Module:Chak-utilities
- The following documentation is located at Module:Chak-utilities/documentation. [edit]
- Useful links: subpage list • transclusions • testcases • sandbox
Utilities for Chakobsa scripts. Implements {{chak-from-root}}.
Exposed functions
l(term, face, alt)- Creates a link to a Chakobsa lexeme - similar to
{{l|chak|term}}
is_geminate(char)- returns true if the supplied 'character' is geminate
compress_consonants(str)- Returns a 'compressed' version of the string where consonant digraphs are reduced to a single character and trigraph geminates are reduced to a geminate of a single character. Mostly for use with other functions for parsing.
expand_consonants(str)- Returns an 'expanded' version of the string where reductions from
compress_consonantsare replaced with the original romanizations.
parse_consonants(str)- Returns a string where the consonants have been split out, delimited by hyphens. Understands geminate consonants and considers them a 'single' consonant.
parse_root(root_str,expandFinal)- Returns a table of parts of the root string is grouped by consonant and vowels. Example: "kkaalatg" > "kk","aa","l","a","tg". If expandFinal is true, returns the final part parsed out through
parse_consonantsThe above example would be "kkaalatg" > "kk","aa","l","a","t-g". Used for inflection functions.
export = {}
local m_links = require("Module:links")
local m_utilities = require("Module:utilities")
local m_headword = require("Module:headword")
local lang = require("Module:Languages").getByCode("chak")
local zwnj = "\u200C"
local function link(term, face, alt)
return m_links.full_link( { term = term, lang = lang, alt = alt }, face )
end
function export.is_geminate(char)
return char ~= nil and #char > 1 and #char < 4 and string.sub(char,1,1) == string.sub(char,2,2)
end
function export.extract_root(root_str)
vowels = "aeiou"
roots = {
onset = '',
vowel = '',
coda = '',
}
if root_str then
root_str = mw.ustring.gsub(root_str,zwnj,'-')
root_str = string.gsub(root_str,'%s','-')
parts = mw.text.split(root_str,'-')
if #parts == 3 then
roots['onset'] = parts[1]
roots['vowel'] = parts[2]
roots['coda'] = parts[3]
elseif #parts == 2 then
if string.find(parts[1],"^[aeiou]") then
roots['onset'] = ''
roots['vowel'] = parts[1]
roots['coda'] = parts[2]
elseif string.find(parts[2],"^[aeiou]") then
roots['onset'] = parts[1]
roots['vowel'] = parts[2]
roots['coda'] = ''
else
roots['onset'] = parts[1]
roots['vowel'] = ''
roots['coda'] = parts[2]
end
elseif #parts == 1 and parts[1] ~= '' then
local temp = root_str
s,e = string.find(temp,"["..vowels.."]+")
if s then
roots['vowel'] = string.sub(temp,s,e)
end
s,e = string.find(temp,"^[^"..vowels.."]+")
if s then
roots['onset'] = string.sub(temp,s,e)
temp = string.gsub(temp,roots['onset'],'',1)
end
s,e = string.find(temp,"[^"..vowels.."]+")
if s then
roots['coda'] = string.sub(temp,s,e)
end
else
return nil
end
else
return nil
end
return roots
end
function export.verbose_root(roots)
r = { roots["onset"], roots["vowel"], roots["coda"] }
return mw.text.listToText(r,'-','-')
end
function export.geminate_char(char)
char = char or ''
if #char == 1 or (#char == 2 and string.sub(char,2) == 'h') then
return string.sub(char,1,1)..char
else
return char
end
end
function export.degeminate_char(char)
char = char or ''
if (#char == 2 or #char == 3) and string.sub(char,1,1) == string.sub(char,2,2) then
return string.sub(char,2)
else
return char
end
end
function export.assimilate(str)
devoiced = "[ktfs]"
voiced = "[gdvz]"
devoicing = {
["g"] = "k",
["d"] = "t",
["v"] = "f",
["z"] = "s",
}
h_devoicing = {
["g"] = "k",
["d"] = "t",
["v"] = "f",
["z"] = "z",
}
output = str
if str and str ~= '' then
--VvC assimilition
output = string.gsub(output,"([au])v([^iua])","%1~v%2"):gsub("(.)~v",{["a"] = "au", ["u"] = "uu"})
--General Devoicing
output = string.gsub(output,"("..devoiced..")("..voiced..")","%1~%2"):gsub("~(.)",devoicing)
output = string.gsub(output,"("..voiced..")("..devoiced..")","~%1%2"):gsub("~(.)",devoicing)
--H devoicing
output = string.gsub(output,"h("..voiced..")","%1~%2"):gsub("~(.)",h_devoicing)
output = string.gsub(output,"("..voiced..")(h)","~%1%2"):gsub("~(.)",h_devoicing)
output = string.gsub(output,"("..voiced..")(h)","~%1%2"):gsub("~(.)",h_devoicing)
end
return output
end
function export.chak_from_root(frame)
local output = {}
local categories = {}
local title = mw.title.getCurrentTitle()
local namespace = title.nsText
local params = {
[1] = { alias_of = "root"},
[2] = { alias_of = "mod"},
["root"] = {required = true},
["mod"] = {},
["nocat"] = { type = "boolean", default = false },
["plain"] = { type = "boolean", default = false },
["alt"] = {},
["face"] = { default = "term" },
["notext"] = { type = "boolean", default = false },
["nolink"] = { type = "boolean", default = false },
}
local args = require("Module:parameters").process(frame:getParent().args, params)
if not args["root"] and namespace == "Template" then
args["root"] = "tes"
args["mod"] = "t"
end
--local verbose_root = export.verbose_root(export.extract_root(args["root"]))
local verbose_root = mw.ustring.gsub(args["root"],"\x{200C}","-")
local link_text = link(args["root"], args["face"], verbose_root:gsub('-','') )
mw.getCurrentFrame():callParserFunction( '#vardefine', { 'chak-root', verbose_root } )
if args["mod"] then
link_text = link_text.." + -"..link(args["mod"], args["face"], args["mod"])
table.insert(categories, m_utilities.format_categories( { "Chakobsa terms with the modifier -" .. args["mod"] }, lang) )
mw.getCurrentFrame():callParserFunction( '#vardefine', { 'chak-mod', args["mod"] } )
end
table.insert(output, link_text)
table.insert(categories, m_utilities.format_categories( { "Chakobsa terms belonging to the root " .. args["root"] }, lang) )
if args["plain"] then
return args["root"].." + -"..args["mod"]
elseif args["nocat"] then
return table.concat(output)
elseif args["notext"] then
return table.concat(categories)
else
return table.concat(output) .. table.concat(categories)
end
return output
end
return export