Mô_đun:String

--[=[ Mô đun này nhằm cung cấp các hàm chuỗi cơ bản.Phần nhiều hàm này cho phép gọi với các tham số có tên, các tham số không cótên, hoặc pha trộn cả hai kiểu. Nếu sử dụng các tham số có tên, MediaWiki tựđộng bỏ qua khoảng cách đằng truớc và đằng sau tham số. Tùy cách sử dụng, bạn cóthể cần giữ hoặc bỏ qua khoảng cách này.Các tùy chọn toàn cục:Các trường hợp kiểm thử đơn vị cho mô đun này có sẵn tại Module:String/tests.]=]--[[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 optionsUnit tests for this module are available at Module:String/tests.]]local str = {}--[[lenThis function returns the length of the target string.Usage:13OR13Parameters s: The string whose length to reportIf invoked using named parameters, Mediawiki will automatically remove any leading ortrailing whitespace from the target string.]]function str.len( frame ) local new_args = str._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:target_stringORtarget_stringParameters 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 str.sub( frame ) local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } ) local s = new_args['s'] or local i = tonumber( new_args['i'] ) or 1 local j = tonumber( new_args['j'] ) or -1 local len = mw.ustring.len( s ) -- Convert negatives for range checking if i < 0 then i = len + i + 1 end if j < 0 then j = len + j + 1 end if i > len or j > len or i < 1 or j < 1 then return str._error( 'String subset index out of range' ) end if j < i then return str._error( 'String subset indices out of order' ) end return mw.ustring.sub( s, i, j )end--[[This function implements that features of and is kept in orderto maintain these older templates.]]function str.sublength( frame ) local i = tonumber( frame.args.i ) or 0 local len = tonumber( frame.args.len ) return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )end--[[_matchThis function returns a substring from the source string that matches aspecified pattern. It is exported for use in other modulesUsage:strmatch = require("Module:String")._matchsresult = strmatch( s, pattern, start, match, plain, nomatch )ParametersFor information on constructing Lua patterns, a form of [regular expression], see:]]-- This sub-routine is exported for use in other modulesfunction str._match( s, pattern, start, match_index, plain_flag, nomatch ) if s == then return str._error( 'Target string is empty' ) end if pattern == then return str._error( 'Pattern string is empty' ) end start = tonumber(start) or 1 if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then return str._error( 'Requested start is out of range' ) end if match_index == 0 then return str._error( 'Match index is out of range' ) end if plain_flag then pattern = str._escapePattern( pattern ) end local result if match_index == 1 then -- Find first match is simple case result = mw.ustring.match( s, pattern, start ) else if start > 1 then s = mw.ustring.sub( s, start ) end local iterator = mw.ustring.gmatch(s, pattern) if match_index > 0 then -- Forward search for w in iterator do match_index = match_index - 1 if match_index == 0 then result = w break end end else -- Reverse search local result_table = {} local count = 1 for w in iterator do result_table[count] = w count = count + 1 end result = result_table[ count + match_index ] end end if result == nil then if nomatch == nil then return str._error( 'Match not found' ) else return nomatch end else return result endend--[[matchThis function returns a substring from the source string that matches aspecified pattern.Usage:nomatch_outputORnomatch_outputParametersIf 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:]]-- This is the entry point for #invoke:String|matchfunction str.match( frame ) local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} ) local s = new_args['s'] or local start = tonumber( new_args['start'] ) or 1 local plain_flag = str._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 str._match( s, pattern, start, match_index, plain_flag, nomatch )end--[[posThis function returns a single character from the target string at position pos.Usage:String Module Error: String index out of rangeORString Module Error: String index out of rangeParameters 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 str.pos( frame ) local new_args = str._getParameters( frame.args, {'target', 'pos'} ) local target_str = new_args['target'] or local pos = tonumber( new_args['pos'] ) or 0 if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) then return str._error( 'String index out of range' ) end return mw.ustring.sub( target_str, pos, pos )end--[[str_findThis function duplicates the behavior of 1, including all of its quirks.This is provided in order to support existing templates, but is NOT RECOMMENDED fornew code and templates. New code is recommended to use the "find" function instead.Returns the first index in "source" that is a match to "target". Indexing is 1-based,and the function returns -1 if the "target" string is not present in "source".Important Note: If the "target" string is empty / missing, this function returns avalue of "1", which is generally unexpected behavior, and must be accounted forseparatetly.]]function str.str_find( frame ) local new_args = str._getParameters( frame.args, {'source', 'target'} ) local source_str = new_args['source'] or local target_str = new_args['target'] or if target_str == then return 1 end local start = mw.ustring.find( source_str, target_str, 1, true ) if start == nil then start = -1 end return startend--[[findThis function allows one to search for a target string or pattern within anotherstring.Usage:ORParameters 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 str.find( frame ) local new_args = str._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 1 local plain = new_args['plain'] or true if source_str == or pattern == then return 0 end plain = str._getBoolean( plain ) local start = mw.ustring.find( source_str, pattern, start_pos, plain ) if start == nil then start = 0 end return startend--[[replaceThis function allows one to replace a target string or pattern within anotherstring.Usage:source_strORsource_stringParameters 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 str.replace( frame ) local new_args = str._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 true if source_str == or pattern == then return source_str end plain = str._getBoolean( plain ) if plain then pattern = str._escapePattern( pattern ) replace = mw.ustring.gsub( replace, "%%", "%%%%" ) --Only need to escape replacement sequences. end local result if count ~= nil then result = mw.ustring.gsub( source_str, pattern, replace, count ) else result = mw.ustring.gsub( source_str, pattern, replace ) end return resultend-- simple function to pipe string.rep to templates.function str.rep( frame ) local repetitions = tonumber( frame.args[2] ) if not repetitions then return str._error( 'function rep expects a number as second parameter, received "' .. ( frame.args[2] or ) .. '"' ) end return 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:pattern_stringParameters]]function str.escapePattern( frame ) local pattern_str = frame.args[1] if not pattern_str then return str._error( 'No pattern string specified' ) end local result = str._escapePattern( pattern_str ) return resultend--[[countThis function counts the number of occurrences of one string in another.]]function str.count(frame) local args = str._getParameters(frame.args, {'source', 'pattern', 'plain'}) local source = args.source or local pattern = args.pattern or local plain = str._getBoolean(args.plain or true) if plain then pattern = str._escapePattern(pattern) end local _, count = mw.ustring.gsub(source, pattern, ) return countend--[[endswithThis function determines whether a string ends with another string.]]function str.endswith(frame) local args = str._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" end if mw.ustring.sub(source, -mw.ustring.len(pattern), -1) == pattern then return "yes" else return "" endend--[[joinJoin all non empty arguments together; the first argument is the separator.Usage:oneseptwosepthree]]function str.join(frame) local args = {} local sep for _, v in ipairs( frame.args ) do if sep then if v ~= then table.insert(args, v) end else sep = v end end return table.concat( args, sep or )end--[[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.]]function str._getParameters( frame_args, arg_list ) local new_args = {} local index = 1 local value for _, arg in ipairs( arg_list ) do value = frame_args[arg] if value == nil then value = frame_args[index] index = index + 1 end new_args[arg] = value end return new_argsend--Helper function to handle error messages.function str._error( error_str ) local frame = mw.getCurrentFrame() local error_category = frame.args.error_category or 'Errors reported by Module String' local ignore_errors = frame.args.ignore_errors or false local no_category = frame.args.no_category or false if str._getBoolean(ignore_errors) then return end local error_str = 'String Module Error: ' .. error_str .. '' if error_category ~= and not str._getBoolean( no_category ) then error_str = '' .. error_str end return error_strend--Helper Function to interpret boolean stringsfunction str._getBoolean( boolean_str ) local boolean_value if type( boolean_str ) == 'string' then boolean_str = boolean_str:lower() if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0' or boolean_str == then boolean_value = false else boolean_value = true end elseif type( boolean_str ) == 'boolean' then boolean_value = boolean_str else error( 'No boolean value found' ) end return boolean_valueend--[[Helper function that escapes all pattern characters so that they will be treatedas plain text.]]function str._escapePattern( pattern_str ) return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )endreturn str