Mòdul:String

--[[This module is intended to provide access to basic string functions.Most of the functions provided here can be invoked with named parameters,unnamed parameters, or a mixture.  If named parameters are used, Mediawiki willautomatically remove any leading or trailing whitespace from the parameter.Depending on the intended use, it may be advantageous to either preserve orremove such whitespace.Global options    ignore_errors: If set to 'true' or 1, any error condition will result in        an empty string being returned rather than an error message.    error_category: If an error occurs, specifies the name of a category to        include with the error message.  The default category is        [Category:Errors reported by Module String].    no_category: If set to 'true' or 1, no category will be added if an error        is generated.Unit tests for this module are available at Module:String/tests.]]local p = {}--[[Helper function that populates the argument list given that user may need to use a mix ofnamed and unnamed parameters.  This is relevant because named parameters are notidentical to unnamed parameters due to string trimming, and when dealing with stringswe sometimes want to either preserve or remove that whitespace depending on the application.]]local function _getParameters( frame_args, arg_list )local new_args = {}local index = 1local valuefor _, arg in ipairs( arg_list ) dovalue = frame_args[arg]if value == nil thenvalue = frame_args[index]index = index + 1endnew_args[arg] = valueendreturn new_argsend        --[[Helper Function to interpret boolean strings]]local function _getBoolean( boolean_str )local boolean_valueif type( boolean_str ) == 'string' thenboolean_str = boolean_str:lower()if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0' or boolean_str == '' thenboolean_value = falseelseboolean_value = trueendelseif type( boolean_str ) == 'boolean' thenboolean_value = boolean_strelseerror( 'Cap de valor booleana trobada' )endreturn boolean_valueend--[[Helper function to handle error messages.]]local function _error( error_str )local frame = mw.getCurrentFrame()local error_category = frame.args.error_category or 'Errors detectats pel modul «String»'local ignore_errors = frame.args.ignore_errors or falselocal no_category = frame.args.no_category or falseif _getBoolean(ignore_errors) thenreturn ''endlocal error_str = '<strong class="error">Error del modul «String»: ' .. error_str .. '</strong>'if error_category ~= '' and not _getBoolean( no_category ) thenerror_str = '[[Categoria:' .. error_category .. ']]' .. error_strendreturn error_strend--[[Helper function that escapes all pattern characters so that they will be treatedas plain text.]]local function _escapePattern( pattern_str )return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )end--[[lenThis function returns the length of the target string.Usage:{{#invoke:String|len|target_string|}}OR{{#invoke:String|len|s=target_string}}Parameters    s: The string whose length to reportIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the target string.]]function p.len( frame )local new_args = _getParameters( frame.args, {'s'} )local s = new_args['s'] or ''return mw.ustring.len( s )end--[[subThis function returns a substring of the target string at specified indices.Usage:{{#invoke:String|sub|target_string|start_index|end_index}}OR{{#invoke:String|sub|s=target_string|i=start_index|j=end_index}}Parameters    s: The string to return a subset of    i: The fist index of the substring to return, defaults to 1.    j: The last index of the string to return, defaults to the last character.The first character of the string is assigned an index of 1.  If either i or jis a negative value, it is interpreted the same as selecting a character bycounting from the end of the string.  Hence, a value of -1 is the same asselecting the last character of the string.If the requested indices are out of range for the given string, an error isreported.]]function p.sub( frame )local new_args = _getParameters( frame.args, { 's', 'i', 'j' } )local s = new_args['s'] or ''local i = tonumber( new_args['i'] ) or 1local j = tonumber( new_args['j'] ) or -1local len = mw.ustring.len( s )-- Convert negatives for range checkingif i < 0 theni = len + i + 1endif j < 0 thenj = len + j + 1endif i > len or j > len or i < 1 or j < 1 thenreturn _error( 'Indicis en defòra del reng de la cadena' )endif j < i thenreturn _error( 'Indicis de la cadena pas ordenats' )endreturn mw.ustring.sub( s, i, j )end--[[matchThis function returns a substring from the source string that matches aspecified pattern.Usage:{{#invoke:String|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}OR{{#invoke:String|match|s=source_string|pattern=pattern_string|start=start_index    |match=match_number|plain=plain_flag|nomatch=nomatch_output}}Parameters    s: The string to search    pattern: The pattern or string to find within the string    start: The index within the source string to start the search.  The first        character of the string has index 1.  Defaults to 1.    match: In some cases it may be possible to make multiple matches on a single        string.  This specifies which match to return, where the first match is        match= 1.  If a negative number is specified then a match is returned        counting from the last match.  Hence match = -1 is the same as requesting        the last match.  Defaults to 1.    plain: A flag indicating that the pattern should be understood as plain        text.  Defaults to false.    nomatch: If no match is found, output the "nomatch" value rather than an error.If invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from each string.  In some circumstances this is desirable, inother cases one may want to preserve the whitespace.If the match_number or start_index are out of range for the string being queried, thenthis function generates an error.  An error is also generated if no match is found.If one adds the parameter ignore_errors=true, then the error will be suppressed andan empty string will be returned on any failure.For information on constructing Lua patterns, a form of [regular expression], see:* http://www.lua.org/manual/5.1/manual.html#5.4.1* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns]]-- This sub-routine is exported for use in other modulesfunction p._match( s, pattern, start, match_index, plain_flag, nomatch )if s == '' thenreturn _error( 'Cadena ont recercar es vuèja' )endif pattern == '' thenreturn _error( 'Cadena de recèrca es vuèja' )endstart = tonumber(start) or 1if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) thenreturn _error( 'Indici d\'inici defòra del reng de la cadena' )endif match_index == 0 thenreturn _error( 'Numèro de coïncidéncia defòra de reng' )endif plain_flag thenpattern = str._escapePattern( pattern )endlocal resultif match_index == 1 then-- Find first match is simple caseresult = mw.ustring.match( s, pattern, start )elseif start > 1 thens = mw.ustring.sub( s, start )endlocal iterator = mw.ustring.gmatch(s, pattern)if match_index > 0 then-- Forward searchfor w in iterator domatch_index = match_index - 1if match_index == 0 thenresult = wbreakendendelse-- Reverse searchlocal result_table = {}local count = 1for w in iterator doresult_table[count] = wcount = count + 1endresult = result_table[ count + match_index ]endendif result == nil thenif nomatch == nil thenreturn _error( 'Cap de coïncidéncia trobada' )elsereturn nomatchendelsereturn resultendend-- This is the entry point for #invoke:String|matchfunction p.match( frame )local new_args = _getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} )local s = new_args['s'] or ''local start = tonumber( new_args['start'] ) or 1local plain_flag = _getBoolean( new_args['plain'] or false )local pattern = new_args['pattern'] or ''local match_index = math.floor( tonumber(new_args['match']) or 1 )local nomatch = new_args['nomatch']return p._match( s, pattern, start, match_index, plain_flag, nomatch )end--[[posThis function returns a single character from the target string at position pos.Usage:{{#invoke:String|pos|target_string|index_value}}OR{{#invoke:String|pos|target=target_string|pos=index_value}}Parameters    target: The string to search    pos: The index for the character to returnIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the target string.  In some circumstances this is desirable, inother cases one may want to preserve the whitespace.The first character has an index value of 1.If one requests a negative value, this function will select a character by counting backwardsfrom the end of the string.  In other words pos = -1 is the same as asking for the last character.A requested value of zero, or a value greater than the length of the string returns an error.]]function p.pos( frame )local new_args = _getParameters( frame.args, {'target', 'pos'} )local target_str = new_args['target'] or ''local pos = tonumber( new_args['pos'] ) or 0if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) thenreturn _error( 'Indici en defòra del reng de la cadena' )end    return mw.ustring.sub( target_str, pos, pos )end--[[findThis function allows one to search for a target string or pattern within anotherstring.Usage:{{#invoke:String|find|source_str|target_string|start_index|plain_flag}}OR{{#invoke:String|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}Parameters    source: The string to search    target: The string or pattern to find within source    start: The index within the source string to start the search, defaults to 1    plain: Boolean flag indicating that target should be understood as plain        text and not as a Lua style regular expression, defaults to trueIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the parameter.  In some circumstances this is desirable, inother cases one may want to preserve the whitespace.This function returns the first index >= "start" where "target" can be foundwithin "source".  Indices are 1-based.  If "target" is not found, then thisfunction returns 0.  If either "source" or "target" are missing / empty, thisfunction also returns 0.This function should be safe for UTF-8 strings.]]function p.find( frame )local new_args = _getParameters( frame.args, {'source', 'target', 'start', 'plain' } ) local source_str = new_args['source'] or ''local pattern = new_args['target'] or ''local start_pos = tonumber(new_args['start']) or 1local plain = new_args['plain'] or trueif source_str == '' or pattern == '' thenreturn 0end    plain = _getBoolean( plain )local start = mw.ustring.find( source_str, pattern, start_pos, plain )if start == nil thenstart = 0endreturn startend--[[replaceThis function allows one to replace a target string or pattern within anotherstring.Usage:{{#invoke:String|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}OR{{#invoke:String|replace|source=source_string|pattern=pattern_string|replace=replace_string|   count=replacement_count|plain=plain_flag}}Parameters    source: The string to search    pattern: The string or pattern to find within source    replace: The replacement text    count: The number of occurences to replace, defaults to all.    plain: Boolean flag indicating that pattern should be understood as plain        text and not as a Lua style regular expression, defaults to true]]function p.replace( frame )local new_args = _getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } )local source_str = new_args['source'] or ''local pattern = new_args['pattern'] or ''local replace = new_args['replace'] or ''local count = tonumber( new_args['count'] )local plain = new_args['plain'] or trueif source_str == '' or pattern == '' thenreturn source_strend    plain = _getBoolean( plain )if plain thenpattern = _escapePattern( pattern )replace = mw.ustring.gsub( replace, "%%", "%%%%" ) --Only need to escape replacement sequences.endlocal resultif count ~= nil thenresult = mw.ustring.gsub( source_str, pattern, replace, count )elseresult = mw.ustring.gsub( source_str, pattern, replace )end        return resultend--[[    simple function to pipe string.rep to templates.]]function p.rep( frame )local repetitions = tonumber( frame.args[2] )if not repetitions then return _error( "S'esperava un numèro coma segond paramètre; trobat: " .. ( frame.args[2] or '' ))endreturn string.rep( frame.args[1] or '', repetitions )end--[[escapePatternThis function escapes special characters from a Lua string pattern. See [1]for details on how patterns work.[1] https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#PatternsUsage:{{#invoke:String|escapePattern|pattern_string}}Parameters    pattern_string: The pattern string to escape.]]function p.escapePattern( frame )local pattern_str = frame.args[1]if not pattern_str thenreturn _error( 'Cap de cadena de modèl especificada' )endlocal result = _escapePattern( pattern_str )return resultend--[[countThis function counts the number of occurrences of one string in another.]]function p.count(frame)local args = _getParameters(frame.args, {'source', 'pattern', 'plain'})local source = args.source or ''local pattern = args.pattern or ''local plain = _getBoolean(args.plain or true)if plain thenpattern = _escapePattern(pattern)endlocal _, count = mw.ustring.gsub(source, pattern, '')return countend--[[endswithThis function determines whether a string ends with another string.]]function p.endswith(frame)local args = _getParameters(frame.args, {'source', 'pattern'})local source = args.source or ''local pattern = args.pattern or ''if pattern == '' then-- All strings end with the empty string.return "yes"endif mw.ustring.sub(source, -mw.ustring.len(pattern), -1) == pattern thenreturn "yes"elsereturn ""endend--[[joinJoin all non empty arguments together; the first argument is the separator.Usage:{{#invoke:String|join|sep|one|two|three}}]]function p.join(frame)local args = {}local sepfor _, v in ipairs( frame.args ) doif sep thenif v ~= '' thentable.insert(args, v)endelsesep = vendendreturn table.concat( args, sep or '' )end--[[ StripThis function Strips charecters from stringUsage:{{#invoke:StringFunc|strip|source_string|charecters_to_strip|plain_flag}}Parameterssource: The string to stripchars:  The pattern or list of charecters 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. ]]function p.strip( frame )local new_args = _getParameters( frame.args,  {'source', 'chars', 'plain'} )local source_str = new_args['source'] or ''local chars = new_args['chars'] or ''source_str = mw.text.trim(source_str)if source_str == '' or chars == '' then return source_strendlocal l_plain = _getBoolean( new_args['plain'] or true )if l_plain thenchars = _escapePattern( chars )endlocal resultresult = mw.ustring.gsub(source_str, "["..chars.."]", '')return resultend--[[SplitThis function Splits a string based on a separator, returns nth substring based on count.Usage:{{#invoke:StringFunc|split|source_string|separator|count}}Parameters:source:    The string to return a subset ofseparator: The string to split on count:     The nth substring based on the separator to return]]function p.split( frame )local new_args = _getParameters( frame.args, {'source', 'separator', 'count'} )local source_str = new_args['source'] or ''local separator = (new_args['separator'] or ''):gsub('"', '')local separator_len = mw.ustring.len(separator)if source_str == '' or separator == '' thenreturn source_str;endlocal ret_count = tonumber( new_args['count'] ) or 1if ret_count < 1 thenreturn ""endlocal start = 1local iter = mw.ustring.find(source_str, separator, start, true)if iter == nil thenif ret_count == 1 thenreturn source_strelsereturn ""endelseiter = iter - 1endif ret_count == 1 thenreturn mw.ustring.sub( source_str, start, iter)end    for i=2, ret_count do    start = iter+separator_len + 1    iter = mw.ustring.find(source_str, separator, start, true)    if iter == nil then    if ret_count == i then    return mw.ustring.sub(source_str, start, mw.ustring.len(source_str))    else    return ""    end    else    iter = iter - 1    end    end    return mw.ustring.sub( source_str,start,iter)endfunction p.isNumber( frame )local new_args = _getParameters( frame.args, {'source'} )local source_str = new_args['source'] or ''if source_str == '' then   return "false"endif tonumber(source_str) == nil and tonumber(string.gsub(source_str, ",", ".", 1) .. '') == nil thenreturn "false"endreturn "true"endreturn p