ tū, നൂ nū, ഭൂ bhū, രൂ rū, ശൂ shū, ഹൂ hū"
+    note "      ടൃ Traditionally written in conjunction with the consonant character: കൃ kṛ ."
+    note "      ടൗ In the older spelling: ൌ."
+    note "      ട്‌  Indicates absence of the inherent short [a] vowel, e.g. ക്‌ k , സ്‌ s. Special, co-called chillu-forms of consonants with that symbol: ണ്‍ ṇ, ന്‍ n, ര്‍ r, ല്‍ l, ള്‍ ḷ."
+    note "      റ  Special ligature: റ്റ ṭ̈."
+  }
+}
+
+tests {
+   "ചൈനയ്ക്കെതിരെ ലഡാക്കിൽ സദാസജ്ജം; യുഎസിൽനിന്ന് ൭൨,൫൦൦ സിഗ്–൧൬ റൈഫിൾ" ->  "chainaykkĕtirĕ laḍākkil sadāsajjaṃ; yuĕsilninn 72,500 sig–16 ṟaiphiḷ"
+   "സർഗഭൂമിക’യ്ക്കില്ല; ലളിതച്ചേച്ചി അങ്ങനെ പറഞ്ഞിട്ടുണ്ടാവില്ല: ആർഎൽവി രാമകൃഷ്ണൻ" ->  "sargabhūmika’ykkilla; laḷitachchechchi aṅṅanĕ paṟaññiṭṭuṇṭāvilla: ārĕlvi rāmakṛṣhṇan"
+   "സ്വർണക്കടത്ത്‌: ഫൈസൽ ഫരീദും റബിന്‍സും ദുബായിൽ അറസ്റ്റിലായെന്ന്‌ എന്‍ഐഎ" ->  "svarṇakkaṭatt: phaisal pharīduṃ ṟabinsuṃ dubāyil aṟasṟṟilāyĕnn ĕnaiĕ"
+   "വരുമോ ചൈനയുടെ വാക്സീൻ?; ആഗോള ഉപയോഗത്തിന് ഡബ്ല്യുഎച്ച്ഒയുമായി ചർച്ച" ->  "varumo chainayuṭĕ vāksīn?; āgoḷa upayogattin ḍablyuĕchchŏyumāyi charchcha"
+   "കുട്ടികളുടെ മാനസിക പിരിമുറുക്കം മാറ്റാൻ പരിശീലനം; ക്ലാസുമായി പോക്സോ പ്രതി" ->  "kuṭṭikaḷuṭĕ mānasika pirimuṟukkaṃ māṟṟān parishīlanaṃ; klāsumāyi pokso prati"
+   "ആദ്യം അമിത് ഷാ, ഇപ്പോൾ മോദി; ബിജെപിയെ പുണരാൻ ജഗൻ; ആന്ധ്രയിലെ കരുനീക്കങ്ങൾ" ->  "ādyaṃ amit ṣhā, ippoḷ modi; bijĕpiyĕ puṇarān jagan; āndhrayilĕ karunīkkaṅṅaḷ"
+   "ലഹരിമരുന്ന് കേസ്: ബിനീഷ് കോടിയേരിയെ ഇഡി 6 മണിക്കൂർ ചോദ്യം ചെയ്തു" ->  "laharimarunn kes: binīṣh koṭiyeriyĕ iḍi 6 maṇikkūr chodyaṃ chĕytu"
+   "ഈന്തപ്പഴം വിതരണം ചെയ്തത് ശിവശങ്കര്‍ പറഞ്ഞതു പ്രകാരം: ടി.വി അനുപമയുടെ മൊഴി" ->  "īntappaḻaṃ vitaraṇaṃ chĕytat shivashaṅkar paṟaññatu prakāraṃ: ṭi.vi anupamayuṭĕ mŏḻi"
+   "൫൦൦൦ മണിക്കൂർ കാത്തിരിക്കാൻ തയാറെന്ന് രാഹുൽ: ഒടുവിൽ വഴങ്ങി ഹരിയാന" ->  "5000 maṇikkūr kāttirikkān tayāṟĕnn rāhul: ŏṭuvil vaḻaṅṅi hariyāna"
+   "കാരണം ഷോര്‍ട്ട്‌സര്‍ക്യൂട്ടല്ല; കത്തിയത് ഫയല്‍ മാത്രം, സാനിറ്റൈസര്‍ ഉള്‍പ്പെടെ കത്തിയില്ല" ->  "kāraṇaṃ ṣhorṭṭsarkyūṭṭalla; kattiyat phayal mātraṃ, sāniṟṟaisar uḷppĕṭĕ kattiyilla"
+   "വിമൺ സയൻറിസ്റ്റ്സ് സ്കീം" ->  "vimaṇ sayanṟisṟṟs skīṃ"
+
+  # Note: UN card expects this to start with an uppercase letter, but that would break other tests
+   "കേരളം" ->  "keraḷaṃ"
+   "തിരുവനന്തപുരം" ->  "tiruvanantapuraṃ"
+}
+
+aliases {
+  mlym_chars_1 = any("\u0d3e\u0d3f\u0d40\u0d41\u0d42\u0d43\u0d46\u0d47\u0d48\u0d4a\u0d4b\u0d4c\u0d4d")
+}
+
+stage main {
+
+  # RULES
+  sub {
+    from "ക"
+    to "k"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഖ"
+    to "kh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഗ"
+    to "g"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഘ"
+    to "gh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ങ"
+    to "ṅ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ച"
+    to "ch"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഛ"
+    to "chh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ജ"
+    to "j"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഝ"
+    to "jh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഞ"
+    to "ñ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ട"
+    to "ṭ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഠ"
+    to "ṭh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഡ"
+    to "ḍ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഢ"
+    to "ḍh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ണ"
+    to "ṇ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ത"
+    to "t"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഥ"
+    to "th"
+    after mlym_chars_1
+  }
+  sub {
+    from "ദ"
+    to "d"
+    after mlym_chars_1
+  }
+  sub {
+    from "ധ"
+    to "dh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ന"
+    to "n"
+    after mlym_chars_1
+  }
+  sub {
+    from "പ"
+    to "p"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഫ"
+    to "ph"
+    after mlym_chars_1
+  }
+  sub {
+    from "ബ"
+    to "b"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഭ"
+    to "bh"
+    after mlym_chars_1
+  }
+  sub {
+    from "മ"
+    to "m"
+    after mlym_chars_1
+  }
+  sub {
+    from "യ"
+    to "y"
+    after mlym_chars_1
+  }
+  sub {
+    from "ര"
+    to "r"
+    after mlym_chars_1
+  }
+  sub {
+    from "ല"
+    to "l"
+    after mlym_chars_1
+  }
+  sub {
+    from "വ"
+    to "v"
+    after mlym_chars_1
+  }
+  sub {
+    from "ശ"
+    to "sh"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഷ"
+    to "ṣh"
+    after mlym_chars_1
+  }
+  sub {
+    from "സ"
+    to "s"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഹ"
+    to "h"
+    after mlym_chars_1
+  }
+  sub {
+    from "ള"
+    to "ḷ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ഴ"
+    to "ḻ"
+    after mlym_chars_1
+  }
+  sub {
+    from "റ"
+    to "ṟ"
+    after mlym_chars_1
+  }
+  sub {
+    from "ക്ഷ"
+    to "kṣh"
+    after mlym_chars_1
+  }
+
+
+  # CHARACTERS
+  parallel {
+    # I. Independent vowel characters
+    sub "അ" "a"
+    sub "ആ" "ā"
+    sub "ഇ" "i"
+    sub "ഈ" "ī"
+    sub "ഉ" "u"
+    sub "ഊ" "ū"
+    sub "ഋ" "ṛ"
+    sub "എ" "ĕ"
+    sub "ഏ" "e"
+    sub "ഐ" "ai"
+    sub "ഒ" "ŏ"
+    sub "ഓ" "o"
+    sub "ഔ" "au"
+
+    # II. Abbreviated vowel characters
+    sub "ാ" "ā"
+    sub "ി" "i"
+    sub "ീ" "ī"
+    sub "ു" "u"
+    sub "ൂ" "ū"
+    sub "ൃ" "ṛ"
+    sub "െ" "ĕ"
+    sub "േ" "e"
+    sub "ൈ" "ai"
+    sub "ൊ" "ŏ"
+    sub "ോ" "o"
+    sub "ൌ" "au"
+
+    #III. Other symbols
+    sub "ഃ" "ḥ"
+    sub "ം" "ṃ"
+    sub "്" ""
+
+    #IV. Consonant characters
+    sub "ക" "ka"
+    sub "ഖ" "kha"
+    sub "ഗ" "ga"
+    sub "ഘ" "gha"
+    sub "ങ" "ṅa"
+    sub "ച" "cha"
+    sub "ഛ" "chha"
+    sub "ജ" "ja"
+    sub "ഝ" "jha"
+    sub "ഞ" "ña"
+    sub "ട" "ṭa"
+    sub "ഠ" "ṭha"
+    sub "ഡ" "ḍa"
+    sub "ഢ" "ḍha"
+    sub "ണ" "ṇa"
+    sub "ത" "ta"
+    sub "ഥ" "tha"
+    sub "ദ" "da"
+    sub "ധ" "dha"
+    sub "ന" "na"
+    sub "പ" "pa"
+    sub "ഫ" "pha"
+    sub "ബ" "ba"
+    sub "ഭ" "bha"
+    sub "മ" "ma"
+    sub "യ" "ya"
+    sub "ര" "ra"
+    sub "ല" "la"
+    sub "വ" "va"
+    sub "ശ" "sha"
+    sub "ഷ" "ṣha"
+    sub "സ" "sa"
+    sub "ഹ" "ha"
+    sub "ക്ഷ" "kṣha"
+    sub "ള" "ḷa"
+    sub "ഴ" "ḻa"
+    sub "റ" "ṟa"
+    sub "റ്റ" "ṭ̈"
+
+
+    sub "्" ""
+    sub "़" ""
+    sub "ൗ" ""
+    sub "‍" ""
+    sub "‌" ""
+
+
+    # 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"
+
+
+    # chillu-forms of consonants note 5
+    sub "ൿ" "k"
+    sub "ൺ" "ṇ"
+    sub "ൻ" "n"
+    sub "ൽ" "l"
+    sub "ൾ" "ḷ"
+    sub "ർ" "r"
+    sub "സ്" "s"
+  }
+
+
+  compose
+}
+}