Module:String2: Difference between revisions

Revision as of 20:15, 18 November 2021

Latest revision as of 12:24, 19 February 2025

(8 intermediate revisions by 5 users not shown)

Line 1:

require ('strict');

local p = {}

Line 11 ⟶ 12:

end

p.ucfirst = function (frame )

local s = mw.text.trim( frame.args[1] or "" );

if not s or '' == s or s:match ('^%s+$') then -- when <s> is nil, empty, or only whitespace

return s; -- abandon because nothing to do

end

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 prefix_patterns_t = { -- sequence of prefix patterns

local lipos = mw.ustring.find(s, "<li>" )

'^\127[^\127]*UNIQ%-%-%a+%-%x+%-QINU[^\127]*\127', -- stripmarker

if lipos then

'^([%*;:#]+)', -- various list markup

s1 = mw.ustring.sub(s, 1, lipos + 3)

'^(\'\'\'*)', -- bold / italic markup

s = mw.ustring.sub(s, lipos + 4)

'^(%b<>)', -- html-like tags because some templates render these

'^(&%a+;)', -- html character entities because some templates render these

'^(&#%d+;)', -- html numeric (decimal) entities because some templates render these

'^(&#x%x+;)', -- html numeric (hexadecimal) entities because some templates render these

'^(%s+)', -- any whitespace characters

'^([%(%)%-%+%?%.%%!~!@%$%^&_={}/`,‘’„“”ʻ|\"\'\\]+)', -- miscellaneous punctuation

}

local prefixes_t = {}; -- list, bold/italic, and html-like markup, & whitespace saved here

local function prefix_strip (s) -- local function to strip prefixes from <s>

for _, pattern in ipairs (prefix_patterns_t) do -- spin through <prefix_patterns_t>

if s:match (pattern) then -- when there is a match

local prefix = s:match (pattern); -- get a copy of the matched prefix

table.insert (prefixes_t, prefix); -- save it

s = s:sub (prefix:len() + 1); -- remove the prefix from <s>

return s, true; -- return <s> without prefix and flag; force restart at top of sequence because misc punct removal can break stripmarker

end

end

return s; -- no prefix found; return <s> with nil flag

end

-- s1 is either "" or the first part of the list markup, so we can continue

local prefix_removed; -- flag; boolean true as long as prefix_strip() finds and removes a prefix

-- and prepend s1 to the returned string

local letterpos

repeat -- one by one remove list, bold/italic, html-like markup, whitespace, etc from start of <s>

if mw.ustring.find(s, "^%[%[[^|]+|[^%]]+%]%]") then

s, prefix_removed = prefix_strip (s);

-- this is a piped wikilink, so we capitalise the text, not the pipe

until (not prefix_removed); -- until <prefix_removed> is nil

local _

_, letterpos = mw.ustring.find(s, "|%A*%a") -- find the first letter after the pipe

s1 = table.concat (prefixes_t); -- recreate the prefix string for later reattachment

else

letterpos = mw.ustring.find(s, '%a')

local first_text = mw.ustring.match (s, '^%[%[[^%]]+%]%]'); -- extract wikilink at start of string if present; TODO: this can be string.match()?

end

if letterpos then

local upcased;

local first = mw.ustring.sub(s, 1, letterpos - 1)

if first_text then

local letter = mw.ustring.sub(s, letterpos, letterpos)

if first_text:match ('^%[%[[^|]+|[^%]]+%]%]') then -- if <first_text> is a piped link

local rest = mw.ustring.sub(s, letterpos + 1)

upcased = mw.ustring.match (s, '^%[%[[^|]+|%W*(%w)'); -- get first letter character

return s1 .. first .. mw.ustring.upper(letter) .. rest

upcased = mw.ustring.upper (upcased); -- upcase first letter character

else

s = mw.ustring.gsub (s, '^(%[%[[^|]+|%W*)%w', '%1' .. upcased); -- replace

return s1 .. s

else -- here when <first_text> is a wikilink but not a piped link

upcased = mw.ustring.match (s, '^%[%[%W*%w'); -- get '[[' and first letter

upcased = mw.ustring.upper (upcased); -- upcase first letter character

s = mw.ustring.gsub (s, '^%[%[%W*%w', upcased); -- replace; no capture needed here

end

elseif s:match ('^%[%S+%s+[^%]]+%]') then -- if <s> is a ext link of some sort; must have label text

upcased = mw.ustring.match (s, '^%[%S+%s+%W*(%w)'); -- get first letter character

upcased = mw.ustring.upper (upcased); -- upcase first letter character

s = mw.ustring.gsub (s, '^(%[%S+%s+%W*)%w', '%1' .. upcased); -- replace

elseif s:match ('^%[%S+%s*%]') then -- if <s> is a ext link without label text; nothing to do

return s1 .. s; -- reattach prefix string (if present) and done

else -- <s> is not a wikilink or ext link; assume plain text

upcased = mw.ustring.match (s, '^%W*%w'); -- get the first letter character

upcased = mw.ustring.upper (upcased); -- upcase first letter character

s = mw.ustring.gsub (s, '^%W*%w', upcased); -- replace; no capture needed here

end

return s1 .. s; -- reattach prefix string (if present) and done

end

p.title = function (frame )

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:

Line 94 ⟶ 141:

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 args = frame.args

local pargs = frame:getParent().args

for k, v in pairs(pargs) do

args[k] = v

end

local str = mw.text.trim(args[1] or args.source or "")

local match = mw.text.trim(args[2] or args.target or ""):gsub('"', '')

if str == "" or match == "" then return nil end

local plain = mw.text.trim(args[3] or args.plain or "")

if plain == "false" then plain = false else plain = true end

local nomatch = mw.text.trim(args[4] or args.nomatch or "")

-- just take the start position

local pos = mw.ustring.find(str, match, 1, plain) or nomatch

return pos

end

Line 227 ⟶ 251:

-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String

function p._escapePattern( pattern_str )

return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )

end

Line 355 ⟶ 379:

function p.startswith(frame)

return (frame.args[1]:sub(1, frame.args[2]:len()) == frame.args[2]) and 'yes' or ''

end

-- Implements [[Template:Isnumeric]]

function p.isnumeric(frame)

local s = frame.args[1] or frame:getParent().args[1]

local boolean = (frame.args.boolean or frame:getParent().args.boolean) == 'true'

if type(s) == 'string' and mw.getContentLanguage():parseFormattedNumber( s ) then

return boolean and 1 or s

end

return boolean and 0 or ''

end

-- Checks if a value in a group of numbers is not an interger.

-- Allows usage of an |empty= parameter to allow empty values to be skipped.

function p.isInteger(frame)

local values = frame.args or frame:getParent().args

local allow_empty = frame.args.empty or frame:getParent().args.empty

for _, value in ipairs(values) do

-- Trim spaces

value = value and value:gsub("^%s*(.-)%s*$", "%1")

if value == "" or value == nil then

if not allow_empty then

return false -- Empty values are not allowed

end

else

value = tonumber(value)

if not (type(value) == "number" and value == math.floor(value)) then

return false

end

end

end

return true

end

-- Returns an error found in a string.

function p.getError(frame)

local text = frame.args[1] or frame:getParent().args[1]

local error_message = text:match('(<strong class="error">.-</strong>)')

return error_message or nil

end