Content deleted Content added
Matthiaspaul (talk | contribs) reverted per talk |
No edit summary |
||
| (22 intermediate revisions by 10 users not shown) | |||
Line 1:
require ('strict');
local p = {}
Line 11 ⟶ 12:
end
p.ucfirst = function (frame
local s =
if not s or '' == s or s:match ('^%s+$') then -- when <s> is nil, empty, or only whitespace
return s; -- abandon because nothing to do
end
s = mw.text.trim( frame.args[1] or "" )
local s1 = ""
local prefix_patterns_t = { -- sequence of prefix patterns
'^\127[^\127]*UNIQ%-%-%a+%-%x+%-QINU[^\127]*\127', -- stripmarker
'^([%*;:#]+)', -- various list markup
'^(\'\'\'*)', -- bold / italic markup
'^(%b<>)', -- html-like tags because some templates render these
'^(&%a+;)', -- html character entities because some templates render these
'^(&#%d+;)', -- html numeric (decimal) entities because some templates render these
'^(&#x%x+;)', -- html numeric (hexadecimal) entities because some templates render these
'^(%s+)', -- any whitespace characters
'^([%(%)%-%+%?%.%%!~!@%$%^&_={}/`,‘’„“”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
local prefix_removed; -- flag; boolean true as long as prefix_strip() finds and removes a prefix
repeat -- one by one remove list, bold/italic, html-like markup, whitespace, etc from start of <s>
s, prefix_removed = prefix_strip (s);
until (not prefix_removed); -- until <prefix_removed> is nil
s1 = table.concat (prefixes_t); -- recreate the prefix string for later reattachment
local first_text = mw.ustring.match (s, '^%[%[[^%]]+%]%]'); -- extract wikilink at start of string if present; TODO: this can be string.match()?
local upcased;
if first_text then
if first_text:match ('^%[%[[^|]+|[^%]]+%]%]') then -- if <first_text> is a piped link
upcased = mw.ustring.match (s, '^%[%[[^|]+|%W*(%w)'); -- get first letter character
upcased = mw.ustring.upper (upcased); -- upcase first letter character
s = mw.ustring.gsub (s, '^(%[%[[^|]+|%W*)%w', '%1' .. upcased); -- replace
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)
-- 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
Line 189 ⟶ 213:
if plain:sub(1, 1) == "f" then plain = false else plain = true end
-- get the page content and look for 'text' - return position or nomatch
local content = titleobj and titleobj:getContent()
return content and mw.ustring.find(content, text, 1, plain) or nomatch
end
p.findpagetext = function(frame)
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, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )
end
Line 251 ⟶ 275:
function p.strip( frame )
local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} )
local source_str = new_args['source'] or ''
local chars = new_args['chars'] or '' or 'characters'
source_str = mw.text.trim(source_str)
if source_str == '' or chars == '' then
return source_str
end
local l_plain = p._getBoolean( new_args['plain'] or true )
if l_plain then
chars = p._escapePattern( chars )
end
local result
result = mw.ustring.gsub(source_str, "["..chars.."]", '')
return result
end
Line 310 ⟶ 334:
function p.hyphen_to_dash( str, spacing )
if (str == nil or str == '') then
return str
end
local accept
str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split
local out = {}
local list = mw.text.split (str, '%s*[,;]%s*')
for _, item in ipairs (list) do -- for each item in the list
item = mw.text.trim(item) -- trim whitespace
item, accept = item:gsub ('^%(%((.+)%)%)$', '%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)
Line 329 ⟶ 353:
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')
else
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–')
end
end
table.insert (out, item)
end
local temp_str = table.concat (out, ',' .. spacing)
temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1')
if accept ~= 0 then
temp_str = str:gsub ('^%(%((.+)%)%)$', '%1')
end
return temp_str
end
Line 350 ⟶ 372:
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]]
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
| |||