Merge pull request #6 from neelsmith/dev

Dev

Project.toml

@@ -1,7 +1,7 @@
 name = "PolytonicGreek"
 uuid = "72b824a7-2b4a-40fa-944c-ac4f345dc63a"
 authors = ["nsmith "]
-version = "0.1.0"
+version = "0.1.1"
 
 [deps]
 DocStringExtensions = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"

pluto/Manifest.toml

@@ -7,34 +7,118 @@ uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
 
+[[Distributed]]
+deps = ["Random", "Serialization", "Sockets"]
+uuid = "8ba89e20-285c-5b6f-9357-94700520ee1b"
+
+[[DocStringExtensions]]
+deps = ["LibGit2", "Markdown", "Pkg", "Test"]
+git-tree-sha1 = "50ddf44c53698f5e784bbebb3f4b21c5807401b1"
+uuid = "ffbed154-4ef7-542d-bbb7-c09d3a79fcae"
+version = "0.8.3"
+
+[[Documenter]]
+deps = ["Base64", "Dates", "DocStringExtensions", "IOCapture", "InteractiveUtils", "JSON", "LibGit2", "Logging", "Markdown", "REPL", "Test", "Unicode"]
+git-tree-sha1 = "b7715ae18be02110a8cf9cc8ed2ccdb1e3e3aba2"
+uuid = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
+version = "0.26.1"
+
+[[IOCapture]]
+deps = ["Logging"]
+git-tree-sha1 = "377252859f740c217b936cebcd918a44f9b53b59"
+uuid = "b5f81e59-6552-4d32-b1f0-c071b021bf89"
+version = "0.1.1"
+
+[[InteractiveUtils]]
+deps = ["Markdown"]
+uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
+
+[[JSON]]
+deps = ["Dates", "Mmap", "Parsers", "Unicode"]
+git-tree-sha1 = "81690084b6198a2e1da36fcfda16eeca9f9f24e4"
+uuid = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
+version = "0.21.1"
+
+[[LibGit2]]
+deps = ["Printf"]
+uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
+
+[[Libdl]]
+uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
+
 [[Logging]]
 uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
 
 [[Markdown]]
 deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 
+[[Mmap]]
+uuid = "a63ad114-7e13-5084-954f-fe012c677804"
+
+[[Orthography]]
+deps = ["DocStringExtensions", "Documenter", "Test"]
+git-tree-sha1 = "53ae798c10043b4a990d1557a594388b0e07a57a"
+uuid = "0b4c9448-09b0-4e78-95ea-3eb3328be36d"
+version = "0.4.1"
+
+[[Parsers]]
+deps = ["Dates"]
+git-tree-sha1 = "50c9a9ed8c714945e01cd53a21007ed3865ed714"
+uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
+version = "1.0.15"
+
+[[Pkg]]
+deps = ["Dates", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "UUIDs"]
+uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
+
 [[PlutoUI]]
 deps = ["Base64", "Dates", "Logging", "Markdown", "Random", "Suppressor"]
 git-tree-sha1 = "e453271bb6e5493e1fd98d72752ab1a9ee1eb6a6"
 uuid = "7f904dfe-b85e-4ff6-b463-dae2292396a8"
 version = "0.6.11"
 
+[[PolytonicGreek]]
+deps = ["DocStringExtensions", "Documenter", "Orthography", "Test", "Unicode"]
+git-tree-sha1 = "a943a5557c26473dc01d89c6528a4e51b03fa833"
+repo-rev = "main"
+repo-url = "https://github.com/neelsmith/PolytonicGreek.jl"
+uuid = "72b824a7-2b4a-40fa-944c-ac4f345dc63a"
+version = "0.1.0"
+
 [[Printf]]
 deps = ["Unicode"]
 uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 
+[[REPL]]
+deps = ["InteractiveUtils", "Markdown", "Sockets"]
+uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
+
 [[Random]]
 deps = ["Serialization"]
 uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 
+[[SHA]]
+uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
+
 [[Serialization]]
 uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
 
+[[Sockets]]
+uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
+
 [[Suppressor]]
 git-tree-sha1 = "a819d77f31f83e5792a76081eee1ea6342ab8787"
 uuid = "fd094767-a336-5f1f-9728-57cf17d0bbfb"
 version = "0.2.0"
 
+[[Test]]
+deps = ["Distributed", "InteractiveUtils", "Logging", "Random"]
+uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[[UUIDs]]
+deps = ["Random", "SHA"]
+uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
+
 [[Unicode]]
 uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"

pluto/Project.toml

@@ -1,2 +1,9 @@
 [deps]
+Markdown = "d6f4376e-aef5-505a-96c1-9c027394607a"
 PlutoUI = "7f904dfe-b85e-4ff6-b463-dae2292396a8"
+PolytonicGreek = "72b824a7-2b4a-40fa-944c-ac4f345dc63a"
+Unicode = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
+
+[compat]
+PlutoUI = "0.6"
+PolytonicGreek = "0.1"

pluto/literaryGreek.jl

@@ -4,22 +4,177 @@
 using Markdown
 using InteractiveUtils
 
+# This Pluto notebook uses @bind for interactivity. When running this notebook outside of Pluto, the following 'mock version' of @bind gives bound variables a default value (instead of an error).
+macro bind(def, element)
+    quote
+        local el = $(esc(element))
+        global $(esc(def)) = Core.applicable(Base.get, el) ? Base.get(el) : missing
+        el
+    end
+end
+
 # ╔═╡ 07723886-6564-11eb-2f61-65638d4bfb6c
 begin
 	using Pkg
 	Pkg.activate(".")
-	# Pkg.add("PolytonicGreek")
-	# using PolytonicGreek
+	Pkg.instantiate()
+
+	using Markdown
+	using PlutoUI
+	using Unicode
+	using PolytonicGreek
 end
 
 
 # ╔═╡ 3da4ca0a-6565-11eb-1b92-b9c1553f3223
 md"Define environment in hidden cell."
 
 # ╔═╡ ee5aa2c2-6563-11eb-1f3a-6b907e19fd31
-md"Walkthrough of `LiteraryGreekOrthography`"
+md"# Introduction to `LiteraryGreekOrthography`"
+
+# ╔═╡ 7dcc46bc-656a-11eb-0f29-01dd8a59d645
+md"""
+Load the library:
+
+```julia
+using PolytonicGreek
+```
+
+"""
+
+# ╔═╡ 937d959e-656a-11eb-2303-7da51f1b0482
+md"""
+
+## Tokenization 
+
+Tokenize a string:
+
+```julia
+str = "Μῆνιν ἄειδε, θεά, Πηληϊάδεω Ἀχιλῆος,"
+tkns = tokenizeLiteraryGreek(str)
+```
+"""
+
+# ╔═╡ 5c89aa08-656a-11eb-3d95-cb47ee3892aa
+str = "Μῆνιν ἄειδε, θεά, Πηληϊάδεω Ἀχιλῆος,"
+
+# ╔═╡ 6d3f90a6-656a-11eb-14d9-2b229f0d6a11
+tkns = tokenizeLiteraryGreek(str)
+
+# ╔═╡ c9fb0c94-656a-11eb-2c35-5189c1360656
+md"Tokens have a string value and a category."
+
+# ╔═╡ d3c8c950-656a-11eb-1ff4-ebd936142caf
+begin
+	items = map(t -> "1. **" * t.text * "** (*$(t.tokencategory)*)", tkns)
+	itemstring = join(items, "\n")
+	Markdown.parse("**Tokens**:\n" * itemstring)
+end
+
+# ╔═╡ e0518030-656b-11eb-0258-9756bc71d49f
+md"""
+## Orthographic categorization and validation
+
+All characters are precomposed in Unicode form NFKC
+"""
+
+# ╔═╡ 081371e6-656c-11eb-2f79-bf0067480cd6
+md"Recognize category of a string"
+
+# ╔═╡ 131640be-656c-11eb-1e3f-7967f02c46a4
+PolytonicGreek.isPunctuation(";")
+
+# ╔═╡ 2515ee86-656c-11eb-1bcf-bd862a853538
+PolytonicGreek.isAlphabetic("μῆνιν")
+
+# ╔═╡ 14d71e8a-656e-11eb-2eee-092306f81a29
+md"""
+
+---
+"""
+
+# ╔═╡ 1c93f238-656e-11eb-11ed-5df25da03158
+md"All recognized punctuation characters:"
+
+# ╔═╡ 2557a112-656e-11eb-2046-9361e24dcccc
+PolytonicGreek.punctuation()
+
+# ╔═╡ b8a3cb52-656a-11eb-0523-034cb44b8955
+md"""
+
+All recognized alphabetic characters (in Unicode order):
+"""
+
+# ╔═╡ 9bc2dfda-656c-11eb-284e-5750c39f56db
+md"""
+
+*Display one character per line*: $(@bind byline CheckBox())
+
+"""
+
+# ╔═╡ 07d856cc-6573-11eb-2f25-af7805e01de6
+md">Some formatting functions"
+
+# ╔═╡ 1b37606a-6572-11eb-265d-796b2e421c17
+function ucat(cp) 
+	if Unicode.isnumeric(cp)
+		"numeric"
+	elseif Unicode.ispunct(cp)
+		"punctuation"
+	elseif Unicode.isletter(cp)
+		"letter"
+	else
+		"uncrecognized category"
+	end
+end
+
+
+# ╔═╡ c35e1238-656e-11eb-2092-85f48cdc3bab
+function stringinfo(s)
+	#string(s,  " (" , length(s) , ")")
+
+
+	uc = Unicode.islowercase(s[begin]) ? "lowercase" : "uppercase"
+
+	string("**", s, "** (*Unicode ", codepoint(s[begin]) , ", ", ucat(s[begin]), " ", uc,  "*)")
+
+end
+
+# ╔═╡ 56830e2c-656c-11eb-0a42-b59d378ee995
+begin
+	if byline
+
+		chlist = []
+		for ch in PolytonicGreek.alphabetic() 
+			push!(chlist, "- " * stringinfo(ch))
+		end
+		Markdown.parse(join(chlist,"\n"))
+	else
+		md"$(PolytonicGreek.alphabetic())"
+
+	end
+end
 
 # ╔═╡ Cell order:
 # ╟─3da4ca0a-6565-11eb-1b92-b9c1553f3223
 # ╟─07723886-6564-11eb-2f61-65638d4bfb6c
 # ╟─ee5aa2c2-6563-11eb-1f3a-6b907e19fd31
+# ╟─7dcc46bc-656a-11eb-0f29-01dd8a59d645
+# ╟─937d959e-656a-11eb-2303-7da51f1b0482
+# ╟─5c89aa08-656a-11eb-3d95-cb47ee3892aa
+# ╟─6d3f90a6-656a-11eb-14d9-2b229f0d6a11
+# ╟─c9fb0c94-656a-11eb-2c35-5189c1360656
+# ╟─d3c8c950-656a-11eb-1ff4-ebd936142caf
+# ╟─e0518030-656b-11eb-0258-9756bc71d49f
+# ╟─081371e6-656c-11eb-2f79-bf0067480cd6
+# ╠═131640be-656c-11eb-1e3f-7967f02c46a4
+# ╠═2515ee86-656c-11eb-1bcf-bd862a853538
+# ╟─14d71e8a-656e-11eb-2eee-092306f81a29
+# ╟─1c93f238-656e-11eb-11ed-5df25da03158
+# ╠═2557a112-656e-11eb-2046-9361e24dcccc
+# ╟─b8a3cb52-656a-11eb-0523-034cb44b8955
+# ╟─9bc2dfda-656c-11eb-284e-5750c39f56db
+# ╟─56830e2c-656c-11eb-0a42-b59d378ee995
+# ╟─07d856cc-6573-11eb-2f25-af7805e01de6
+# ╟─c35e1238-656e-11eb-2092-85f48cdc3bab
+# ╟─1b37606a-6572-11eb-265d-796b2e421c17

src/ortho.jl

@@ -43,8 +43,9 @@ function alphabetic()
     '\u1f5d' ; '\u1f5f':'\u1f7d' ;
     '\u1f80':'\u1faf'; '\u1fb2':'\u1fb4' ;
     '\u1fb6':'\u1fbc'; 
-    '\u1fc5':'\u1fcc';
-    '\u1fd2':'\u1fd3'; '\u1fd6':'\u1fdc';
+	'\u1fc2':'\u1fc4';
+    '\u1fc6':'\u1fcc';
+    '\u1fd2':'\u1fd3'; '\u1fd6':'\u1fdb';
     '\u1fe2':'\u1fe7';
     '\u1fea':'\u1fec';
     '\uf1f2':'\u1ff4'; '\u1ff6':'\u1ffc'
@@ -74,6 +75,10 @@ end
 function isAlphabetic(s::AbstractString)
     chlist = split(s,"")
     alphas = alphabetic()
+    tfs = []
+    for i in collect(eachindex(s)) 
+        push!(tfs, occursin(s[i], alphas))
+    end
     tfs = map(c -> occursin(c, alphas), chlist)
     nogood = false in tfs