metadata {

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

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
       birāma.

  - Candrabindu 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 {

test "অসমীয়া কবিতা", "asamīẏā kabitā"
test "কবিৰ আজি জন্মদিন", "kabira āji janmadina"
test "বেৰুটত এমাহৰ পাছতে পুনৰ ভয়ংকৰ অগ্নিকাণ্ড", "beruṭata emāhara pāchate punara bhayaṃkara agnikāṇḍa"
test "ভঙাৰ বিৰুদ্ধে আৱেদন দাখিল কংগনাৰ", "bhaṅāra biruddhe āwedana dākhila kaṃganāra"
test "আপুনি পঢ়ি ভাল পাব পৰা বাতৰি", "āpuni paṛhi bhāla pāba parā bātari"
test "শ্ৰীৰামপুৰত গৰুভৰ্তি ট্ৰাক জব্দ, দুজনক আটক", "śrīrāmapurata garubharti ṭrāka jabda, dujanaka āṭaka"
test "কেনে আছে প্ৰাক্তন", "kene āche prāktana"
test "কমুম্বাইৰ মেয়ৰৰ দেহত কোভিড পজিটিভ", "kamumbāira meẏarara dehata kobhiḍa pajiṭibha"
test "টুইটাৰযোগে খোদ সদৰী কৰে এই কথা", "ṭuiṭāraẏoge khoda sadarī kare ei kathā"
test "লখিমপুৰ জিলাৰ নাৰায়ণপুৰৰ বৰপথাৰত আজি প্ৰশান্তি ধাম নামেৰে এখন বৃদ্ধাশ্ৰমৰ শুভাৰম্ভ কৰা হয়", "lakhimapura jilāra nārāẏaṇapurara barapathārata āji praśānti dhāma nāmere ekhana bṛddhāśramara śubhārambha karā haẏa"

}

aliases {

def_alias deva_chars_1, any("\u09be\u09bf\u09c0\u09c1\u09c2\u09c3\u09c7\u09c8\u09cb\u09cc\u094d\u09cd")

}

stage {

# RULES
# note[2]
sub "ক", "k", after: deva_chars_1
sub "খ", "kh", after: deva_chars_1
sub "গ", "g", after: deva_chars_1
sub "ঘ", "gh", after: deva_chars_1
sub "ঙ", "ṅ", after: deva_chars_1
sub "চ", "c", after: deva_chars_1
sub "ছ", "ch", after: deva_chars_1
sub "জ", "j", after: deva_chars_1
sub "ঝ", "jh", after: deva_chars_1
sub "ঞ", "ñ", after: deva_chars_1
sub "ট", "ṭ", after: deva_chars_1
sub "ঠ", "ṭh", after: deva_chars_1
sub "ড", "ḍ", after: deva_chars_1
sub "ড়", "ṛ", after: deva_chars_1
sub "ঢ", "ḍh", after: deva_chars_1
sub "ঢ়", "ṛh", after: deva_chars_1
sub "ণ", "ṇ", after: deva_chars_1
sub "ত", "t", after: deva_chars_1
sub "ৎ", "ṭ", after: deva_chars_1
sub "থ", "th", after: deva_chars_1
sub "দ", "d", after: deva_chars_1
sub "ধ", "dh", after: deva_chars_1
sub "ন", "n", after: deva_chars_1
sub "প", "p", after: deva_chars_1
sub "ফ", "ph", after: deva_chars_1
sub "ব", "b", after: deva_chars_1
sub "ভ", "bh", after: deva_chars_1
sub "ম", "m", after: deva_chars_1
sub "য়", "y", after: deva_chars_1
sub "য", "ẏ", after: deva_chars_1
sub "য়", "ẏ", after: deva_chars_1
sub "ৰ", "r", after: deva_chars_1
sub "ল", "l", after: deva_chars_1
sub "ৱ", "w", after: deva_chars_1
sub "শ", "ś", after: deva_chars_1
sub "ষ", "sh", after: deva_chars_1
sub "স", "s", after: deva_chars_1
sub "হ", "h", after: deva_chars_1
# note[3]
sub "\u0981", "ṅ", after: any("কখগঘঙচছজঝঞটঠডড়ঢঢ়ণতৎথদধন") # ঁ before guttural, palatal, cerebral, and dental

# CHARACTERS
parallel {

  #Vowels and Diphthongs (see Note 1)

  sub "অ", "a"
  sub "আ", "ā"
  sub "ই", "i"
  sub "ঈ", "ī"
  sub "উ", "u"
  sub "ঊ", "ū"
  sub "ঋ", "ṛ"
  sub "ৠ", "ṝ"
  sub "ঌ", "ḹ"
  sub "এ", "e"
  sub "ঐ", "ai"
  sub "ও", "o"
  sub "ঔ", "au"

  # Consonant characters

  #Gutturals
  sub "ক", "ka"
  sub "খ", "kha"
  sub "গ", "ga"
  sub "ঘ", "gha"
  sub "ঙ", "ṅa"

  #Palatals
  sub "চ", "ca"
  sub "ছ", "cha"
  sub "জ", "ja"
  sub "ঝ", "jha"
  sub "ঞ", "ña"

  #Cerebrals
  sub "ট", "ṭa"
  sub "ঠ", "ṭha"
  sub "ড", "ḍa"
  sub "ড়", "ṛa"
  sub "ঢ", "ḍha"
  sub "ঢ়", "ṛha"
  sub "ণ", "ṇa"

  #Dentals
  sub "ত", "ta"
  sub "ৎ", "ṭ"
  sub "থ", "tha"
  sub "দ", "da"
  sub "ধ", "dha"
  sub "ন", "na"

  #Labials
  sub "প", "pa"
  sub "ফ", "pha"
  sub "ব", "ba"
  sub "ভ", "bha"
  sub "ম", "ma"

  #Semivowels
  sub "য়", "ya"
  sub "য", "ẏa"
  sub "য়", "ẏa"
  sub "ৰ", "ra"
  sub "ল", "la"
  sub "ৱ", "wa"

  #Sibilants
  sub "শ", "śa"
  sub "ষ", "sha"
  sub "স", "sa"

  #Aspirate
  sub "হ", "ha"

  # Anusvāra
  sub "ং", "ṃ"

  # Bisarga
  sub "ঃ", "ḥ"

  # Candrabindu (see Note 3)
  sub "ঁ", "m̐"

  # Abagraha  (see Note 4)
  sub "ऽ", "’" # (apostrophe)

  # Medials # Needed for connecting constants
  sub "\u09be", "ā"
  sub "\u09bf", "i"
  sub "\u09c0", "ī"
  sub "\u09c1", "u"
  sub "\u09c2", "ū"
  sub "\u09c3", "ṛ"
  sub "\u09c7", "e"
  sub "\u09c8", "ai"
  sub "\u09cb", "o"
  sub "\u09cc", "au"
  sub "।", "."
  sub "्", ""
  sub "\u09CD", "" # Used for joining

  # Digits

  sub "১", "1"
  sub "২", "2"
  sub "৩", "3"
  sub "৪", "4"
  sub "৫", "5"
  sub "৬", "6"
  sub "৭", "7"
  sub "৮", "8"
  sub "৯", "9"
  sub "০", "0"
}

compose

}