metadata {
authority_id: alalc id: 1997 language: iso-639-2:mal source_script: Mlym destination_script: Latn name: Romanization Table -- Malayalam (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
}