Modul:string
Dette modul giver grundlæggende funktioner for behandlinger på tekststrenge.
Forklaring på udvalgte elementer.
pos
Giver bogstaven af strengen som findes ved den angivne position.
{{#invoke:string|pos|streng|index}}{{#invoke:string|pos|target=streng|pos=index}}
Parametre:
target: den streng man søger påpos: índeks på det bogstav man søger
Det første bogstav af strengen har indeks-værdien 1. Sidste bogstav i strengen kan findes ved indeks-værdien -1, talt fra enden af. Hvis tallet overstiger antallet af elementer i strengen, gives en fejl tilbage.
Se også Modul:String, som udfører nogle af de samme funktionaliteter.
--[[
This module is intended to provide access to basic string functions.
]]
local str = {}
--[[
len
Parameters
s: The string whose length to report
]]
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
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.
]]
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( 'Índex fora del rang de la cadena' );
end
if j < i then
return str._error( 'Índexs de la cadena no ordenats' );
end
return mw.ustring.sub( s, i, j )
end
--[[
match
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.
]]
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( 'Cadena on cercar està buida' );
end
if pattern == '' then
return str._error( 'Cadena de cerca està buida' );
end
if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then
return str._error( 'Índex d\'inici fora del rang de la cadena' );
end
if match_index == 0 then
return str._error( 'Número de coincidència fora de rang' );
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( 'Cap coincidència trobada' );
else
return nomatch;
end
else
return result;
end
end
--[[
pos
Parameters
target: The string to search
pos: The index for the character to return
]]
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( 'Índex fora del rang de la cadena' );
end
return mw.ustring.sub( target_str, pos, pos );
end
--[[
find
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 true
]]
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
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 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 result;
end
--Sørger for, at det første bogstav i en streng er stort.
function str.initUpper( frame )
local new_args = str._getParameters( frame.args, {'s'} )
local s = new_args['s'] or ''
return (s:gsub("^%l", string.upper))
end
--[[
Helper function that populates the argument list given that user may need to use a mix of
named and unnamed parameters. This is relevant because named parameters are not
identical to unnamed parameters due to string trimming, and when dealing with strings
we 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 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
--[[
Helper function to handle error messages.
]]
function str._error( error_str )
local frame = mw.getCurrentFrame();
local error_category = frame.args.error_category or 'Errors detectats pel mòdul 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 = '<strong class="error">Error del mòdul String: ' .. error_str .. '</strong>';
if error_category ~= '' and not str._getBoolean( no_category ) then
error_str = '[[Categoria:' .. 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();
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( 'Cap valor booleà trobat' );
end
return boolean_value
end
--[[
Helper function that escapes all pattern characters so that they will be treated
as plain text.
]]
function str._escapePattern( pattern_str )
return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );
end
return str