查看“︁Module:String”︁的源代码

--[[  

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 will 
automatically remove any leading or trailing whitespace from the parameter.  
Depending on the intended use, it may be advantageous to either preserve or
remove 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 str = {}

--[[
len
]]
function str.len( frame )
    local new_args = str._getParameters( frame.args, {'s'} );
    local s = new_args['s'] or '';
    return mw.ustring.len( s )
end

--[[
sub
]]
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 );

    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( '截取字符串索引脱离区间' );
    end
    if j < i then
        return str._error( '截取字符串指示脱离顺序' );
    end
    
    return mw.ustring.sub( s, i, j )
end

--[[
sublength
]]
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

--[[
match
]]
function 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'];
    
    if s == '' then
        return str._error( '目标字符串是空的' );
    end
    if pattern == '' then
        return str._error( '模式字符串是空的' );
    end
    if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then
        return str._error( '要求的起始点脱离区间' );
    end
    if match_index == 0 then
        return str._error( '匹配索引脱离区间' );
    end
    if plain_flag then
        pattern = str._escapePattern( pattern );
    end
    
    local result
    if match_index == 1 then
        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
            for w in iterator do
                match_index = match_index - 1;
                if match_index == 0 then
                    result = w;
                    break;
                end
            end    
        else
            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( '找不到匹配' );
        else
            return nomatch;
        end
    else
        return result;
    end
end

--[[
pos
]]
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( '字符串索引脱离区间' );
    end    
    
    return mw.ustring.sub( target_str, pos, pos );
end

--[[
str_find
]]
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 start
end

--[[
find
]]
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 start
end

--[[
replace
]]
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, "%%", "%%%%" );
    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 result;
end

--[[
rep
]]
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

--[[
split
]]
function str.split(inputstr, sep, no_pattern, ignore_null)
	if type(inputstr) == type({table}) then
		if not getArgs then getArgs = require('Module:Arguments').getArgs end
		args = getArgs(inputstr, {parentFirst=true})
		for arg_name, arg_value in pairs( args ) do
			if arg_name == 1 or arg_name == '1' or arg_name == "str" or arg_name == "inputstr" or arg_name == "input" then
				input_str = arg_value
			elseif arg_name == 2 or arg_name == '2' or arg_name == "sep" or arg_name == "separator" then
				separ = arg_value
			elseif arg_name == 3 or arg_name == '3' or arg_name == "no_pattern" or arg_name == "no pattern" then
				no_pattern_flag = arg_value
			elseif arg_name == 4 or arg_name == '4' or arg_name == "ignore_null" or arg_name == "ignore null" then
				ignore_null_flag = arg_value
			elseif arg_name == 5 or arg_name == '5' or arg_name == "format" then
				format = arg_value or "*{{{1}}}\n";
			end
		end
		if not yesno then yesno = require('Module:Yesno') end
		no_pattern_flag = yesno( no_pattern_flag or 'yes' )
		ignore_null_flag = yesno( ignore_null_flag or 'no' )
		is_invoke = true
		format = mw.ustring.gsub(format or "*{{{1}}}\n", "%{%{%{.-%}%}%}", "%%s" );
		it = mw.ustring.find(format, "%%s", 1)
		if it == nil then format = format .. "%s" end
		format = mw.ustring.gsub(format, "\\n", "\n")
	else
		input_str = inputstr
		separ = sep
		no_pattern_flag = no_pattern
		ignore_null_flag = ignore_null
		is_invoke = false
	end
	input_str = input_str or '' 
	separ = separ or "%s"
	if no_pattern_flag == nil then no_pattern_flag = true end
	if ignore_null_flag == nil then ignore_null_flag = false end

	length = mw.ustring.len(input_str)
	if no_pattern_flag then
		separ = mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(mw.ustring.gsub(separ, 
			"%[", "%["), "%]", "%]"), "%{", "%{"), "%}", "%}"), "%%", "%%%%"), "%)", "%)"), "%-", "%-"),
			"%^", "%^"), "%$", "%$"), "%(", "%("), "%.", "%."), "%*", "%*"), "%+", "%+"), "%|", "%|");
	end
	iterator = 1 ; i = 1 ; flag = true
	result = {}
	separ_str_begin, separ_str_end = mw.ustring.find(input_str, separ, iterator)
	debug1 = 1
	while flag do
		debug1 = debug1 + 1
		if separ_str_begin == nil or iterator > length or debug1 >= 100 then
			separ_str_begin = 0
			separ_str_end = -2
			flag = false
		end
		if separ_str_end < separ_str_begin then separ_str_end = separ_str_begin end
		finded_str = mw.ustring.sub(input_str, iterator, separ_str_begin - 1)
		if not(mw.text.trim(finded_str) == '' and ignore_null_flag) then
			result[i] = finded_str
			i = i + 1
		end

		iterator = separ_str_end + 1
		separ_str_begin, separ_str_end = mw.ustring.find(input_str, separ, iterator)
	end
	if is_invoke then
		body = ''
		for i, result_str in pairs( result ) do
			body = body .. mw.ustring.gsub(format, "%%s", result_str)
		end
		return body
	end
	return result;
end

--[[
join
]]
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 functions

function str._getParameters( frame_args, arg_list )
    local new_args = {};
    local index = 1;
    local value;
    
    for i,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_args;
end        

function str._error( error_str )
    local frame = mw.getCurrentFrame();
    local error_category = frame.args.error_category or '字符串模块报告的错误';
    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 = '<strong class="error">字符串模块出错：' .. error_str .. '</strong>';
    if error_category ~= '' and not str._getBoolean( no_category ) then
        error_str = '[[Category:' .. error_category .. ']]' .. error_str;
    end        
    
    return error_str;
end

function 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( '布尔值找不到' );
    end    
    return boolean_value
end

function str._escapePattern( pattern_str )
    return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );
end

return str