Sətir 1: |
Sətir 1: |
| + | local p = {} |
| + | |
| + | p.trim = function(frame) |
| + | return mw.text.trim(frame.args[1] or "") |
| + | end |
| + | |
| + | p.sentence = function (frame) |
| + | -- {{lc:}} is strip-marker safe, string.lower is not. |
| + | frame.args[1] = frame:callParserFunction('lc', 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 = mw.ustring.find(s, "<li>" ) |
| + | if lipos then |
| + | s1 = mw.ustring.sub(s, 1, lipos + 3) |
| + | s = mw.ustring.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 |
| + | local letterpos |
| + | 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, "|%A*%a") -- find the first letter after the pipe |
| + | else |
| + | letterpos = mw.ustring.find(s, '%a') |
| + | 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 ) |
| + | -- 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 |
| + | -- {{lc:}} is strip-marker safe, string.lower is not. |
| + | s = frame:callParserFunction('lc', s) |
| + | if i == 1 or alwayslower[s] ~= 1 then |
| + | s = mw.getContentLanguage():ucfirst(s) |
| + | end |
| + | words[i] = s |
| + | end |
| + | return table.concat(words, " ") |
| + | end |
| + | |
| + | -- findlast finds the last item in a list |
| + | -- the first unnamed parameter is the list |
| + | -- the second, optional unnamed parameter is the list separator (default = comma space) |
| + | -- returns the whole list if separator not found |
| + | p.findlast = function(frame) |
| + | local s = mw.text.trim( frame.args[1] or "" ) |
| + | local sep = frame.args[2] or "" |
| + | if sep == "" then sep = ", " end |
| + | local pattern = ".*" .. sep .. "(.*)" |
| + | local a, b, last = s:find(pattern) |
| + | if a then |
| + | return last |
| + | else |
| + | return s |
| + | end |
| + | 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 "") |
| + | local 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 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 |
| + | |
| + | -- 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 |
| + | |
| + | -- val2percent scans through a string, passed as either the first unnamed parameter or |txt= |
| + | -- it converts each number it finds into a percentage and returns the resultant string. |
| + | p.val2percent = function(frame) |
| + | local args = frame.args |
| + | if not(args[1] or args.txt) then args = frame:getParent().args end |
| + | local txt = mw.text.trim(args[1] or args.txt or "") |
| + | if txt == "" then return nil end |
| + | local function v2p (x) |
| + | x = (tonumber(x) or 0) * 100 |
| + | if x == math.floor(x) then x = math.floor(x) end |
| + | return x .. "%" |
| + | end |
| + | txt = txt:gsub("%d[%d%.]*", v2p) -- store just the string |
| + | return txt |
| + | end |
| + | |
| + | -- one2a scans through a string, passed as either the first unnamed parameter or |txt= |
| + | -- it converts each occurrence of 'one ' into either 'a ' or 'an ' and returns the resultant string. |
| + | p.one2a = function(frame) |
| + | local args = frame.args |
| + | if not(args[1] or args.txt) then args = frame:getParent().args end |
| + | local txt = mw.text.trim(args[1] or args.txt or "") |
| + | if txt == "" then return nil end |
| + | txt = txt:gsub(" one ", " a "):gsub("^one", "a"):gsub("One ", "A "):gsub("a ([aeiou])", "an %1"):gsub("A ([aeiou])", "An %1") |
| + | return txt |
| + | end |
| + | |
| + | -- findpagetext returns the position of a piece of text in a page |
| + | -- First positional parameter or |text is the search text |
| + | -- Optional parameter |title is the page title, defaults to current page |
| + | -- Optional parameter |plain is either true for plain search (default) or false for Lua pattern search |
| + | -- Optional parameter |nomatch is the return value when no match is found; default is nil |
| + | p._findpagetext = function(args) |
| + | -- process parameters |
| + | local nomatch = args.nomatch or "" |
| + | if nomatch == "" then nomatch = nil end |
| + | -- |
| + | local text = mw.text.trim(args[1] or args.text or "") |
| + | if text == "" then return nil end |
| + | -- |
| + | local title = args.title or "" |
| + | local titleobj |
| + | if title == "" then |
| + | titleobj = mw.title.getCurrentTitle() |
| + | else |
| + | titleobj = mw.title.new(title) |
| + | end |
| + | -- |
| + | local plain = args.plain or "" |
| + | 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) |
| + | local args = frame.args |
| + | local pargs = frame:getParent().args |
| + | for k, v in pairs(pargs) do |
| + | args[k] = v |
| + | end |
| + | if not (args[1] or args.text) then return nil end |
| + | -- just the first value |
| + | return (p._findpagetext(args)) |
| + | end |
| + | |
| + | -- returns the decoded url. Inverse of parser function {{urlencode:val|TYPE}} |
| + | -- Type is: |
| + | -- QUERY decodes + to space (default) |
| + | -- PATH does no extra decoding |
| + | -- WIKI decodes _ to space |
| + | p._urldecode = function(url, type) |
| + | url = url or "" |
| + | type = (type == "PATH" or type == "WIKI") and type |
| + | return mw.uri.decode( url, type ) |
| + | end |
| + | -- {{#invoke:String2|urldecode|url=url|type=type}} |
| + | p.urldecode = function(frame) |
| + | return mw.uri.decode( frame.args.url, frame.args.type ) |
| + | end |
| + | |
| + | -- what follows was merged from Module:StringFunc |
| + | |
| + | -- helper functions |
| + | p._GetParameters = require('Module:GetParameters') |
| + | |
| + | -- Argument list helper function, as per Module:String |
| + | p._getParameters = p._GetParameters.getParameters |
| + | |
| + | -- 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 |
| + | |
| + | -- Helper Function to interpret boolean strings, as per Module:String |
| + | p._getBoolean = p._GetParameters.getBoolean |
| + | |
| --[[ | | --[[ |
− | Кое-какие дополнительные функции для строк
| + | Strip |
| + | |
| + | This function Strips characters from string |
| + | |
| + | Usage: |
| + | {{#invoke:String2|strip|source_string|characters_to_strip|plain_flag}} |
| + | |
| + | Parameters |
| + | source: The string to strip |
| + | chars: The pattern or list of characters to strip from string, replaced with '' |
| + | plain: A flag indicating that the chars should be understood as plain text. defaults to true. |
| + | |
| + | Leading and trailing whitespace is also automatically stripped from the string. |
| ]] | | ]] |
− | local M = {
| + | function p.strip( frame ) |
− | bs=function(f)-- первый параметр до начала второго параметра (или до конца, если он не встретился)
| + | local new_args = p._getParameters( frame.args, {'source', 'chars', 'plain'} ) |
− | --необяз. 3-й параметр - с какого по номеру (с 1) символа начинать поиск.
| + | local source_str = new_args['source'] or '' |
− | 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)
| + | local chars = new_args['chars'] or '' or 'characters' |
− | end;
| + | source_str = mw.text.trim(source_str) |
− | as=function(f)-- первый параметр после начала второго параметра
| + | if source_str == '' or chars == '' then |
− | return mw.ustring.sub(f.args[1], (mw.ustring.find(f.args[1],f.args[2],1,true) or 0)+1)
| + | return source_str |
− | end;
| |
− | Tr=function(s,f,t,cf,df,sf)-- транслитерация первого параметра путём замены символов из второго параметра символами из третьего.
| |
− | -- Отдельными параметрами можно передавать флаги c, d и s, как в Perl; диапазоны в замене не работают, только в левой части
| |
− | -- (т.е. дефис надо передавать первым или последним). Второй результат - число заменённых символов
| |
− | local r, l, l2 = {}, mw.ustring.len(f), mw.ustring.len(t);
| |
− | for i = 1, l do
| |
− | r[mw.ustring.sub(f,i,i)] = i<=l2 and mw.ustring.sub(t,i,i) or df and '' or mw.ustring.sub(t,l2,l2)
| |
− | end
| |
− | local n2=0;
| |
− | local res, n = mw.ustring.gsub(
| |
− | s,
| |
− | ('[%s%s]%s'):format(
| |
− | cf and '^' or '',
| |
− | f:gsub('%','%%'):gsub(']','%]'):gsub('^%^','%^'),
| |
− | sf and '+' or ''
| |
− | ),
| |
− | sf and function(cc)
| |
− | n2 = n2+mw.ustring.len(cc)-1;
| |
− | return mw.ustring.gsub(cc,'.',r)
| |
− | end or r
| |
− | )
| |
− | return res, n+n2
| |
− | end;
| |
− | -- tr = function(f) return (M.Tr(f.args[1],f.args[2],f.args[3],f.args['c'],f.args['d'],f.args['s'])) end;-- транслитерировать
| |
− | -- trс = function(f) return ({M.Tr(f.args[1],f.args[2],f.args[3],f.args['c'],f.args['d'],f.args['s'])})[2] end;-- посчитать символы
| |
− | Trg = function(s,t,f,fi)-- Производит замену строк произвольной длины (если с fi, регистр не учитывает).
| |
− | -- Приоритет - по порядку в таблицах.
| |
− | for n,p in ipairs(t) do
| |
− | t[n] = {fi and mw.ustring.upper(p) or p,mw.ustring.len(p)}
| |
− | end
| |
− | local r,i,l,N = {},1,mw.ustring.len(s),0
| |
− | while i<=l do
| |
− | (function()
| |
− | for n,p in ipairs(t) do
| |
− | if ( fi and mw.ustring.upper(mw.ustring.sub(s,i,i+p[2]-1)) or mw.ustring.sub(s,i,i+p[2]-1) ) == p[1] then
| |
− | table.insert(r,f[n]);
| |
− | i = i+p[2]; N=N+1;
| |
− | return
| |
− | end
| |
− | end
| |
− | table.insert(r,mw.ustring.sub(s,i,i));
| |
− | i=i+1;
| |
− | return
| |
− | end)()
| |
− | end
| |
− | return table.concat(r),N
| |
− | end;
| |
− | trg = function(frame)--Работает с номерными аргументами шаблона,если задан параметр u, иначе со своими.
| |
− | -- Заменяет в первом аргументе аргументы 2, 4, 6... на аргументы 3, 5, 7...
| |
− | local tf, t, f, i= frame.args['u'] and frame.getParent() or f, {}, {}, 1;
| |
− | while tf.args[2*i] do t[tf.args[2*i]]=tf.args[2*i+1] or '' end
| |
− | return ( M.Trg(tf.args[1],t,f,(frame.args['i'] or '')~='') )
| |
− | end;
| |
− | join = function (f) --объединяет нумерованные аргументы вызвавшего шаблона
| |
− | -- от from или 1 до to или первого отсутствующего
| |
− | -- через первый параметр invoke. Последний элемент можно присоединять иначе, задав второй параметр.
| |
− | -- По умолчанию ',' & 'и'
| |
− | -- Если 3-й параметр invoke — "s", строки из пробелов игнорируются; если "_", игнорируются пустые строки
| |
− | local t, tf, i = {}, f:getParent(), tonumber(f.args.from) or 1
| |
− | local k,j,m = tonumber(f.args.to),i,f.args[3]
| |
− | while k and i<=k or tf.args[i] do
| |
− | if (
| |
− | ({
| |
− | ['_']=function(s)return s~=''end;
| |
− | ['s']=function(s)return not tostring(s):match("^%s*$")end
| |
− | })[m] or function() return true end
| |
− | )(tf.args[i]) then
| |
− | t[j]=tf.args[i];
| |
− | j=j+1
| |
− | end;
| |
− | i=i+1
| |
− | end
| |
− | return mw.text.listToText(t,f.args[1],f.args[2] or f.args[1])
| |
| end | | 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 |
| | | |
− | function M.formatRound(frame) --форматирует число, чтобы оно имело order знаков после запятой
| + | --[[ |
− |
| + | Match any |
− | return string.format("%0."..frame.args[2].."f",tonumber(frame.args[1])); | + | Returns the index of the first given pattern to match the input. Patterns must be consecutively numbered. |
− |
| + | Returns the empty string if nothing matches for use in {{#if:}} |
| + | |
| + | Usage: |
| + | {{#invoke:String2|matchAll|source=123 abc|456|abc}} returns '2'. |
| + | |
| + | Parameters: |
| + | source: the string to search |
| + | plain: A flag indicating that the patterns should be understood as plain text. defaults to true. |
| + | 1, 2, 3, ...: the patterns to search for |
| + | ]] |
| + | function p.matchAny(frame) |
| + | local source_str = frame.args['source'] or error('The source parameter is mandatory.') |
| + | local l_plain = p._getBoolean( frame.args['plain'] or true ) |
| + | for i = 1, math.huge do |
| + | local pattern = frame.args[i] |
| + | if not pattern then return '' end |
| + | if mw.ustring.find(source_str, pattern, 1, l_plain) then |
| + | return tostring(i) |
| + | end |
| + | end |
| end | | end |
| | | |
− | -- если строка s содержит число, увеличивает первое такое число на n, иначе возращает пустую строку. | + | --[[--------------------------< H Y P H E N _ T O _ D A S H >-------------------------------------------------- |
− | -- если число начинается на 0, то увеличенное число будет содержать по крайне мере столько цифр сколько исходное. | + | |
− | function M.increase(s, n) | + | Converts a hyphen to a dash under certain conditions. The hyphen must separate |
− | local a,b,c = string.match(s, "([^0-9]*)([0-9]+)(.*)")
| + | like items; unlike items are returned unmodified. These forms are modified: |
− | if b==nil then return s end
| + | letter - letter (A - B) |
− | local num = tonumber(b) + n
| + | digit - digit (4-5) |
− | if b:sub(1,1)=='0'
| + | digit separator digit - digit separator digit (4.1-4.5 or 4-1-4-5) |
− | then b = string.format("%0"..b:len().."d", num)
| + | letterdigit - letterdigit (A1-A5) (an optional separator between letter and |
− | else b=num | + | digit is supported – a.1-a.5 or a-1-a-5) |
| + | digitletter - digitletter (5a - 5d) (an optional separator between letter and |
| + | digit is supported – 5.a-5.d or 5-a-5-d) |
| + | |
| + | any other forms are returned unmodified. |
| + | |
| + | str may be a comma- or semicolon-separated list |
| + | |
| + | ]] |
| + | 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+$') then -- letter hyphen letter |
| + | item = item:gsub ('(%w*[%.%-]?%w+)%s*%-%s*(%w*[%.%-]?%w+)', '%1–%2') -- replace hyphen, remove extraneous space characters |
| + | else |
| + | item = mw.ustring.gsub (item, '%s*[–—]%s*', '–') -- for endash or emdash separated ranges, replace em with en, remove extraneous whitespace |
| + | end |
| + | end |
| + | table.insert (out, item) -- add the (possibly modified) item to the output table |
| end | | end |
− | return a .. b .. c
| + | |
| + | local temp_str = table.concat (out, ',' .. spacing) -- concatenate the output table into a comma separated string |
| + | temp_str, accept = temp_str:gsub ('^%(%((.+)%)%)$', '%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 | | end |
− | return M | + | |
| + | 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]] |
| + | function p.startswith(frame) |
| + | return (frame.args[1]:sub(1, frame.args[2]:len()) == frame.args[2]) and 'yes' or '' |
| + | end |
| + | |
| + | return p |