跳转到内容

Module:String2

轻之舟百科,让知识轻装启航

The module “String2” contains 4 available calls that convert strings to upper, lower, sentence or title case.

The sentence case function finds the first letter and capitalises that, so it works properly with text containing wiki-markup. Compare {{#invoke:String2|sentence|[[action game]]}} -> Action game with {{ucfirst:{{lc:[[action game]]}}}} -> action game. Piped wiki-links are handled as well: {{#invoke:String2|sentence|[[trimix (breathing gas)|trimix]]}} -> Trimix.

The title case function capitalises the first letter of each word in the text, apart from a number of short words recommended by The U.S. Government Printing Office Style Manual.

Further functions commonly used on strings would be useful additions.

{#invoke:String2 | upper |…}}
{#invoke:String2 | lower |…}}
{#invoke:String2 | sentence |…}}
{#invoke:String2 | title |…}}

Just one unnamed parameter is used, representing the text to be converted to the required case.

Input Output
{{#invoke:String2| upper | abcd }} ABCD
{{#invoke:String2| upper | abCD }} ABCD
{{#invoke:String2| upper | ABcd }} ABCD
{{#invoke:String2| upper | ABCD }} ABCD
{{#invoke:String2| upper | }}
 
{{#invoke:String2| lower | abcd }} abcd
{{#invoke:String2| lower | abCD }} abcd
{{#invoke:String2| lower | ABcd }} abcd
{{#invoke:String2| lower | ABCD }} abcd
{{#invoke:String2| lower | }}
 
{{#invoke:String2| sentence | abcd }} Abcd
{{#invoke:String2| sentence | abCD }} Abcd
{{#invoke:String2| sentence | ABcd }} Abcd
{{#invoke:String2| sentence | ABCD }} Abcd
{{#invoke:String2| sentence | [[action game]] }} Action game
{{#invoke:String2| sentence | [[trimix (breathing gas)|trimix]] }} Trimix
{{#invoke:String2| sentence | }}
 
{{#invoke:String2| title | abcd }} Abcd
{{#invoke:String2| title | abCD }} Abcd
{{#invoke:String2| title | ABcd }} Abcd
{{#invoke:String2| title | ABCD }} Abcd
{{#invoke:String2| title | }}
{{#invoke:String2| title | The Vitamins Are In My Fresh California Raisins}} The Vitamins Are in My Fresh California Raisins

Module:String for the following functions:

  • len
  • sub
  • sublength
  • match
  • pos
  • str_find
  • find
  • replace
  • rep

local p = {}


p.upper = function(frame)
	local s = mw.text.trim(frame.args[1] or "")
	return string.upper(s)
end

p.lower = function(frame)
	local s = mw.text.trim(frame.args[1] or "")
	return string.lower(s)
end


p.sentence = function (frame )
	frame.args[1] = string.lower(frame.args[1])
	return p.ucfirst(frame)
end


p.ucfirst = function (frame )
	local s =  mw.text.trim( frame.args[1] or "" )
	local s1 = ""
	-- if it's a list chop off and (store as s1) everything up to the first <li>
	local lipos = string.find(s, "<li>" )
	if lipos then
		s1 = string.sub(s, 1, lipos + 3)
		s = string.sub(s, lipos + 4)
	end
	-- s1 is either "" or the first part of the list markup, so we can continue
	-- and prepend s1 to the returned string
	if string.find(s, "^%[%[[^|]+|[^%]]+%]%]") then
		-- this is a piped wikilink, so we capitalise the text, not the pipe
		local b, c = string.find(s, "|%A*%a") -- find the first letter after the pipe
		return s1 .. string.sub(s, 1, c-1) .. string.upper(string.sub(s, c, c)) .. string.sub(s, c+1)
	end
	local letterpos = string.find(s, '%a')
	if letterpos then
		local first = string.sub(s, 1, letterpos - 1)
		local letter = string.sub(s, letterpos, letterpos)
		local rest = string.sub(s, letterpos + 1)
		return s1 .. first .. string.upper(letter) .. rest
	else
		return s1 .. s
	end
end


p.title = function (frame )
	-- http://grammar.yourdictionary.com/capitalization/rules-for-capitalization-in-titles.html
	-- recommended by The U.S. Government Printing Office Style Manual:
	-- "Capitalize all words in titles of publications and documents,
	-- except a, an, the, at, by, for, in, of, on, to, up, and, as, but, or, and nor."
	local alwayslower = {['a'] = 1, ['an'] = 1, ['the'] = 1, 
		['and'] = 1, ['but'] = 1, ['or'] = 1, ['for'] = 1,
		['nor'] = 1, ['on'] = 1, ['in'] = 1, ['at'] = 1, ['to'] = 1,
		['from'] = 1, ['by'] = 1, ['of'] = 1, ['up'] = 1 }
	local res = ''
	local s =  mw.text.trim( frame.args[1] or "" )
	local words = mw.text.split( s, " ")
	for i, s in ipairs(words) do
		s = string.lower( s )
		if( i > 1 and alwayslower[s] == 1) then
			-- leave in lowercase
		else
			s = mw.getContentLanguage():ucfirst(s)
		end
		words[i] = s
	end
	return table.concat(words, " ")
end


-- stripZeros finds the first number and strips leading zeros (apart from units)
-- e.g "0940" -> "940"; "Year: 0023" -> "Year: 23"; "00.12" -> "0.12"
p.stripZeros = function(frame)
	local s = mw.text.trim(frame.args[1] or "")
	n = tonumber( string.match( s, "%d+" ) ) or ""
	s = string.gsub( s, "%d+", n, 1 )
	return s
end


-- nowiki ensures that a string of text is treated by the MediaWiki software as just a string
-- it takes an unnamed parameter and trims whitespace, then removes any wikicode
p.nowiki = function(frame)
	local str = mw.text.trim(frame.args[1] or "")
	return mw.text.nowiki(str)
end


-- posnq (position, no quotes) returns the numerical start position of the first occurrence
-- of one piece of text ("match") inside another ("str").
-- It returns nil if no match is found, or if either parameter is blank.
-- It takes the text to be searched in as the first unnamed parameter, which is trimmed.
-- It takes the text to match as the second unnamed parameter, which is trimmed and
-- any double quotes " are stripped out.
p.posnq = function(frame)
	local str = mw.text.trim(frame.args[1] or "")
	local match = mw.text.trim(frame.args[2] or ""):gsub('"', '')
	if  str == "" or match == "" then return nil end
	-- just take the start position
	local pos = str:find(match, 1, true)
	return pos
end


-- split splits text at boundaries specified by separator
-- and returns the chunk for the index idx (starting at 1)
-- #invoke:String2 |split |text |separator |index |true/false
-- #invoke:String2 |split |txt=text |sep=separator |idx=index |plain=true/false
-- if plain is false/no/0 then separator is treated as a Lua pattern - defaults to plain=true
p.split = function(frame)
	local args = frame.args
	if not(args[1] or args.txt) then args = frame:getParent().args end
	local txt = args[1] or args.txt or ""
	if txt == "" then return nil end
	local sep = (args[2] or args.sep or ""):gsub('"', '')
	local idx = tonumber(args[3] or args.idx) or 1
	local plain = (args[4] or args.plain or "true"):sub(1,1)
	plain = (plain ~= "f" and plain ~= "n" and plain ~= "0")
	local splittbl = mw.text.split( txt, sep, plain )
	if idx < 0 then idx = #splittbl + idx + 1 end
	return splittbl[idx]
end

-- первый параметр до начала второго параметра (или до конца, если он не встретился)
-- необяз. 3-й параметр - с какого по номеру (с 1) символа начинать поиск.
p.bs = function(f)
	return mw.ustring.sub(f.args[1], 1, (mw.ustring.find(f.args[1],f.args[2],tonumber(f.args[3] or 1),true) or 0)-1)
end

p.len2 = function(f)
	local s = f.args['s'] or f.args[1] or ''
	s = mw.text.unstrip(s)
	s = s:gsub('<%/?.->', ''):gsub("'''", ''):gsub("%-%{", ''):gsub("%}%-", ''):gsub('%[%[([^\n]-)%]%]', function (x) 
		local text = string.gsub(x, '^.-%|(.-)$', '%1')
		if string.find(target, ':') == 1 then
			if text == target then
				text = string.sub(text, 2)
			end
		end
		return text
	end)
	local i = mw.ustring.len( s:gsub('%w+', ''):gsub('%p+', ''):gsub('%s+', '') )
	local j = mw.ustring.len( s )
	return (j - i) / 2 + i
end
	
function p.hyphen_to_dash( str, spacing )
	if (str == nil or str == '') then
		return str
	end

	local accept

	str = mw.text.decode(str, true )											-- replace html entities with their characters; semicolon mucks up the text.split

	local out = {}
	local list = mw.text.split (str, '%s*[,;]%s*')								-- split str at comma or semicolon separators if there are any

	for _, item in ipairs (list) do												-- for each item in the list
		item = mw.text.trim(item)												-- trim whitespace
		item, accept = item:gsub ('^%(%((.+)%)%)$', '%1')
		if accept == 0 and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then	-- if a hyphenated range or has endash or emdash separators
			if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or			-- letterdigit hyphen letterdigit (optional separator between letter and digit)
				item:match ('^%d+[%.%-]?%a+%s*%-%s*%d+[%.%-]?%a+$') or			-- digitletter hyphen digitletter (optional separator between digit and letter)
				item:match ('^%d+[%.%-]%d+%s*%-%s*%d+[%.%-]%d+$') or			-- digit separator digit hyphen digit separator digit
				item:match ('^%d+%s*%-%s*%d+$') or								-- digit hyphen digit
				item:match ('^%a+%s*%-%s*%a+$') then							-- letter hyphen letter
					item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2')	-- replace hyphen, remove extraneous space characters
			else
				item = mw.ustring.gsub (item, '%s*[–—]%s*', '–')				-- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace
			end
		end
		table.insert (out, item)												-- add the (possibly modified) item to the output table
	end

	local temp_str = table.concat (out, ',' .. spacing)							-- concatenate the output table into a comma separated string
	temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1')					-- remove accept-this-as-written markup when it wraps all of concatenated out
	if accept ~= 0 then
		temp_str = str:gsub ('^%(%((.+)%)%)$', '%1')							-- when global markup removed, return original str; do it this way to suppress boolean second return value
	end
	return temp_str
end


function p.hyphen2dash( frame )
	local str = frame.args[1] or ''
	local spacing = frame.args[2] or ' ' -- space is part of the standard separator for normal spacing (but in conjunction with templates r/rp/ran we may need a narrower spacing

	return p.hyphen_to_dash(str, spacing)
end

-- Similar to [[Module:String#endswith]]


return p