metadata {

authority_id: alalc
id: 1997
language: iso-639-2:tel
source_script: Telu
destination_script: Latn
name: Romanization Table -- Telugu (1997)
url: http://catdir.loc.gov/catdir/cpso/romanization/telugu.pdf
creation_date: 1997
description: |
  ALA-LC Romanization table for Telugu

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 ( ౬ ) called valapalagilaka.
  - |
    Exception: Sunna is transliterated by:
    a) ṅ before gutturals,
    b) ñ before palatals,
    c) ṇ before cerebrals,
    d) n before dentals, and
    e) m before labials.
  - |
    Ardhasunna before gutturals and palatal, cerebral, and dental occlusives is transliterated n̐.
    Before labials, sibilants, semivowels, the aspirate, vowels, and in final position it is
    transliterated m

}

tests {

test "తమిళనాడు", "tamiḷanāḍu"
test "తంటికొండ ఘటన: ఆగని మృత్యుఘోష", "taṃṭikoṇḍa ghaṭana: āgani mṛtayughŏṣa"
test "మళ్లీ వివాదం: అమితాబ్‌పై కేసు", "maḷalī vivādaṃ: amitābapai kēsu"
test "‘వరద సాయం పేరుతో వైట్ కాలర్ దోపిడీ’", "‘varada sāyaṃ pērutŏ vaiṭa kālara dŏpiḍī’"
test "రెండో విడత జీఎస్టీ పరిహారం", "reṃḍŏ viḍata jīesaṭī parihāraṃ"
test "నితీష్‌ కుమార్‌ అధ్యాయం ముగిసినట్లేనా?!", "nitīṣa kumāra adhayāyaṃ mugisinaṭalēnā?!"
test "వారిపై జీవితాంతం నిషేధం విధించండి!", "vāripai jīvitāntaṃ niṣēdhaṃ vidhiñcaṃḍi!"
test "మరో లాక్‌డౌన్‌ వల్ల అన్నీ అనర్థాలే!", "marŏ lākaḍauna valala ananī anarathālē!"
test "జెసిండా మరో సంచలనం", "jesiṃḍā marŏ sañcalanaṃ"
test "స్వీయ నిర్బంధంలోకి డబ్ల్యూహెచ్‌ఓ డైరెక్టర్‌", "savīya nirabandhaṃlŏki ḍabalayūhecaō ḍairekaṭara"
test "కరోనాపై యుద్ధంలో సమిధలు", "karŏnāpai yudadhaṃlŏ samidhalu"
test "అమెరికా ఎన్నికలు: ‘పెద్దన్న’ ఎవరో?!", "amerikā enanikalu: ‘pedadanana’ evarŏ?!"
test "౪౬౨౬౯", "46269"

}

aliases {

def_alias telu_chars_1, any("\u0c3e\u0c3f\u0c40\u0c41\u0c42\u0c43\u0c46\u0c47\u0c48\u0c4a\u0c4b\u0c4c\u0c6c")

}

stage {

 # RULES
 # rule II
   sub "క", "k", after: telu_chars_1
   sub "ఖ", "kh", after: telu_chars_1
   sub "గ", "g", after: telu_chars_1
   sub "ఘ", "gh", after: telu_chars_1
   sub "ఙ", "ṅ", after: telu_chars_1
   sub "చ", "c", after: telu_chars_1
   sub "ౘ", "ĉ", after: telu_chars_1
   sub "ఛ", "ch", after: telu_chars_1
   sub "జ", "j", after: telu_chars_1
   sub "ౙ", "ĵ", after: telu_chars_1
   sub "ఝ", "jh", after: telu_chars_1
   sub "ఞ", "ñ", after: telu_chars_1
   sub "ట", "ṭ", after: telu_chars_1
   sub "ఠ", "ṭh", after: telu_chars_1
   sub "డ", "ḍ", after: telu_chars_1
   sub "ఢ", "ḍh", after: telu_chars_1
   sub "ణ", "ṇ", after: telu_chars_1
   sub "త", "t", after: telu_chars_1
   sub "థ", "th", after: telu_chars_1
   sub "ద", "d", after: telu_chars_1
   sub "ధ", "dh", after: telu_chars_1
   sub "న", "n", after: telu_chars_1
   sub "ప", "p", after: telu_chars_1
   sub "ఫ", "ph", after: telu_chars_1
   sub "బ", "b", after: telu_chars_1
   sub "భ", "bh", after: telu_chars_1
   sub "మ", "m", after: telu_chars_1
   sub "య", "y", after: telu_chars_1
   sub "ర", "r", after: telu_chars_1
   sub "ఱ", "ṛ", after: telu_chars_1
   sub "ల", "l", after: telu_chars_1
   sub "ళ", "ḷ", after: telu_chars_1
   sub "వ", "v", after: telu_chars_1
   sub "శ", "ś", after: telu_chars_1
   sub "ష", "ṣ", after: telu_chars_1
   sub "స", "s", after: telu_chars_1
   sub "హ", "h", after: telu_chars_1

 # rule III
   sub "\u0C02", "ṅ", after: any("కఖగఘఙ")
   sub "\u0C02", "ñ", after: any("చౘఛజౙఝఞ")
   sub "\u0C02", "ṇ", after: any("టఠడఢణ")
   sub "\u0C02", "n", after: any("తథదధన")
   sub "\u0C02", "m", after: any("పఫబభమ")

 # rule IV
   sub "\u0C01", "n̐", after: any("కఖగఘఙచౘఛజౙఝఞటఠడఢణతథదధన") # before guttural, palatal, cerebral, and dental

 # CHARACTERS
 parallel {

   sub "అ", "a"
   sub "ఆ", "ā"
   sub "ఇ", "i"
   sub "ఈ", "ī"
   sub "ఉ", "u"
   sub "ఊ", "ū"
   sub "ఋ", "ṛ"
   sub "ౠ", "ṝ"
   sub "ఌ", "ḻ"
   sub "ఎ", "e"
   sub "ఏ", "ē"
   sub "ఐ", "ai"
   sub "ఒ", "o"
   sub "ఓ", "ō"
   sub "ఔ", "au"

   # Gutturals
   sub "క", "ka"
   sub "ఖ", "kha"
   sub "గ", "ga"
   sub "ఘ", "gha"
   sub "ఙ", "ṅa"

   # Palatals
   sub "చ", "ca"
   sub "ౘ", "ĉa"
   sub "ఛ", "cha"
   sub "జ", "ja"
   sub "ౙ", "ĵa"
   sub "ఝ", "jha"
   sub "ఞ", "ña"

   # Cerebrals
   sub "ట", "ṭa"
   sub "ఠ", "ṭha"
   sub "డ", "ḍa"
   sub "ఢ", "ḍha"
   sub "ణ", "ṇa"

   # Dentals
   sub "త", "ta"
   sub "థ", "tha"
   sub "ద", "da"
   sub "ధ", "dha"
   sub "న", "na"

   # Labials
   sub "ప", "pa"
   sub "ఫ", "pha"
   sub "బ", "ba"
   sub "భ", "bha"
   sub "మ", "ma"

   # Semivowels
   sub "య", "ya"
   sub "ర", "ra"
   sub "ఱ", "ṛa"
   sub "ల", "la"
   sub "ళ", "ḷa"
   sub "వ", "va"

   # Sibilants
   sub "శ", "śa"
   sub "ష", "ṣa"
   sub "స", "sa"

   # Aspirate
   sub "హ", "ha"

   # Chandrabindu
   sub "ঁ", "m̐"
   sub "ఁ", "m̐"

   # Bisarga
   sub "ః", "ḥ"

   # Anusvāra
   sub "ం", "ṃ"

   # Medials # Needed for connecting constants

   sub "ా", "ā"
   sub "ి", "i"
   sub "ీ", "ī"
   sub "ు", "u"
   sub "ూ", "ū"
   sub "ృ", "ṛ"
   sub "ె", "e"
   sub "ే", "ē"
   sub "ై", "ai"
   sub "ొ", "o"
   sub "ో", "ŏ"
   sub "ౌ", "au"
   sub "\u09CD", "" # Used for joining

   sub "\u0c4d", "" #verma sign for halanta
   sub "ౕ\t", ""
   sub "ౖ\t", ""
   sub "्", ""
   sub "़", ""
   sub "‍", "" # Used for joining
   sub "‌", "" # Used for non joining

   # numbers

   sub "౦", "0"
   sub "౧", "1"
   sub "౨", "2"
   sub "౩", "3"
   sub "౪", "4"
   sub "౫", "5"
   sub "౬", "6"
   sub "౭", "7"
   sub "౮", "8"
   sub "౯", "9"
 }

compose

}