Working with QuranTree.jl
Yunir.jl can seemlessly work with QuranTree.jl.
julia> using Yunirjulia> using QuranTreejulia> data = QuranData();julia> crps, tnzl = load(data);julia> crpsdata = table(crps)Quranic Arabic Corpus (morphology) (C) 2011 Kais Dukes 128219×7 DataFrame Row │ chapter verse word part form tag features ⋯ │ Int64 Int64 Int64 Int64 String String String ⋯ ────────┼─────────────────────────────────────────────────────────────────────── 1 │ 1 1 1 1 bi P PREFIX|bi+ ⋯ 2 │ 1 1 1 2 somi N STEM|POS:N|LEM:{so 3 │ 1 1 2 1 {ll~ahi PN STEM|POS:PN|LEM:{l 4 │ 1 1 3 1 {l DET PREFIX|Al+ 5 │ 1 1 3 2 r~aHoma`ni ADJ STEM|POS:ADJ|LEM:r ⋯ 6 │ 1 1 4 1 {l DET PREFIX|Al+ 7 │ 1 1 4 2 r~aHiymi ADJ STEM|POS:ADJ|LEM:r 8 │ 1 2 1 1 {lo DET PREFIX|Al+ ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋱ 128213 │ 114 5 5 2 n~aAsi N STEM|POS:N|LEM:n~a ⋯ 128214 │ 114 6 1 1 mina P STEM|POS:P|LEM:min 128215 │ 114 6 2 1 {lo DET PREFIX|Al+ 128216 │ 114 6 2 2 jin~api N STEM|POS:N|LEM:jin 128217 │ 114 6 3 1 wa CONJ PREFIX|w:CONJ+ ⋯ 128218 │ 114 6 3 2 {l DET PREFIX|Al+ 128219 │ 114 6 3 3 n~aAsi N STEM|POS:N|LEM:n~a 1 column and 128204 rows omittedjulia> tnzldata = table(tnzl)Tanzil Quran Text (Uthmani) (C) 2008-2010 Tanzil.net 6236×3 DataFrame Row │ chapter verse form │ Int64 Int64 String ──────┼─────────────────────────────────────────────────── 1 │ 1 1 بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ 2 │ 1 2 ٱلْحَمْدُ لِلَّهِ رَبِّ ٱلْعَٰلَمِينَ 3 │ 1 3 ٱلرَّحْمَٰنِ ٱلرَّحِيمِ 4 │ 1 4 مَٰلِكِ يَوْمِ ٱلدِّينِ 5 │ 1 5 إِيَّاكَ نَعْبُدُ وَإِيَّاكَ نَسْتَعِينُ 6 │ 1 6 ٱهْدِنَا ٱلصِّرَٰطَ ٱلْمُسْتَقِيمَ 7 │ 1 7 صِرَٰطَ ٱلَّذِينَ أَنْعَمْتَ عَلَيْهِمْ غَيْرِ ٱلْمَغْضُو… 8 │ 2 1 بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ الٓمٓ ⋮ │ ⋮ ⋮ ⋮ 6230 │ 113 5 وَمِن شَرِّ حَاسِدٍ إِذَا حَسَدَ 6231 │ 114 1 بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ قُلْ أَعُوذُ بِ… 6232 │ 114 2 مَلِكِ ٱلنَّاسِ 6233 │ 114 3 إِلَٰهِ ٱلنَّاسِ 6234 │ 114 4 مِن شَرِّ ٱلْوَسْوَاسِ ٱلْخَنَّاسِ 6235 │ 114 5 ٱلَّذِى يُوَسْوِسُ فِى صُدُورِ ٱلنَّاسِ 6236 │ 114 6 مِنَ ٱلْجِنَّةِ وَٱلنَّاسِ 6221 rows omittedjulia> arabic(verses(crpsdata[114])[1])"قُلْ أَعُوذُ بِرَبِّ ٱلنَّاسِ"
You have to install QuranTree.jl to run the above example. To install, run
using Pkg
Pkg.add("QuranTree")Normalization
julia> ikhlas = crpsdata[114]Chapter 114: ٱلنَّاس (People) 30×6 DataFrame Row │ verse word part form tag features ⋯ │ Int64 Int64 Int64 String String String ⋯ ─────┼────────────────────────────────────────────────────────────────────────── 1 │ 1 1 1 qulo V STEM|POS:V|IMPV|LEM:qaAla|ROOT ⋯ 2 │ 1 2 1 >aEuw*u V STEM|POS:V|IMPF|LEM:Eu*o|ROOT: 3 │ 1 3 1 bi P PREFIX|bi+ 4 │ 1 3 2 rab~i N STEM|POS:N|LEM:rab~|ROOT:rbb|M 5 │ 1 4 1 {l DET PREFIX|Al+ ⋯ 6 │ 1 4 2 n~aAsi N STEM|POS:N|LEM:n~aAs|ROOT:nws| 7 │ 2 1 1 maliki N STEM|POS:N|LEM:malik|ROOT:mlk| 8 │ 2 2 1 {l DET PREFIX|Al+ ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋱ 24 │ 5 5 2 n~aAsi N STEM|POS:N|LEM:n~aAs|ROOT:nws| ⋯ 25 │ 6 1 1 mina P STEM|POS:P|LEM:min 26 │ 6 2 1 {lo DET PREFIX|Al+ 27 │ 6 2 2 jin~api N STEM|POS:N|LEM:jin~ap|ROOT:jnn 28 │ 6 3 1 wa CONJ PREFIX|w:CONJ+ ⋯ 29 │ 6 3 2 {l DET PREFIX|Al+ 30 │ 6 3 3 n~aAsi N STEM|POS:N|LEM:n~aAs|ROOT:nws| 1 column and 15 rows omittedjulia> ikhlas_vrs = verses(ikhlas)6-element Vector{String}: "qulo >aEuw*u birab~i {ln~aAsi" "maliki {ln~aAsi" "<ila`hi {ln~aAsi" "min \$ar~i {lowasowaAsi {loxan~aAsi" "{l~a*iY yuwasowisu fiY Suduwri {ln~aAsi" "mina {lojin~api wa{ln~aAsi"julia> ikhlas_nrm = normalize.(ikhlas_vrs; isarabic=false)6-element Vector{String}: "qulo AaEuw*u birab~i Aln~aAsi" "maliki Aln~aAsi" "AilaAhi Aln~aAsi" "min \$ar~i AlowasowaAsi Aloxan~aAsi" "Al~a*iy yuwasowisu fiy Suduwri Aln~aAsi" "mina Alojin~ahi waAln~aAsi"julia> arabic.(ikhlas_nrm)6-element Vector{String}: "قُلْ اَعُوذُ بِرَبِّ النَّاسِ" "مَلِكِ النَّاسِ" "اِلَاهِ النَّاسِ" "مِن شَرِّ الْوَسْوَاسِ الْخَنَّاسِ" "الَّذِي يُوَسْوِسُ فِي صُدُورِ النَّاسِ" "مِنَ الْجِنَّهِ وَالنَّاسِ"
Dediacritization
julia> ikhlas_ddc = dediac.(ikhlas_vrs; isarabic=false)6-element Vector{String}: "ql >Ew* brb {lnAs" "mlk {lnAs" "<lh {lnAs" "mn \$r {lwswAs {lxnAs" "{l*Y ywsws fY Sdwr {lnAs" "mn {ljnp w{lnAs"julia> arabic.(ikhlas_ddc)6-element Vector{String}: "قل أعوذ برب ٱلناس" "ملك ٱلناس" "إله ٱلناس" "من شر ٱلوسواس ٱلخناس" "ٱلذى يوسوس فى صدور ٱلناس" "من ٱلجنة وٱلناس"
Transliteration
julia> ar_ikhlas = verses(tnzldata[114])6-element Vector{String}: "بِسْمِ ٱللَّهِ ٱلرَّحْمَٰنِ ٱلرَّحِيمِ قُلْ أَعُوذُ بِرَبِّ ٱلنَّاسِ" "مَلِكِ ٱلنَّاسِ" "إِلَٰهِ ٱلنَّاسِ" "مِن شَرِّ ٱلْوَسْوَاسِ ٱلْخَنَّاسِ" "ٱلَّذِى يُوَسْوِسُ فِى صُدُورِ ٱلنَّاسِ" "مِنَ ٱلْجِنَّةِ وَٱلنَّاسِ"julia> encode.(ar_ikhlas)6-element Vector{String}: "bisomi {ll~ahi {lr~aHoma`ni {lr~aHiymi qulo >aEuw*u birab~i {ln~aAsi" "maliki {ln~aAsi" "<ila`hi {ln~aAsi" "min \$ar~i {lowasowaAsi {loxan~aAsi" "{l~a*iY yuwasowisu fiY Suduwri {ln~aAsi" "mina {lojin~api wa{ln~aAsi"