Module:String2/sandbox: Difference between revisions

Revision as of 14:47, 3 March 2024

Revision as of 18:45, 10 March 2024

Line 22:

local prefix_patterns_t = { -- sequence of prefix patterns

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

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

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

Line 35:

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

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

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

Line 48 ⟶ 47:

end

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

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, prefixes_t);

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

-- if it's a list chop off and (store as s1) everything up to the first <li>

-- why just list markup? Could be any sort of html markup:

-- <span title="Spanish-language text"><i lang="es">casa</i></span> (this from {{lang|es|casa}})

-- what about wikitext italic or bold markup? (''italic text'', '''bold text''') – both may be legitimate

-- local lipos = mw.ustring.find(s, "<li>" ) -- why not constrained to start of string?

-- if lipos then

-- s1 = mw.ustring.sub(s, 1, lipos + 3) -- get <li> tag (assumes that the tag is the first text in the string <s> – it may not be)

-- s = mw.ustring.sub(s, lipos + 4) -- get everything after the <li> tag

-- end

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

-- -- and prepend s1 to the returned string

-- local letterpos

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

Line 100 ⟶ 84:

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

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

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

-- local _

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

-- else

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

-- end

-- if letterpos then

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

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

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

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

-- else

-- return s1 .. s

-- end

end

p.title = function (frame )