497 lines
12 KiB
Lua
497 lines
12 KiB
Lua
require "r2h2_modified"
|
|
require "color"
|
|
|
|
words = dofile("heonian-content/words.lua")
|
|
|
|
input = arg[1] or "input.txt"
|
|
|
|
function apply(text)
|
|
print(text)
|
|
end
|
|
|
|
function printD(...)
|
|
io.stderr:write(
|
|
effectText(
|
|
EFFECT.Bold,
|
|
colorText(
|
|
COLOR.HighPurple,
|
|
"\tDEBUG:\t"
|
|
)
|
|
) ..
|
|
colorText(
|
|
COLOR.HighPurple,
|
|
table.unpack({...}) , "\n"
|
|
)
|
|
)
|
|
end
|
|
|
|
function printW(...)
|
|
io.stderr:write(
|
|
effectText(
|
|
EFFECT.Bold,
|
|
colorText(
|
|
COLOR.HighYellow,
|
|
"\t WARN:\t"
|
|
)
|
|
) ..
|
|
colorText(
|
|
COLOR.HighYellow,
|
|
table.unpack({...}) .. "\n"
|
|
)
|
|
)
|
|
end
|
|
|
|
function printE(...)
|
|
io.stderr:write(
|
|
effectText(
|
|
EFFECT.Bold,
|
|
colorText(
|
|
COLOR.HighRed,
|
|
"\tERROR:\t"
|
|
)
|
|
) ..
|
|
colorText(
|
|
COLOR.HighRed,
|
|
table.unpack({...}) .. "\n"
|
|
)
|
|
)
|
|
end
|
|
|
|
function process_content(content)
|
|
content = content .. " "
|
|
for i=1, 2 do
|
|
if i == 1 then
|
|
apply_html("html/convo/text/start_roman.html")
|
|
else
|
|
apply_html("html/convo/text/start_heonian.html")
|
|
|
|
end
|
|
|
|
local ac = check_symbol(content)
|
|
while string.find(ac, " ") do
|
|
local new_word = string.sub(ac, 0, string.find(ac, " ")-1)
|
|
local indicators = {}
|
|
|
|
if i == 1 then
|
|
print_text = new_word
|
|
else
|
|
print_text = mod_convertToHeonian(new_word)
|
|
end
|
|
|
|
new_word = strip_symbols(new_word)
|
|
new_word, indicators = revert_verbs(new_word, indicators)
|
|
new_word, indicators = revert_nouns(new_word,indicators)
|
|
new_word, indicators = categorize_word(new_word,indicators)
|
|
add_word(new_word)
|
|
|
|
local html_stuff = [[
|
|
<span
|
|
class="clickable"
|
|
onclick="showPopup('REPLACE_WORD','REPLACE_SEARCH','REPLACE_DATA')"
|
|
onmouseover="checkHover('REPLACE_WORD','REPLACE_SEARCH',this,'REPLACE_DATA')"
|
|
onmouseout="clearHover()">
|
|
REPLACE_PRINT
|
|
</span>
|
|
]]
|
|
|
|
local REPLACE_PRINT = print_text
|
|
while string.find(html_stuff, "REPLACE_PRINT") do
|
|
html_stuff = string.gsub(html_stuff, "REPLACE_PRINT", REPLACE_PRINT)
|
|
end
|
|
|
|
local REPLACE_WORD = print_text
|
|
while string.find(REPLACE_WORD, "%\'") do
|
|
REPLACE_WORD = string.gsub(REPLACE_WORD, "%\'", "$")
|
|
end
|
|
while string.find(REPLACE_WORD, "%$") do
|
|
REPLACE_WORD = string.gsub(REPLACE_WORD, "%$", "\\\'")
|
|
end
|
|
while string.find(html_stuff, "REPLACE_WORD") do
|
|
html_stuff = string.gsub(html_stuff, "REPLACE_WORD", REPLACE_WORD)
|
|
end
|
|
|
|
local REPLACE_SEARCH = new_word
|
|
while string.find(html_stuff, "REPLACE_SEARCH") do
|
|
html_stuff = string.gsub(html_stuff, "REPLACE_SEARCH", REPLACE_SEARCH)
|
|
end
|
|
|
|
local REPLACE_DATA = ""
|
|
local k = 0
|
|
for _, v in pairs(indicators) do
|
|
if k > 0 then
|
|
REPLACE_DATA = REPLACE_DATA .. " "
|
|
end
|
|
REPLACE_DATA = REPLACE_DATA .. v
|
|
k = k + 1
|
|
end
|
|
|
|
if REPLACE_DATA and REPLACE_DATA ~= "" then
|
|
while string.find(REPLACE_DATA, "\t") do
|
|
REPLACE_DATA = string.gsub(REPLACE_DATA, "\t", " ")
|
|
end
|
|
while string.find(html_stuff, "REPLACE_DATA") do
|
|
html_stuff = string.gsub(html_stuff, "REPLACE_DATA", REPLACE_DATA)
|
|
end
|
|
else
|
|
html_stuff = string.gsub(html_stuff, ",'REPLACE_DATA'","")
|
|
end
|
|
apply(html_stuff)
|
|
|
|
ac = string.sub(ac, string.find(ac, " ")+1)
|
|
|
|
-- now we print the thing with teh appropiate indicators.
|
|
printD(print_text, table.unpack(indicators))
|
|
end
|
|
apply_html("html/convo/text/end.html")
|
|
end
|
|
end
|
|
|
|
function cell_builder(...)
|
|
arg = {...}
|
|
for i=1, #arg do
|
|
apply_html("html/words/definition/cell_start.html")
|
|
apply(arg[i])
|
|
apply_html("html/words/definition/cell_end.html")
|
|
end
|
|
end
|
|
|
|
function print_word_stuff(word)
|
|
apply_html("html/words/definition/start.html")
|
|
local exit = false
|
|
for _, v in pairs(words) do
|
|
if strip_symbols(v[1]) == strip_spaces(word) then
|
|
cell_builder(mod_convertToHeonian(word),v[1],v[3],v[2])
|
|
exit = true
|
|
end
|
|
end
|
|
if not exit then cell_builder(mod_convertToHeonian(word),word, "???","???") end
|
|
apply_html("html/words/definition/end.html")
|
|
end
|
|
|
|
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)
|
|
if not in_dictionary(str) then printW("\"" .. str .. "\" is not known") end
|
|
end
|
|
end
|
|
|
|
function strip_spaces(str)
|
|
while string.find(str, "% ") do
|
|
str = string.gsub(str, " ","")
|
|
end
|
|
return str
|
|
end
|
|
|
|
function strip_symbols(str)
|
|
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),"")
|
|
end
|
|
end
|
|
return str
|
|
end
|
|
|
|
function replace_sign(str)
|
|
while string.find(str, "%-") do
|
|
str = string.gsub(str, "%-"," ")
|
|
end
|
|
return str
|
|
end
|
|
|
|
function check_symbol(str)
|
|
if not in_dictionary(str) then
|
|
return replace_sign(str)
|
|
end
|
|
end
|
|
|
|
function find_n_replace(str, tbl,find,repl,indicator)
|
|
if not in_dictionary(str) then
|
|
if string.find(str, find) then
|
|
str = string.gsub(str,find, repl)
|
|
table.insert(tbl,indicator)
|
|
end
|
|
end
|
|
return str, tbl
|
|
end
|
|
|
|
function in_dictionary(str)
|
|
for i=1, #words do
|
|
if strip_symbols(words[i][1]) == str then return true end
|
|
end
|
|
end
|
|
|
|
function categorize_word(str,indicators)
|
|
local ind = {}
|
|
for _, v in pairs(words) do
|
|
if strip_symbols(v[1]) == strip_spaces(str) then
|
|
table.insert(ind, string.lower(v[3]))
|
|
break
|
|
end
|
|
end
|
|
for _, v in pairs(indicators) do
|
|
table.insert(ind, v)
|
|
end
|
|
return str, ind
|
|
end
|
|
|
|
function check_morphemes(str, tbl,match,repl,indicators)
|
|
if type(indicators) ~= "table" then
|
|
indicators = {indicators}
|
|
end
|
|
if not in_dictionary(str) then
|
|
local flen = string.len(match)
|
|
if string.sub(str, -flen) == match then
|
|
str = string.sub(str, 0,string.len(str)-flen) .. repl
|
|
if tbl then
|
|
for _, v in pairs(indicators) do
|
|
table.insert(tbl,v)
|
|
end
|
|
end
|
|
end
|
|
end
|
|
return str, tbl
|
|
end
|
|
|
|
function revert_nouns(str, tbl)
|
|
str, tbl = check_morphemes(str,tbl,"lfur","","formal-n1")
|
|
str, tbl = check_morphemes(str,tbl,"lafura","","formal-n2")
|
|
str, tbl = check_morphemes(str,tbl,"lan","","genitive")
|
|
str, tbl = check_morphemes(str,tbl,"la","","possesive")
|
|
str, tbl = check_morphemes(str,tbl,"n","","plural")
|
|
return str, tbl
|
|
end
|
|
|
|
function revert_verbs(str, tbl)
|
|
-- moods first
|
|
str, tbl = revert_mood(str, tbl,"pash","","volitional-mood")
|
|
str, tbl = revert_mood(str, tbl,"dash","","imperative-mood")
|
|
str, tbl = revert_mood(str, tbl,"bash","","shy-mood")
|
|
str, tbl = revert_mood(str, tbl,"tash","","threat-mood")
|
|
str, tbl = revert_mood(str, tbl,"shu","","comfy-mood")
|
|
str, tbl = revert_mood(str, tbl,"ha","","excited-mood")
|
|
-- once we've cleaned moods lets try to get tense
|
|
str, tbl = check_morphemes(str, tbl,"kanya","ku",{"present-tense-formal","formal-v1"})
|
|
str, tbl = check_morphemes(str, tbl,"kome","ku",{"past-tense-formal","formal-v2"})
|
|
-- maybe it's informal?
|
|
str, tbl = check_morphemes(str, tbl,"nya","",{"present-tense-informal","informal-v1"})
|
|
str, tbl = check_morphemes(str, tbl,"me","",{"past-tense-informal","informal-v2"})
|
|
for _, v in pairs(tbl) do
|
|
if v == "informal-v1"
|
|
or v == "informal-v2" then
|
|
str = str .. "ku"
|
|
end
|
|
end
|
|
-- negate
|
|
str, tbl = check_morphemes(str, tbl,"faku","ku","negated")
|
|
return str, tbl
|
|
end
|
|
|
|
function revert_mood(str, tbl,match,repl,indicator)
|
|
str, tbl = find_n_replace(str, tbl,"fa"..match,repl,indicator.."-negated")
|
|
str, tbl = find_n_replace(str, tbl,match,repl,indicator)
|
|
return str, tbl
|
|
end
|
|
|
|
function apply_html(path)
|
|
-- copy
|
|
local file = io.open(path,"r")
|
|
local html = file:read("*all")
|
|
|
|
file:close()
|
|
-- paste
|
|
apply(html)
|
|
end
|
|
|
|
function convo_image(string,alt_text)
|
|
if string then
|
|
apply_html("html/convo/header/image/start.html")
|
|
apply(string)
|
|
apply_html("html/convo/header/image/middle.html")
|
|
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")
|
|
apply(string)
|
|
apply_html("html/convo/header/date/end.html")
|
|
end
|
|
end
|
|
|
|
function convo_header_start()
|
|
if not header then
|
|
header = true
|
|
apply_html("html/convo/header/start.html")
|
|
end
|
|
end
|
|
|
|
function convo_header_end()
|
|
if header then
|
|
header = false
|
|
apply_html("html/convo/header/end.html")
|
|
end
|
|
end
|
|
|
|
function convo_start(color)
|
|
convo_header_end()
|
|
if not convo then
|
|
if color then
|
|
apply_html("html/convo/start_green.html")
|
|
else
|
|
apply_html("html/convo/start_gray.html")
|
|
end
|
|
convo = true
|
|
end
|
|
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
|
|
end
|
|
|
|
-- lets make the html
|
|
apply_html("html/start.html")
|
|
-- get text
|
|
local file = io.open(input,"r")
|
|
local text = file:read("*all")
|
|
file:close()
|
|
|
|
-- first analyze text
|
|
-- (this is the fun part)
|
|
word_list = {}
|
|
local p = 0
|
|
local s = 0
|
|
local convo = false
|
|
local header = false
|
|
local notes = false
|
|
local green = true
|
|
local skip = 1
|
|
local user = {}
|
|
while p ~= nil do
|
|
s = s + 1
|
|
local np = string.find(text,"\n",p+1)
|
|
if np and p - np ~= 1 then
|
|
if p then
|
|
skip = 1
|
|
if string.sub(text,p+1,p+1) == "\n"
|
|
or string.sub(text,p+1,p+1) == "/" then
|
|
-- end of new bubble
|
|
convo_end()
|
|
elseif string.sub(text,p+1,p+1) == "\t" then
|
|
-- its tabbed so its spoken?
|
|
convo_start()
|
|
process_content(string.sub(text,p+2,np-1))
|
|
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()
|
|
if green then
|
|
green = false
|
|
else
|
|
green = true
|
|
end
|
|
convo_start(green)
|
|
-- this is a header section
|
|
convo_header_start()
|
|
-- lets check for images
|
|
local nl = string.find(text,"\n",p+1)
|
|
local nlp = string.find(text,"\n",nl+1)
|
|
|
|
current_user = string.sub(text,p+1,np-1)
|
|
user[current_user] = user[current_user] or {image = nil}
|
|
if nlp and string.sub(text,nl+1,nl+1) == "i" then
|
|
user[current_user].image = string.sub(text,nl+3,nlp-1)
|
|
skip = skip + 1
|
|
nl = string.find(text,"\n",nl+1)
|
|
nlp = string.find(text,"\n",nlp+1)
|
|
end
|
|
convo_image(user[current_user].image)
|
|
|
|
-- print name
|
|
apply_html("html/convo/header/name/start.html")
|
|
apply(string.sub(text,p+1,np-1))
|
|
apply_html("html/convo/header/name/end.html")
|
|
|
|
-- lets check for dates
|
|
if nlp and string.sub(text,nl+1,nl+1) == "d" then
|
|
convo_date(string.sub(text,nl+3,nlp-1))
|
|
skip = skip + 1
|
|
else
|
|
convo_date("")
|
|
end
|
|
header = true
|
|
|
|
end
|
|
end
|
|
while skip > 0 do
|
|
p = string.find(text,"\n",p+1)
|
|
skip = skip - 1
|
|
end
|
|
else
|
|
break
|
|
end
|
|
end
|
|
|
|
convo_end()
|
|
|
|
-- 3.5 separation
|
|
apply_html("html/spacer.html")
|
|
|
|
-- fourth lets make word lists
|
|
-- process contents
|
|
|
|
-- lets print the words
|
|
apply_html("html/spacer.html")
|
|
apply_html("html/words/start.html")
|
|
for i=1, #word_list do
|
|
print_word_stuff(word_list[i])
|
|
end
|
|
apply_html("html/words/end.html")
|
|
-- pop up
|
|
apply_html("html/pop_up.html")
|
|
-- lets end the html
|
|
apply_html("html/end.html")
|