added submodule content, work on uh words in progress

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "heonian-content"]
+	path = heonian-content
+	url = https://git.succubi.services/lustlion/heonian-content

converter.lua

@@ -1,8 +1,20 @@
-require "R2H2"
+require "r2h2_modified"
+
+function add_word(str)
+	local add = true
+	for _, v in pairs(word_list) do
+		if v == str then
+			add = false
+		end
+	end
+	if add then 
+		table.insert(word_list,str) 
+	end
+end
 
 
 function strip_symbols(str)
-	local symbol_table = "'~()!?:></.\t"
+	local symbol_table = "'~()!?:></.,\t…"
 	for i=1, #symbol_table do
 		while string.find(str, "%"..string.sub(symbol_table,i,i)) do
 			str = string.gsub(str, "%"..string.sub(symbol_table,i,i),"")
@@ -11,15 +23,29 @@ function strip_symbols(str)
 	return str
 end
 
-function reverse_verbs(str)
+function replace_symbols(str)
-	while string.find(str, "kanya") do
+	while string.find(str, "%-") do
-		str = string.gsub(str, "kanya","ku")
+		str = string.gsub(str, "%-"," ")
 	end
-	while string.find(str, "kome") do
+	return str
-		str = string.gsub(str, "kome","ku")
+end
+
+function find_n_replace(str,find,repl)
+	while string.find(str, find) do
+		str = string.gsub(str, find, repl)
 	end
 	return str
 end
+function revert_verbs(str)
+	str = find_n_replace(str, "kanya","ku")
+	str = find_n_replace(str, "kome","ku")
+	str = find_n_replace(str, "kupash","ku")
+	str = find_n_replace(str, "kudash","ku")
+	str = find_n_replace(str, "kubash","ku")
+	str = find_n_replace(str, "kutash","ku")
+	str = find_n_replace(str, "faku","ku")
+	return str
+end
 
 function apply_html(path)
 	-- copy
@@ -28,23 +54,36 @@ function apply_html(path)
 		
 	file:close()
 	-- paste
-	print(html)	
+	apply(html)	
+end
+
+function apply(text)
+	--print(text)	
 end
 
 function convo_image(string,alt_text)
 	if string then
 		apply_html("html/convo/header/image/start.html")
-		print(string)
+		apply(string)
 		apply_html("html/convo/header/image/middle.html")
-		print(alt_text)
+		apply(alt_text)
 		apply_html("html/convo/header/image/end.html")
 	end
 end
 
+function convo_notes(string)
+	apply_html("html/convo/middle.html")
+	if string then
+		apply_html("html/convo/notes/start.html")
+		apply(string)
+		apply_html("html/convo/notes/end.html")
+	end
+end
+
 function convo_date(string)
 	if string then
 		apply_html("html/convo/header/date/start.html")
-		print(string)
+		apply(string)
 		apply_html("html/convo/header/date/end.html")
 	end
 end
@@ -58,7 +97,7 @@ end
 
 function convo_header_end()
 	if header then
-		header = false
+		header = false		
 		apply_html("html/convo/header/end.html")
 	end
 end
@@ -78,6 +117,10 @@ end
 function convo_end()
 	convo_header_end()
 	if convo then 
+		if not notes then 
+			apply_html("html/convo/middle.html")
+		end
+		notes = 	false
 		apply_html("html/convo/end.html")
 		convo = false
 	end
@@ -97,6 +140,7 @@ local p = 0
 local s = 0
 local convo = false
 local header = false
+local notes = false
 local green = true
 local skip = 1
 local user = {}
@@ -114,18 +158,32 @@ while p ~= nil do
 				-- its tabbed so its spoken?
 				convo_start()
 				apply_html("html/convo/text/start_roman.html")
-				print(string.sub(text,p+2,np-1))
+				apply(string.sub(text,p+2,np-1))
-					--content = content .. " " .. reverse_verbs(strip_symbols(string.sub(text,p+2,np-1))) 
+				content = content .. " " .. string.sub(text,p+2,np-1) 
-					--print("\n"..reverse_verbs(strip_symbols(string.sub(text,p+2,np-1))))
 				apply_html("html/convo/text/end.html")
 				-- heonian
 				apply_html("html/convo/text/start_heonian.html")
-				print(convertToHeonian(string.sub(text,p+2,np-1)).."")
+				apply(mod_convertToHeonian(string.sub(text,p+2,np-1)).."")
 				apply_html("html/convo/text/end.html")
+			elseif string.sub(text,p+1,p+1) == "h" then
+				-- spoken but forced to h
+				convo_start()
+				apply_html("html/convo/text/start_raw.html")
+				apply(mod_convertToHeonian(string.sub(text,p+3,np-1)).."")
+				apply_html("html/convo/text/end.html")	
+			elseif string.sub(text,p+1,p+1) == "r" then
+				-- spoken but forced to r
+				convo_start()
+				apply_html("html/convo/text/start_raw.html")
+				apply(string.sub(text,p+3,np-1))
+				apply_html("html/convo/text/end.html")			
 			elseif string.sub(text,p+1,p+1) == "i" then -- independant image, no username
 				convo_start(green)			
 				convo_header_start() 
 				convo_image(string.sub(text,p+3,np-1))
+			elseif string.sub(text,p+1,p+1) == "!" then -- independant image, no username
+				convo_notes(string.sub(text,p+3,np-1))
+				notes = true
 			else
 				--  new user name
 				convo_end()
@@ -153,7 +211,7 @@ while p ~= nil do
 				
 				-- print name
 				apply_html("html/convo/header/name/start.html")
-				print(string.sub(text,p+1,np-1))
+				apply(string.sub(text,p+1,np-1))
 				apply_html("html/convo/header/name/end.html")
 				
 				-- lets check for dates
@@ -179,9 +237,21 @@ end
 apply_html("html/convo/end.html")
 
 -- fourth lets make word lists
+-- process contents
+content = strip_symbols(content)
+content = replace_symbols(content)
+content = revert_verbs(content)
+
+word_list = {}
+while string.find(content, " ") do
+	add_word(string.sub(content,  0, string.find(content, " ")))
+	content = string.sub(content, string.find(content, " ")+1)
+	--print(string.find(content, " "))
+end
+
+for i=1, #word_list do
+	print(word_list[i])
+end
 
 -- lets end the html
 apply_html("html/end.html")
-
-
--- print(content)

heonian-content

@@ -0,0 +1 @@
+Subproject commit 19de5190c0876edbeb307f09b540a2c4d111b783

html/convo/end.html

@@ -1,2 +1 @@
-            </div>
         </div>

html/convo/middle.html

@@ -0,0 +1 @@
+            </div>

html/convo/notes/end.html

@@ -0,0 +1,2 @@
+</p>
+            </div>

html/convo/notes/start.html

@@ -0,0 +1,2 @@
+            <div class="notes">
+                <p>

html/convo/text/start_raw.html

@@ -0,0 +1 @@
+                <p class="convo-raw">

r2h2_modified.lua

@@ -0,0 +1,212 @@
+--functions
+
+-- DATA
+-- vowels
+vowel_table = 					{"a","e","i","o","u"}
+symbol_vowel = 				{"","","","",""}
+symbol_extending_vowel = 		{"","","","",""}
+-- consonants
+consonant_table = 				{"g","sh","r","ny","ch","n","y","f","t","k","w","l","p","b","d","h","m"}
+symbol_consonant = 			{"","","","","","","","","","","","","","","","",""}
+symbol_extending_consonant = 	{"","","","","","","","","","","","","","","","",""}
+-- composites
+composing_consonant_table =		{"g","sh","r","ny","ch","m","y","f","t","k","w","l","p","b","d","h"}
+symbol_composite = {
+							{"","","","","","","","","","","","","","","",""},
+							{"","","","","","","","","","","","","","","",""},
+							{"","","","","","","","","","","","","","","",""},
+							{"","","","","","","","","","","","","","","",""},
+							{"","","","","","","","","","","","","","","",""}
+}
+
+-- program start
+function mod_convertToHeonian(text)
+	local step = true -- this is set to false when a conclusion has been reached
+	local transcribed = false
+	local transcribed_text = ""
+	
+	local debug = false
+	local autocopy = false
+	
+	for _, v in pairs(arg) do	
+		if v == "-v" or v == "--verbose" then debug = true end
+		if v == "-c" or v == "--copy" then autocopy = true end
+	end		
+	
+	-- if its necessary to run the script, then we continue :D
+	if step  then
+	-- prepare text
+		-- 1. add syllable marker at start if it isn't already present.
+			if string.sub(text,1,1) ~= "." then text = "." .. text end
+		-- 2. turn [x] into [ksh]
+			text = string.gsub(text,"x","ksh")
+		-- 3. turn [z] into [dsh]
+			text = string.gsub(text,"z","d.sh")
+		-- 4. turn [j] into [y]
+			text = string.gsub(text,"j","y")
+	
+	-- read input and transcribe	
+		-- debug log
+		if debug then print("") end
+		if debug then print("src: ".. text) end
+		if debug then PrintPosition(text) end
+				
+		-- sort through all the letters
+		local i = 1
+		while  i <  string.len(text)+1 do
+			local pos = i
+			-- know current pos, since we will be modifying i but still evaluating from the position
+			local char_step = true 
+			-- this is false when a conclusion has been reached about what symbol does the next segment correspond to
+			local debug_s = ""
+			-- debug string
+			local new_syllable = false 
+			-- this is true when a new syllable begins, and is used to distinguish normal vowels and consonants from trailing ones
+			
+			if i == 1 then new_syllable = true end
+			
+			if string.sub(text,i,i) == "\t" 
+			or string.sub(text,i,i) == "-" then  -- check if its an unsupported symbol to skip it.
+				-- adjust i
+				i = i + 1
+				pos = i
+				char_step = false
+			end
+			-- init checkup
+			if string.sub(text,i,i) == "." 
+			or string.sub(text,i,i) == "'"
+			or string.sub(text,i,i) == " "
+			or string.sub(text,i,i) == "’" then  -- this forces the new syllable, since . is the syllable separator, also skips the symbol and repositions
+				if string.sub(text,i,i) == " " then -- spaces are exception
+					transcribed_text = transcribed_text .. " "
+					new_syllable = true
+				end				
+				-- debug log
+				if debug then print("") end
+				if debug then print(" @[".. tostring(i).."]"..debug_s.." new syllable MARKER found") end
+				-- start syllable
+				new_syllable = true
+				debug_s = ""
+				-- adjust i
+				i = i + 1
+				-- debug log
+				if debug then print("    >>> adjusting by (1) from [".. pos .. "] to [".. i .. "]" ) end
+				-- adjust pos
+				pos = i
+			end
+				
+			-- debug log
+			if debug then print("") end
+			if debug then print(" @[".. tostring(i).."]"..debug_s.." checking string: ".. string.sub(text,i,i)) end -- debug print positional info
+			
+			-- lets check if it is a composite
+			if char_step == true then
+				local cons_id = 0
+				local length = 0	
+				-- check if its valid consonant for a composite
+				for _, consonant in pairs(composing_consonant_table) do
+					cons_id = cons_id + 1
+					-- get consonant length its checking against, so we can properly compare.
+					length = string.len(consonant)
+					-- debug log 
+					--if debug then print("     checking composite consonant: " .. composing_consonant_table[cons_id]) end
+					if string.sub(text,i,i+length-1) == consonant then
+						-- debug log 
+						if debug then print("    (!) valid consonant: " .. composing_consonant_table[cons_id]) end
+						-- check if its a valid vowel AFTER the valid consonant, while sorting through all vowels
+						local vowel_id = 0
+						for _, vowel in pairs(vowel_table) do		
+							vowel_id = vowel_id + 1
+							--if debug then print("        checking composite: " .. composing_consonant_table[cons_id]..vowel_table[vowel_id]) end
+							if string.sub(text,i+length,i+length) == vowel then	
+								-- adjust by consonant length + vowel
+								i = i + string.len(consonant) + 1 
+								-- debug log 
+								if debug then print("    (!) valid composite: " .. consonant .. vowel ..", length: "..length+1) end
+								if debug then print("    >>> adjusting by ("  .. tostring(length+1) .. ") from [".. pos .. "] to [".. i .. "]" ) end
+								-- transcribe; conclude;
+								transcribed_text = transcribed_text .. symbol_composite[vowel_id][cons_id]
+								char_step = false
+								break
+							end
+						end
+						-- no need to check for more consonants if one is valid
+						break
+					end
+				end
+				if debug then if char_step ~= false then print("    [!] invalid composite") end end
+			end
+			
+			-- lets check if it is a non composite vowel
+			if char_step == true then
+				local id = 0
+				local length = 0	
+				for _, vowel in pairs(vowel_table) do
+					id = id+ 1
+					-- get vowel length its checking against, so we can properly compare.
+					length = string.len(vowel)
+					-- debug log 
+					--if debug then print("     checking standalone vowel: " .. vowel_table[id]) end
+					if string.sub(text,i,i+length-1) == vowel then
+						i = i + string.len(vowel) 
+						-- debug log 
+						if debug then print("    (!) valid vowel: " .. vowel_table[id]) end
+						if debug then print("    >>> adjusting by ("  .. tostring(length) .. ") from [".. pos .. "] to [".. i .. "]" ) end
+						-- transcribe; conclude;
+						local table = nil
+						if new_syllable then
+							table = symbol_vowel
+						else
+							table = symbol_extending_vowel
+						end
+						transcribed_text = transcribed_text .. table[id]
+						char_step = false
+						break
+					end
+				end
+			end
+			
+			
+			-- lets check if it is a non composite consonant
+			if char_step == true then
+				local id = 0
+				local length = 0	
+				for _, consonant in pairs(consonant_table) do
+					id = id+ 1
+					-- get consonant length its checking against, so we can properly compare.
+					length = string.len(consonant)
+					-- debug log 
+					--if debug then print("     checking standalone consonant: " .. consonant_table[id]) end
+					if string.sub(text,i,i+length-1) == consonant then
+						i = i + string.len(consonant) 
+						-- debug log 
+						if debug then print("    (!) valid consonant: " .. consonant_table[id]) end
+						if debug then print("    >>> adjusting by ("  .. tostring(length) .. ") from [".. pos .. "] to [".. i .. "]" ) end
+						-- transcribe; conclude;
+						local table = nil
+						if new_syllable then
+							table = symbol_consonant
+						else
+							table = symbol_extending_consonant
+						end
+						transcribed_text = transcribed_text .. table[id]
+						char_step = false
+						break
+					end
+				end
+			end
+					
+			-- if no idea, move on, and just be confused. prints ?
+			if char_step == true then
+				-- debug log
+				if debug then print("    [!] no idea; moving on to next [".. pos + 1 .."]") end
+				-- no idea
+				transcribed_text = transcribed_text .. string.sub(text,i,i)
+				i = i + 1
+				-- debug log
+				if debug then print("    >>> adjusting by (1) from [".. pos .. "] to [".. i .. "]" ) end
+			end
+		end
+		return transcribed_text 
+	end
+end