API References

align(src::Array{String}, tgt::Array{String}; 
	costmodel::CostModel=CostModel(match=0, mismatch=1, insertion=1, deletion=0),
	store_results::Bool=true
)

ALign tgt array of texts to src array of texts using a particular costmodel from BioAlignments.jl. store_results if results of alignment are stored or returned, otherwise, only the scores are returned.

align(src::String, tgt::String; costmodel::BioAlignments.CostModel=BioAlignments.CostModel(match=0, mismatch=1, insertion=1, deletion=1))

Align tgt string to src string using a particular costmodel from BioAlignments.jl.

arabic(s::String[, encoder::AbstractEncoder])

Encode the String object into Arabic characters. Custom encoder generated from @transliterator can be provided, but default is Buckwalter.

Examples

julia> bw_basmala = "bisomi {ll~ahi {lr~aHoma`ni {lr~aHiymi"
julia> arabic(bw_basmala)
"بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"

clean(s::String, replace_non_ar::String, target_regex::Regex)

Clean the input text by replacing all non-Arabic texts with a string input.

dediac(s::String)

Dediacritize the input String object.

Examples

julia> bw_basmala = "bisomi {ll~ahi {lr~aHoma`ni {lr~aHiymi"
julia> dediac(bw_basmala)
"bsm {llh {lrHmn {lrHym"
julia> dediac(arabic(bw_basmala))
"بسم ٱلله ٱلرحمن ٱلرحيم"

encode(s::String)

Transliterate the input String object using Buckwalter.

Examples

julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"
julia> encode(ar_basmala)
"bisomi {ll~ahi {lr~aHoma`ni {lr~aHiymi"

encode(s::Union{Char,String}, encoder::AbstractEncoder)

Transliterate the input String object using a custom encoder. Custom encoder is generated using the @transliterator.

isfeat(x::Orthography, y::Type{<:AbstractConsonant})

checks if x is a y feature.

julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ";
julia> arb_token = tokenize(ar_basmala)
4-element Vector{String}:
 "بِسْمِ"
 "ٱللَّهِ"
 "ٱلرَّحْمَٰنِ"
 "ٱلرَّحِيمِ"
julia> arb_parsed2 = parse.(Orthography, arb_token)
4-element Vector{Orthography}:
 Orthography(Type[Ba, Kasra, Seen, Sukun, Meem, Kasra])
 Orthography(Type[AlifHamzatWasl, Lam, Lam, Shadda, Fatha, Ha, Kasra])
 Orthography(Type[AlifHamzatWasl, Lam, Ra, Shadda, Fatha, HHa, Sukun, Meem, Fatha, AlifKhanjareeya, Noon, Kasra])
 Orthography(Type[AlifHamzatWasl, Lam, Ra, Shadda, Fatha, HHa, Kasra, Ya, Meem, Kasra])
julia> isfeat(arb_parsed2[1], AbstractLunar)
6-element BitVector:
 1
 0
 0
 0
 1
 0

normalize(s::String)

Normalize a Arabic or Buckwalter String characters.

Examples

julia> normalize("بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ")
"بِسْمِ اللَّهِ الرَّحْمَانِ الرَّحِيمِ"

normalize(s::String, char::Symbol)

Normalize a specific Arabic or Buckwalter String character (chars).

Examples

julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"
julia> normalize(ar_basmala, :alif_khanjareeya) === "بِسْمِ ٱللَّهِ ٱلرَّحْمَانِ ٱلرَّحِيمِ"

normalize(s::String, chars::Array{Symbol,1})

Normalize a specific Arabic or Buckwalter String character/s (chars).

Examples

julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"
julia> normalize(ar_basmala, [:alif_khanjareeya, :hamzat_wasl]) === "بِسْمِ اللَّهِ الرَّحْمَانِ الرَّحِيمِ"

tokenize(s::String)

tokenizes the string input s by space, and also tokenizes the punctuations.

julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"
julia> tokenize(ar_basmala)
4-element Vector{String}:
 "بِسْمِ"
 "ٱللَّهِ"
 "ٱلرَّحْمَٰنِ"
 "ٱلرَّحِيمِ"

@transliterator(dict, name)

Create a custom transliterator using an input dict (Dict object) with its corresponding name as String object. This will automatically update the transliterator inside all functions like arabic, verses, and encode.

Examples

julia> my_encoder = Dict(
    Symbol(Char(0x0621)) => Symbol('('),
    Symbol(Char(0x0622)) => Symbol('''),
    Symbol(Char(0x0623)) => Symbol('&'),
    Symbol(Char(0x0624)) => Symbol('>'),
    Symbol(Char(0x0625)) => Symbol('}'),
    Symbol(Char(0x0626)) => Symbol('<'),
    Symbol(Char(0x0627)) => Symbol('b'),
    Symbol(Char(0x0628)) => Symbol('A'),
    Symbol(Char(0x0629)) => Symbol('t'),
    Symbol(Char(0x062A)) => Symbol('p'),
    Symbol(Char(0x062B)) => Symbol('j'),
    Symbol(Char(0x062C)) => Symbol('v'),
    Symbol(Char(0x062D)) => Symbol('x'),
    Symbol(Char(0x062E)) => Symbol('H'),
    Symbol(Char(0x062F)) => Symbol('*'),
    Symbol(Char(0x0630)) => Symbol('d'),
    Symbol(Char(0x0631)) => Symbol('z'),
    Symbol(Char(0x0632)) => Symbol('r'),
    Symbol(Char(0x0633)) => Symbol('$'),
    Symbol(Char(0x0634)) => Symbol('s'),
    Symbol(Char(0x0635)) => Symbol('D'),
    Symbol(Char(0x0636)) => Symbol('S'),
    Symbol(Char(0x0637)) => Symbol('Z'),
    Symbol(Char(0x0638)) => Symbol('T'),
    Symbol(Char(0x0639)) => Symbol('g'),
    Symbol(Char(0x063A)) => Symbol('E'),
    Symbol(Char(0x0640)) => Symbol('f'),
    Symbol(Char(0x0641)) => Symbol('_'),
    Symbol(Char(0x0642)) => Symbol('k'),
    Symbol(Char(0x0643)) => Symbol('q'),
    Symbol(Char(0x0644)) => Symbol('m'),
    Symbol(Char(0x0645)) => Symbol('l'),
    Symbol(Char(0x0646)) => Symbol('h'),
    Symbol(Char(0x0647)) => Symbol('n'),
    Symbol(Char(0x0648)) => Symbol('Y'),
    Symbol(Char(0x0649)) => Symbol('w'),
    Symbol(Char(0x064A)) => Symbol('F'),
    Symbol(Char(0x064B)) => Symbol('y'),
    Symbol(Char(0x064C)) => Symbol('K'),
    Symbol(Char(0x064D)) => Symbol('N'),
    Symbol(Char(0x064E)) => Symbol('u'),
    Symbol(Char(0x064F)) => Symbol('a'),
    Symbol(Char(0x0650)) => Symbol('~'),
    Symbol(Char(0x0651)) => Symbol('i'),
    Symbol(Char(0x0652)) => Symbol('^'),
    Symbol(Char(0x0653)) => Symbol('o'),
    Symbol(Char(0x0654)) => Symbol('`'),
    Symbol(Char(0x0670)) => Symbol('#'),
    Symbol(Char(0x0671)) => Symbol(':'),
    Symbol(Char(0x06DC)) => Symbol('{'),
    Symbol(Char(0x06DF)) => Symbol('"'),
    Symbol(Char(0x06E0)) => Symbol('@'),
    Symbol(Char(0x06E2)) => Symbol(';'),
    Symbol(Char(0x06E3)) => Symbol('['),
    Symbol(Char(0x06E5)) => Symbol('.'),
    Symbol(Char(0x06E6)) => Symbol(','),
    Symbol(Char(0x06E8)) => Symbol('-'),
    Symbol(Char(0x06EA)) => Symbol('!'),
    Symbol(Char(0x06EB)) => Symbol('%'),
    Symbol(Char(0x06EC)) => Symbol('+'),
    Symbol(Char(0x06ED)) => Symbol(']')
);
julia> @transliterator my_encoder "MyEncoder"
julia> encode(ar_basmala)
"A~$^l~ :mmiun~ :mziux^lu#h~ :mziux~Fl~"

@transliterator(symbl)

Fallback to the default Buckwalter transliterator.

julia> @transliterator :default
julia> ar_basmala = "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ"
julia> encode(ar_basmala)
"bisomi {ll~ahi {lr~aHoma`ni {lr~aHiymi"