Module:String2: Difference between revisions
From the Croc Wiki, the Croc encyclopedia
Jump to navigationJump to search
Content added Content deleted
(add optional spacing parameter to hyphen2dash for improved support in templates r/rp/ran. Default is a normal space after the separating comma.) |
(update from Module:String2/sandbox: tweaks + findpagetext won't fail if given an invalid or nonexistent page title) |
||
Line 189: | Line 189: | ||
if plain:sub(1, 1) == "f" then plain = false else plain = true end |
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 |
-- get the page content and look for 'text' - return position or nomatch |
||
local content = titleobj:getContent() |
local content = titleobj and titleobj:getContent() |
||
return mw.ustring.find(content, text, 1, plain) or nomatch |
return content and mw.ustring.find(content, text, 1, plain) or nomatch |
||
end |
end |
||
p.findpagetext = function(frame) |
p.findpagetext = function(frame) |
||
Line 228: | Line 228: | ||
-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String |
-- Escape Pattern helper function so that all characters are treated as plain text, as per Module:String |
||
function p._escapePattern( pattern_str) |
function p._escapePattern( pattern_str) |
||
return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" ) |
return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" ) |
||
end |
end |
||
Line 251: | Line 251: | ||
function p.strip( frame ) |
function p.strip( frame ) |
||
local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} ) |
local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} ) |
||
local source_str = new_args['source'] or '' |
local source_str = new_args['source'] or '' |
||
local chars = new_args['chars'] or '' or 'characters' |
local chars = new_args['chars'] or '' or 'characters' |
||
source_str = mw.text.trim(source_str) |
source_str = mw.text.trim(source_str) |
||
if source_str == '' or chars == '' then |
if source_str == '' or chars == '' then |
||
return source_str |
return source_str |
||
end |
end |
||
local l_plain = p._getBoolean( new_args['plain'] or true ) |
local l_plain = p._getBoolean( new_args['plain'] or true ) |
||
if l_plain then |
if l_plain then |
||
chars = p._escapePattern( chars ) |
chars = p._escapePattern( chars ) |
||
end |
end |
||
local result |
local result |
||
result = mw.ustring.gsub(source_str, "["..chars.."]", '') |
result = mw.ustring.gsub(source_str, "["..chars.."]", '') |
||
return result |
return result |
||
end |
end |
||
Line 310: | Line 310: | ||
function p.hyphen_to_dash( str, spacing ) |
function p.hyphen_to_dash( str, spacing ) |
||
if (str == nil or str == '') then |
if (str == nil or str == '') then |
||
return str |
return str |
||
end |
end |
||
local accept |
local accept |
||
str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split |
str = mw.text.decode(str, true ) -- replace html entities with their characters; semicolon mucks up the text.split |
||
local out = {} |
local out = {} |
||
local list = mw.text.split (str, '%s*[,;]%s*') |
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 |
for _, item in ipairs (list) do -- for each item in the list |
||
item = mw.text.trim(item) -- trim whitespace |
item = mw.text.trim(item) -- trim whitespace |
||
item, accept = item:gsub ('^%(%((.+)%)%)$', '%1') |
item, accept = item:gsub ('^%(%((.+)%)%)$', '%1') |
||
if accept == 0 and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators |
if accept == 0 and mw.ustring.match (item, '^%w*[%.%-]?%w+%s*[%-–—]%s*%w*[%.%-]?%w+$') then -- if a hyphenated range or has endash or emdash separators |
||
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) |
if item:match ('^%a+[%.%-]?%d+%s*%-%s*%a+[%.%-]?%d+$') or -- letterdigit hyphen letterdigit (optional separator between letter and digit) |
||
Line 329: | Line 329: | ||
item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit |
item:match ('^%d+%s*%-%s*%d+$') or -- digit hyphen digit |
||
item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter |
item:match ('^%a+%s*%-%s*%a+$') then -- letter hyphen letter |
||
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2') |
item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2') -- replace hyphen, remove extraneous space characters |
||
else |
else |
||
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–') |
item = mw.ustring.gsub (item, '%s*[–—]%s*', '–') -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace |
||
end |
end |
||
end |
end |
||
table.insert (out, item) |
table.insert (out, item) -- add the (possibly modified) item to the output table |
||
end |
end |
||
local temp_str = table.concat (out, ',' .. spacing) |
local temp_str = table.concat (out, ',' .. spacing) -- concatenate the output table into a comma separated string |
||
temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1') |
temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%1') -- remove accept-this-as-written markup when it wraps all of concatenated out |
||
if accept ~= 0 then |
if accept ~= 0 then |
||
temp_str = str:gsub ('^%(%((.+)%)%)$', '%1') |
temp_str = str:gsub ('^%(%((.+)%)%)$', '%1') -- when global markup removed, return original str; do it this way to suppress boolean second return value |
||
⚫ | |||
else |
|||
return temp_str; -- else, return assembled temp_str |
|||
end |
end |
||
⚫ | |||
end |
end |
||
Line 350: | Line 348: | ||
local str = frame.args[1] or '' |
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 |
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) |
return p.hyphen_to_dash(str, spacing) |
||
end |
end |