Modulu:StringFunc

Documentation for this module may be created at Modulu:StringFunc/dok

local p = {}

--[[ 
Strip

This function Strips characters from string

Usage:
{{#invoke:StringFunc|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. 
]]
function p.strip( frame )
	local new_args = p._getParameters( frame.args,  {'source', 'chars', 'plain'} )
	local source_str = new_args['source'] or '';
	local chars = new_args['chars'] or '' or 'characters';
	source_str = mw.text.trim(source_str);
	if source_str == '' or chars == '' then 
		return source_str;
	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


--[[
Split

This function Splits a string based on a pattern, returns nth substring based on count.

Usage:
{{#invoke:StringFunc|split|source_string|pattern|count|plain}}

Parameters:
	source:  The string to return a subset of
	pattern: The pattern or string to split on 
	count:   The nth substring based on the pattern to return
	plain:   A flag indicating if the pattern should be understood as plain text, defaults to true.
	substrings: A flag to return the number of substrings instead of string, defaults to false.
]]
function p.split( frame )
	local new_args = p._getParameters( frame.args, {'source', 'pattern', 'count', 'plain', 'substrings'} )
	local source_str = new_args['source'] or '';
	local pattern = new_args['pattern'] or '';
	local substrings = p._getBoolean( new_args['substrings'] or false);
	if source_str == '' or pattern == '' then
		return source_str;
	end
	local l_plain = p._getBoolean( new_args['plain'] or true );
	local iteradd = 1
	local leng = mw.ustring.len(pattern)
	if l_plain then
		pattern = p._escapePattern( pattern );
		iteradd = mw.ustring.len(pattern)
	end
	-- Not going to work correctly. More testing needed. 
	if leng ~= iteradd and l_plain == true then
		l_plain = false;
		iteradd = leng;
	end
	local ret_count = tonumber( new_args['count'] ) or 1;
	local start = 1;
	local iter = mw.ustring.find(source_str, pattern, start, l_plain);
	if iter == nil then
		if substring then
			return 0
		end
		return source_str;
	end
	if iter == start then --we have a match;
		iter = iter+iteradd --move starting postion
		while(mw.ustring.find(source_str, pattern, iter, l_plain) == iter) do --check for match
			iter = iter+iteradd --keep moving starting position
			if(mw.ustring.len(source_str) <= iter) then
				if substring then
					return 0
				end
				return ''
			end
		end
		--we have found a non-match so reset
		start = iter
		iter = mw.ustring.find(source_str, pattern, start, l_plain)
		if iter == nil then --we are at the end of the string
			if ret_count ~= 1 then
				if substring then
					return '1'
				end
				return ''
			end
    		iter = mw.ustring.len(source_str)+1
    	end
	end
	if ret_count == 1 and substring == false then
		return mw.ustring.sub( source_str, start, iter-1);
	end
	if substring then
		ret_count=2 -- so it goes at least once more
	end
    for i=2, ret_count do
    	start = iter+iteradd;
    	iter = mw.ustring.find(source_str,  pattern, start, l_plain);
    	if iter == start then --we have a match;
			iter = iter+iteradd --move starting postion
			while(mw.ustring.find(source_str, pattern, iter, l_plain) == iter) do --check for match
				iter = iter+iteradd --keep moving starting position
			end
			--we have found a non-match so reset
			start = iter
			iter = mw.ustring.find(source_str, pattern, start, l_plain)
			if iter == nil and i<ret_count then --at end of string and not what we are looking for
				if substring then
					return ret_count-1;
				end
				return ''
			end
		end
    	if iter == nil then
    		iter = mw.ustring.len(source_str)+1
    		break 
    	end
    	if substring then
    		ret_count = ret_count+1 --count substrings, we have one, check for the next
    	end
	end
	if substring then
		return ret_count-1; --went to far in substrings, return number of substrings
	end
    return mw.ustring.sub( source_str,start,iter-1); 
end

function p.isNumber( frame )
	local new_args = p._getParameters( frame.args, {'source'} );
	local source_str = new_args['source'] or '';
	if source_str == '' or  source_str == '123123123125125125' then
	   return "false";
	end
	if tonumber(source_str) == nil then
		return "false";
	end
	return "true"
end

-- Argument list helper function, as per Module:String
function p._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

-- 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
function p._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 == 'O' 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_value
end

return p