add docs

Author: alstat

Manifest.toml

@@ -174,9 +174,9 @@ version = "0.12.11"
 
 [[deps.Compat]]
 deps = ["TOML", "UUIDs"]
-git-tree-sha1 = "0037835448781bb46feb39866934e243886d756a"
+git-tree-sha1 = "9d8a54ce4b17aa5bdce0ea5c34bc5e7c340d16ad"
 uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
-version = "4.18.0"
+version = "4.18.1"
 weakdeps = ["Dates", "LinearAlgebra"]
 
     [deps.Compat.extensions]
@@ -242,9 +242,9 @@ version = "1.11.0"
 
 [[deps.Distributions]]
 deps = ["AliasTables", "FillArrays", "LinearAlgebra", "PDMats", "Printf", "QuadGK", "Random", "SpecialFunctions", "Statistics", "StatsAPI", "StatsBase", "StatsFuns"]
-git-tree-sha1 = "3e6d038b77f22791b8e3472b7c633acea1ecac06"
+git-tree-sha1 = "3bc002af51045ca3b47d2e1787d6ce02e68b943a"
 uuid = "31c24e10-a181-5473-b8eb-7969acd0382f"
-version = "0.25.120"
+version = "0.25.122"
 
     [deps.Distributions.extensions]
     DistributionsChainRulesCoreExt = "ChainRulesCore"
@@ -845,9 +845,9 @@ version = "0.8.5+0"
 
 [[deps.OpenSSL_jll]]
 deps = ["Artifacts", "JLLWrappers", "Libdl"]
-git-tree-sha1 = "2ae7d4ddec2e13ad3bddf5c0796f7547cf682391"
+git-tree-sha1 = "f19301ae653233bc88b1810ae908194f07f8db9d"
 uuid = "458c3c95-2e84-50aa-8efc-19380b2a3a95"
-version = "3.5.2+0"
+version = "3.5.4+0"
 
 [[deps.OpenSpecFun_jll]]
 deps = ["Artifacts", "CompilerSupportLibraries_jll", "JLLWrappers", "Libdl"]

Project.toml

@@ -1,7 +1,7 @@
 name = "Yunir"
 uuid = "6ba116df-6904-454d-b214-90038a8281a6"
 authors = ["Al-Ahmadgaid B. Asaad"]
-version = "0.3.0"
+version = "0.2.8"
 
 [deps]
 BioAlignments = "00701ae9-d1dc-5365-b64a-a3a3ebf5695e"

docs/Project.toml

@@ -6,4 +6,5 @@ Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
 DocumenterCitations = "daee34ce-89f3-4625-b898-19384cb65244"
 Kitab = "56988f64-bbe1-4670-be0e-9b8570beea21"
 Makie = "ee78f7c6-11fb-53f2-987a-cfe4a2b5a57a"
+QuranTree = "f647ab69-6f05-4d64-883f-59d0fbe08d2b"
 Yunir = "6ba116df-6904-454d-b214-90038a8281a6"

docs/make.jl

@@ -1,3 +1,7 @@
+using Pkg
+Pkg.develop(PackageSpec(path=dirname(@__DIR__)))
+Pkg.instantiate()
+
 using Documenter
 using DocumenterCitations
 using Yunir
@@ -19,7 +23,7 @@ makedocs(;
         "Home" => "index.md",
         "Basic Utilities" => "man/basic_utilities.md",
         "Orthographical Analysis" => "man/orthography.md",
-        "Text Alignment" => "man/text_alignment.md",
+        # "Text Alignment" => "man/text_alignment.md",
         "Rhytmic Analysis" => "man/rhythmic_analysis.md",
         "Symmetry Analysis" => "man/symmetry_analysis.md",
         "References" => "man/references.md",

docs/src/man/basic_utilities.md

@@ -3,10 +3,6 @@ Basic Utilities
 In this section, we are going to discuss how to use the APIs for dediacritization, normalization, and transliteration.
 ## Dediacritization
 The function to use is `dediac` which works on either Arabic, Buckwalter or custom transliterated characters.
-```@setup abc
-using Yunir
-@transliterator :default
-```
 ```@repl abc
 using Yunir
 

docs/src/man/rhythmic_analysis.md

@@ -1,11 +1,90 @@
 Rhythmic Analysis
 =============
-Pre-Islamic civilization in Arabia is known for their expertise in poetry prior to Qur'an. Such prevalence in Arabic language may invoke some interest in studying the rhythmic signatures of these texts. There are no resources that looked into this computationally until the recent work of [asaadthesis](@citet).
+The prevalence of poetry in Arabic literature necessitates scientific tool to study the rhythmic signatures. Unfortunately, there are no resources for such methodology until the recent work of [asaadthesis](@citet). This section will demonstrate the APIs for doing rhythmic analysis based on the methodologies proposed by [asaadthesis](@citet). To do this, there are two types of text that will be studied, and these are pre-Islamic poetry and the Holy Qur'an.
 
-## Classic Poetry
-Thi
+## Arabic Poetry
+The first data is from a well known author, [Al-Mutanabbi المتنبّي](https://en.wikipedia.org/wiki/Al-Mutanabbi), who authored several poetry including the titled [*'Indeed, every woman with a swaying walk'*](https://www.youtube.com/watch?v=9c1IrQwfYFM), which will be the basis for this section.
+## Loading Data
+The following codes assigns the said poem of Al-Mutanabbi to a variable poem.
+```@example abc
+using Yunir
 
-### References
+poem = """
+    ألا كُلُّ مَاشِيَةِ الخَيْزَلَى ;
+    فِدَى كلِّ ماشِيَةِ الهَيْذَبَى;
+    وَكُلِّ نَجَاةٍ بُجَاوِيَّةٍ;
+    خَنُوفٍ وَمَا بيَ حُسنُ المِشَى;
+    وَلَكِنّهُنّ حِبَالُ الحَيَاةِ;
+    وَكَيدُ العُداةِ وَمَيْطُ الأذَى;
+    ضرَبْتُ بهَا التّيهَ ضَرْبَ القِمَا;
+    رِ إمّا لهَذا وَإمّا لِذا;
+    إذا فَزِعَتْ قَدّمَتْهَا الجِيَادُ;
+    وَبِيضُ السّيُوفِ وَسُمْرُ القَنَا;
+    فَمَرّتْ بِنَخْلٍ وَفي رَكْبِهَا;
+    عَنِ العَالَمِينَ وَعَنْهُ غِنَى;
+    وَأمْسَتْ تُخَيّرُنَا بِالنّقا;
+    بِ وَادي المِيَاهِ وَوَادي القُرَى;
+    وَقُلْنَا لهَا أينَ أرْضُ العِراقِ;
+    فَقَالَتْ وَنحنُ بِتُرْبَانَ هَا;
+    وَهَبّتْ بِحِسْمَى هُبُوبَ الدَّبُو;
+    رِ مُستَقْبِلاتٍ مَهَبَّ الصَّبَا;
+    رَوَامي الكِفَافِ وَكِبْدِ الوِهَادِ;
+    وَجَارِ البُوَيْرَةِ وَادي الغَضَى;
+    وَجَابَتْ بُسَيْطَةَ جَوْبَ الرِّدَا;
+    ءِ بَينَ النّعَامِ وَبَينَ المَهَا;
+    إلى عُقْدَةِ الجَوْفِ حتى شَفَتْ;
+    بمَاءِ الجُرَاوِيّ بَعضَ الصّدَى;
+    وَلاحَ لهَا صَوَرٌ وَالصّبَاحَ،;
+    وَلاحَ الشَّغُورُ لهَا وَالضّحَى;
+    وَمَسّى الجُمَيْعيَّ دِئْدَاؤهَا;
+    وَغَادَى الأضَارِعَ ثمّ الدَّنَا;
+    فَيَا لَكَ لَيْلاً على أعْكُشٍ;
+    أحَمَّ البِلادِ خَفِيَّ الصُّوَى;
+    وَرَدْنَا الرُّهَيْمَةَ في جَوْزِهِ;
+    وَبَاقيهِ أكْثَرُ مِمّا مَضَى;
+    فَلَمّا أنَخْنَا رَكَزْنَا الرّمَاحَ ;
+    بَين مَكارِمِنَا وَالعُلَى;
+    وَبِتْنَا نُقَبّلُ أسْيَافَنَا;
+    وَنَمْسَحُهَا من دِماءِ العِدَى;
+    لِتَعْلَمَ مِصْرُ وَمَنْ بالعِراقِ;
+    ومَنْ بالعَوَاصِمِ أنّي الفَتى;
+    وَأنّي وَفَيْتُ وَأنّي أبَيْتُ;
+    وَأنّي عَتَوْتُ على مَنْ عَتَا;
+    وَمَا كُلّ مَنْ قَالَ قَوْلاً وَفَى;
+    وَلا كُلُّ مَنْ سِيمَ خَسْفاً أبَى;
+    وَلا بُدَّ للقَلْبِ مِنْ آلَةٍ;
+    وَرَأيٍ يُصَدِّعُ صُمَّ الصّفَا;
+    وَمَنْ يَكُ قَلْبٌ كَقَلْبي لَهُ;
+    يَشُقُّ إلى العِزِّ قَلْبَ التَّوَى;
+    وَكُلُّ طَرِيقٍ أتَاهُ الفَتَى;
+    على قَدَرِ الرِّجْلِ فيه الخُطَى;
+    وَنَام الخُوَيْدِمُ عَنْ لَيْلِنَا;
+    وَقَدْ نامَ قَبْلُ عَمًى لا كَرَى;
+    وَكانَ عَلى قُرْبِنَا بَيْنَنَا;
+    مَهَامِهُ مِنْ جَهْلِهِ وَالعَمَى;
+    وَمَنْ جَهِلَتْ نَفْسُهُ قَدْرَهُ;
+    رَأى غَيرُهُ مِنْهُ مَا لا يَرَى
+"""
+```
+## Extracting Syllables
+Now let's try extracting the syllables for the first line. To do this, let's convert the text into a vector of stanzas of the poem. We therefore split the text on the `";\n"` separator, where the `\n` is the code for line break. The function `strip` simply removes the whitespaces before and after each stanza.
+```@example abc
+texts = map(x -> strip(string(x)), split.(poem, ";\n"))
+```
+Next is to initialize the syllabification for each stanza, suppose we want to capture the consonant before and after each vowel to represent one syllable. For example, for the word `basmala`, the syllabification if only the consonant preceding the vowel is considered then we have `ba`, `ma`, and `la`. To specify this configuration for the syllable, we do it as follows:
+```@repl abc
+syllable = Syllable(1, 0, 10)
+```
+Here the first argument represents the number of characters prior to the vowel is considered, the next argument which is 0 is the number of character after the vowel, and 10 the third argument simply mean how many vowels do we need to capture for each word. So that,
+```@repl abc
+r = Syllabification(false, syllable)
+```
+Then,
+```@repl abc
+r(string(split(texts[1], " ")[1]), isarabic=true, first_word=true, silent_last_vowel=false)
+```
+
+## References
 ```@bibliography
 Pages = ["rhythmic_analysis.md"]
 Canonical = false

docs/src/man/symmetry_analysis.md

@@ -2,7 +2,7 @@ Symmetric Analysis
 =============
 The work of [farrin2014structure](@citet)
 
-### References
+## References
 ```@bibliography
 Pages = ["symmetry_analysis.md"]
 Canonical = false

docs/src/man/text_alignment.md

@@ -186,7 +186,7 @@ count_aligned(res2[2,1])
 ```
 ## Visualization
 In this section, we are going to display the alignment by plotting the results.
-```@example abc
+```@repl abc
 using CairoMakie
 f, a, xys = plot(res1, :matches, nchars=60)
 a[1].xlabel = "Shamela0023790"
@@ -202,7 +202,7 @@ The figure above is divided into three subplots arranged in rows. You can think
 We added further customization to the plot, readers are encouraged to explore the API.
 
 As for the plot of insertions of characters, we have:
-```@example abc
+```@repl abc
 f, a, xys = plot(res1, :insertions, nchars=60)
 a[1].xlabel = "Shamela0023790"
 a[1].xlabelsize = 20
@@ -213,7 +213,7 @@ a[3].xticks = 0:2:unique(xys[2][1])[end]
 f
 ```
 For deletions, we have:
-```@example abc
+```@repl abc
 f, a, xys = plot(res1, :deletions, nchars=60)
 a[1].xlabel = "Shamela0023790"
 a[1].xlabelsize = 20
@@ -224,7 +224,7 @@ a[3].xticks = 0:2:unique(xys[2][1])[end]
 f
 ```
 And for mismatches, we have
-```@example abc
+```@repl abc
 f, a, xys = plot(res1, :mismatches, nchars=60)
 a[1].xlabel = "Shamela0023790"
 a[1].xlabelsize = 20

docs/src/man/working_with_quran.md

@@ -0,0 +1,142 @@
+using DataFrames
+using QuranTree
+using Makie
+using Colors
+using CairoMakie
+using MakieThemes
+using Yunir
+
+CairoMakie.activate!(type = "svg")
+active_theme = :dust
+
+if active_theme == :earth
+    Makie.set_theme!(ggthemr(:earth))
+    current_theme = Dict(
+        :background => "#36312C",
+        :text       => ["#555555", "#F8F8F0"],
+        :line       => ["#ffffff", "#827D77"],
+        :gridline   => "#504940",
+        :swatch     => ["#F8F8F0", "#DB784D", "#95CC5E", "#E84646", "#F8BB39", "#7A7267", "#E1AA93", "#168E7F", "#2B338E"],
+        :gradient   => ["#7A7267", "#DB784D"]
+    )
+elseif active_theme == :dust
+    Makie.set_theme!(ggthemr(:dust))
+    current_theme = Dict(
+        :background => "#FAF7F2",
+        :text       => ["#5b4f41", "#5b4f41"],
+        :line       => ["#8d7a64", "#8d7a64"],
+        :gridline   => "#E3DDCC",
+        :swatch     => ["#555555", "#db735c", "#EFA86E", "#9A8A76", "#F3C57B", "#7A6752", "#2A91A2", "#87F28A", "#6EDCEF"],
+        :gradient   => ["#F3C57B", "#7A6752"]
+    )
+else
+    error("No active_theme=" * string(active_theme))
+end;
+colors = [parse(Color, i) for i in current_theme[:swatch]]
+crps, tnzl = load(QuranData());
+crps_tbl = table(crps)
+tnzl_tbl = table(tnzl)
+
+function last_syllable(bw_texts)
+    bw1_texts = Array{String,1}()
+    bw2_texts = Array{String,1}()
+    bw3_texts = Array{String,1}()
+    for bw_text in bw_texts
+        @info bw_text
+        push!(bw1_texts, replace(bw_text[end-3:end-2], "o" => ""))
+        push!(bw2_texts, replace(bw_text[end-3:end-1], "o" => ""))
+        push!(bw3_texts, replace(bw_text[end-4:end-1], "o" => ""))
+    end
+    return bw1_texts, bw2_texts, bw3_texts
+end
+
+function encode_to_number(ychars::Array{String})
+    y = unique(ychars)
+    y_dict = Dict()
+    for i in eachindex(y)
+        if i == 1
+            y_dict[y[i]] = i
+        end
+        
+        if y[i] .∈ Ref(Set(keys(y_dict)))
+            continue
+        else
+            y_dict[y[i]] = i
+        end
+    end
+    y_vec = Array{Int64,1}()
+    for i in ychars
+        push!(y_vec, y_dict[i])
+    end
+    return y_vec, y_dict # scaling to 100 since algo will fail saying range step cannot 0
+end
+
+bw_texts = verses(crps_tbl[1])
+y1_chars, y2_chars, y3_chars = last_syllable(bw_texts)
+y1, y1_dict = encode_to_number(y1_chars)
+y2, y2_dict = encode_to_number(y2_chars)
+y3, y3_dict = encode_to_number(y3_chars)
+
+f = Figure(resolution=(800, 800));
+a1 = Axis(f[1, 1], 
+    ylabel="Last Pronounced Syllable\n\n\n",
+    title="Surah Al-Fatihah\n\n",
+    yticks=(unique(y1), unique(string.(y1_chars))),
+    xticks = collect(eachindex(y1_chars))
+)
+# ylims!(a1, 100, maximum(y1) .+1)
+
+a2 = Axis(f[2, 1], 
+    ylabel="3 Characters\n\n\n",
+    yticks=(unique(y2), unique(string.(y2_chars))),
+    xticks = collect(eachindex(y2_chars))
+)
+
+a3 = Axis(f[3, 1], 
+    ylabel="3-4 Characters\n\n",
+    yticks=(unique(y3), unique(string.(y3_chars))),
+    xticks = collect(eachindex(y3_chars))
+)
+
+lines!(a1, collect(eachindex(y1_chars)), y1)
+hidexdecorations!(a1)
+lines!(a2, collect(eachindex(y2_chars)), y2)
+hidexdecorations!(a2)
+lines!(a3, collect(eachindex(y3_chars)), y3)
+
+f
+
+bw_texts = verses(crps_tbl[55])
+y1_chars, y2_chars, y3_chars = last_syllable(bw_texts)
+y1, y1_dict = encode_to_number(y1_chars)
+y2, y2_dict = encode_to_number(y2_chars)
+y3, y3_dict = encode_to_number(y3_chars)
+
+# f = Figure(resolution=(500, 500));
+a1 = Axis(f[1, 2], 
+    # ylabel="Last Syllable",
+    title="Surah Ar-Rahman\n\n",
+    yticks=(unique(y1), unique(string.(y1_chars))),
+    # xticks = collect(eachindex(y1_chars))
+)
+
+a2 = Axis(f[2, 2], 
+    # ylabel="2-3 Characters",
+    yticks=(unique(y2), unique(string.(y2_chars))),
+    # xticks = collect(eachindex(y2_chars))
+)
+
+a3 = Axis(f[3, 2], 
+    # ylabel="3-4 Characters",
+    # yticks=(collect(eachindex(y3_chars)), string.(y3_chars)),
+    # xticks = collect(eachindex(y3_chars))
+)
+
+lines!(a1, collect(eachindex(y1_chars)), y1)
+hidexdecorations!(a1)
+lines!(a2, collect(eachindex(y2_chars)), y2)
+hidexdecorations!(a2)
+lines!(a3, collect(eachindex(y3_chars)), y3)
+f
+
+# save("plots/plot_rhythmic1.svg", f)