Module:String: Difference between revisions

--[[   

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  

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

This 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 report

If invoked using named parameters, Mediawiki will automatically remove any leading or

trailing whitespace from the target string.   

     return mw.ustring.len( s )

end

--[[

sub

This 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 j

is a negative value, it is interpreted the same as selecting a character by  

counting from the end of the string.  Hence, a value of -1 is the same as  

selecting the last character of the string.

If the requested indices are out of range for the given string, an error is  

reported.

     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

         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' );

         return str._error( 'String subset indices out of order' );

     end

     return mw.ustring.sub( s, i, j )

end

--[[

This function implements that features of {{str sub old}} and is kept in order

     return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )

end

--[[

match

This function returns a substring from the source string that matches a  

specified pattern.

Usage:

{{#invoke:String|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}

{{#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

         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 or

trailing whitespace from each string.  In some circumstances this is desirable, in  

other cases one may want to preserve the whitespace.

If the match_number or start_index are out of range for the string being queried, then

this 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 and  

an empty string will be returned on any failure.

For information on constructing Lua patterns, a form of [regular expression], see:

]]

function str.match( frame )

     local match_index = math.floor( tonumber(new_args['match']) or 1 );

     local nomatch = new_args['nomatch'];

     if s == '' then

         return str._error( 'Target string is empty' );

         pattern = str._escapePattern( pattern );

     end

     local result

     if match_index == 1 then

             s = mw.ustring.sub( s, start );

         end

         local iterator = mw.ustring.gmatch(s, pattern);

         if match_index > 0 then

                 count = count + 1;

             end

             result = result_table[ count + match_index ];             

         end

     end         

     if result == nil then

         if nomatch == nil then

     end

end

--[[

pos

This 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 return

If invoked using named parameters, Mediawiki will automatically remove any leading or

trailing whitespace from the target string.  In some circumstances this is desirable, in  

other 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 backwards  

from 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.

]]

     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_find

This function duplicates the behavior of {{str_find}}, including all of its quirks.

This is provided in order to support existing templates, but is NOT RECOMMENDED for  

new 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 a

value of "1", which is generally unexpected behavior, and must be accounted for

     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

This function allows one to search for a target string or pattern within another

string.

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

     plain: Boolean flag indicating that target should be understood as plain

         text and not as a Lua style regular expression, defaults to true

If invoked using named parameters, Mediawiki will automatically remove any leading or

trailing whitespace from the parameter.  In some circumstances this is desirable, in  

other cases one may want to preserve the whitespace.

This function returns the first index >= "start" where "target" can be found  

within "source".  Indices are 1-based.  If "target" is not found, then this  

function returns 0.  If either "source" or "target" are missing / empty, this

function also returns 0.

This function should be safe for UTF-8 strings.

]]

     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

This function allows one to replace a target string or pattern within another

string.

Usage:

{{#invoke:String|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}

{{#invoke:String|replace|source=source_string|pattern=pattern_string|replace=replace_string|

   count=replacement_count|plain=plain_flag}}

Parameters

     source: The string to search

     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 );

         result = mw.ustring.gsub( source_str, pattern, replace );

     end         

     return result;

end

--[[  

     simple function to pipe string.rep to templates.

]]

function str.rep( frame )

     local repetitions = tonumber( frame.args[2] )

     return string.rep( frame.args[1] or '', repetitions )

end

--[[

Helper function that populates the argument list given that user may need to use a mix of

     local index = 1;

     local value;

     for i,arg in ipairs( arg_list ) do

         value = frame_args[arg]

         new_args[arg] = value;

     end

     return new_args;

end         

--[[

Helper function to handle error messages.

     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">String Module Error: ' .. 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

--[[

Helper Function to interpret boolean strings

function str._getBoolean( boolean_str )

     local boolean_value;

     if type( boolean_str ) == 'string' then

         boolean_str = boolean_str:lower();

     return boolean_value

end

--[[

Helper function that escapes all pattern characters so that they will be treated  

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

end

return str