https://www.nmnwiki.com/index.php?title=Module:String&feed=atom&action=historyModule:String - Revision history2024-03-29T15:39:05ZRevision history for this page on the wikiMediaWiki 1.34.1https://www.nmnwiki.com/index.php?title=Module:String&diff=142&oldid=prevWebadmin: 1 revision imported2020-05-14T19:16:36Z<p>1 revision imported</p>
<p><b>New page</b></p><div>--[[<br />
<br />
This module is intended to provide access to basic string functions.<br />
<br />
Most of the functions provided here can be invoked with named parameters,<br />
unnamed parameters, or a mixture. If named parameters are used, Mediawiki will<br />
automatically remove any leading or trailing whitespace from the parameter.<br />
Depending on the intended use, it may be advantageous to either preserve or<br />
remove such whitespace.<br />
<br />
Global options<br />
ignore_errors: If set to 'true' or 1, any error condition will result in<br />
an empty string being returned rather than an error message.<br />
<br />
error_category: If an error occurs, specifies the name of a category to<br />
include with the error message. The default category is<br />
[Category:Errors reported by Module String].<br />
<br />
no_category: If set to 'true' or 1, no category will be added if an error<br />
is generated.<br />
<br />
Unit tests for this module are available at Module:String/tests.<br />
]]<br />
<br />
local str = {}<br />
<br />
--[[<br />
len<br />
<br />
This function returns the length of the target string.<br />
<br />
Usage:<br />
{{#invoke:String|len|target_string|}}<br />
OR<br />
{{#invoke:String|len|s=target_string}}<br />
<br />
Parameters<br />
s: The string whose length to report<br />
<br />
If invoked using named parameters, Mediawiki will automatically remove any leading or<br />
trailing whitespace from the target string.<br />
]]<br />
function str.len( frame )<br />
local new_args = str._getParameters( frame.args, {'s'} )<br />
local s = new_args['s'] or ''<br />
return mw.ustring.len( s )<br />
end<br />
<br />
--[[<br />
sub<br />
<br />
This function returns a substring of the target string at specified indices.<br />
<br />
Usage:<br />
{{#invoke:String|sub|target_string|start_index|end_index}}<br />
OR<br />
{{#invoke:String|sub|s=target_string|i=start_index|j=end_index}}<br />
<br />
Parameters<br />
s: The string to return a subset of<br />
i: The fist index of the substring to return, defaults to 1.<br />
j: The last index of the string to return, defaults to the last character.<br />
<br />
The first character of the string is assigned an index of 1. If either i or j<br />
is a negative value, it is interpreted the same as selecting a character by<br />
counting from the end of the string. Hence, a value of -1 is the same as<br />
selecting the last character of the string.<br />
<br />
If the requested indices are out of range for the given string, an error is<br />
reported.<br />
]]<br />
function str.sub( frame )<br />
local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } )<br />
local s = new_args['s'] or ''<br />
local i = tonumber( new_args['i'] ) or 1<br />
local j = tonumber( new_args['j'] ) or -1<br />
<br />
local len = mw.ustring.len( s )<br />
<br />
-- Convert negatives for range checking<br />
if i < 0 then<br />
i = len + i + 1<br />
end<br />
if j < 0 then<br />
j = len + j + 1<br />
end<br />
<br />
if i > len or j > len or i < 1 or j < 1 then<br />
return str._error( 'String subset index out of range' )<br />
end<br />
if j < i then<br />
return str._error( 'String subset indices out of order' )<br />
end<br />
<br />
return mw.ustring.sub( s, i, j )<br />
end<br />
<br />
--[[<br />
This function implements that features of {{str sub old}} and is kept in order<br />
to maintain these older templates.<br />
]]<br />
function str.sublength( frame )<br />
local i = tonumber( frame.args.i ) or 0<br />
local len = tonumber( frame.args.len )<br />
return mw.ustring.sub( frame.args.s, i + 1, len and ( i + len ) )<br />
end<br />
<br />
--[[<br />
match<br />
<br />
This function returns a substring from the source string that matches a<br />
specified pattern.<br />
<br />
Usage:<br />
{{#invoke:String|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}<br />
OR<br />
{{#invoke:String|match|s=source_string|pattern=pattern_string|start=start_index<br />
|match=match_number|plain=plain_flag|nomatch=nomatch_output}}<br />
<br />
Parameters<br />
s: The string to search<br />
pattern: The pattern or string to find within the string<br />
start: The index within the source string to start the search. The first<br />
character of the string has index 1. Defaults to 1.<br />
match: In some cases it may be possible to make multiple matches on a single<br />
string. This specifies which match to return, where the first match is<br />
match= 1. If a negative number is specified then a match is returned<br />
counting from the last match. Hence match = -1 is the same as requesting<br />
the last match. Defaults to 1.<br />
plain: A flag indicating that the pattern should be understood as plain<br />
text. Defaults to false.<br />
nomatch: If no match is found, output the "nomatch" value rather than an error.<br />
<br />
If invoked using named parameters, Mediawiki will automatically remove any leading or<br />
trailing whitespace from each string. In some circumstances this is desirable, in<br />
other cases one may want to preserve the whitespace.<br />
<br />
If the match_number or start_index are out of range for the string being queried, then<br />
this function generates an error. An error is also generated if no match is found.<br />
If one adds the parameter ignore_errors=true, then the error will be suppressed and<br />
an empty string will be returned on any failure.<br />
<br />
For information on constructing Lua patterns, a form of [regular expression], see:<br />
<br />
* http://www.lua.org/manual/5.1/manual.html#5.4.1<br />
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns<br />
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns<br />
<br />
]]<br />
-- This sub-routine is exported for use in other modules<br />
function str._match( s, pattern, start, match_index, plain_flag, nomatch )<br />
if s == '' then<br />
return str._error( 'Target string is empty' )<br />
end<br />
if pattern == '' then<br />
return str._error( 'Pattern string is empty' )<br />
end<br />
start = tonumber(start) or 1<br />
if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then<br />
return str._error( 'Requested start is out of range' )<br />
end<br />
if match_index == 0 then<br />
return str._error( 'Match index is out of range' )<br />
end<br />
if plain_flag then<br />
pattern = str._escapePattern( pattern )<br />
end<br />
<br />
local result<br />
if match_index == 1 then<br />
-- Find first match is simple case<br />
result = mw.ustring.match( s, pattern, start )<br />
else<br />
if start > 1 then<br />
s = mw.ustring.sub( s, start )<br />
end<br />
<br />
local iterator = mw.ustring.gmatch(s, pattern)<br />
if match_index > 0 then<br />
-- Forward search<br />
for w in iterator do<br />
match_index = match_index - 1<br />
if match_index == 0 then<br />
result = w<br />
break<br />
end<br />
end<br />
else<br />
-- Reverse search<br />
local result_table = {}<br />
local count = 1<br />
for w in iterator do<br />
result_table[count] = w<br />
count = count + 1<br />
end<br />
<br />
result = result_table[ count + match_index ]<br />
end<br />
end<br />
<br />
if result == nil then<br />
if nomatch == nil then<br />
return str._error( 'Match not found' )<br />
else<br />
return nomatch<br />
end<br />
else<br />
return result<br />
end<br />
end<br />
-- This is the entry point for #invoke:String|match<br />
function str.match( frame )<br />
local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} )<br />
local s = new_args['s'] or ''<br />
local start = tonumber( new_args['start'] ) or 1<br />
local plain_flag = str._getBoolean( new_args['plain'] or false )<br />
local pattern = new_args['pattern'] or ''<br />
local match_index = math.floor( tonumber(new_args['match']) or 1 )<br />
local nomatch = new_args['nomatch']<br />
<br />
return str._match( s, pattern, start, match_index, plain_flag, nomatch )<br />
end<br />
<br />
--[[<br />
pos<br />
<br />
This function returns a single character from the target string at position pos.<br />
<br />
Usage:<br />
{{#invoke:String|pos|target_string|index_value}}<br />
OR<br />
{{#invoke:String|pos|target=target_string|pos=index_value}}<br />
<br />
Parameters<br />
target: The string to search<br />
pos: The index for the character to return<br />
<br />
If invoked using named parameters, Mediawiki will automatically remove any leading or<br />
trailing whitespace from the target string. In some circumstances this is desirable, in<br />
other cases one may want to preserve the whitespace.<br />
<br />
The first character has an index value of 1.<br />
<br />
If one requests a negative value, this function will select a character by counting backwards<br />
from the end of the string. In other words pos = -1 is the same as asking for the last character.<br />
<br />
A requested value of zero, or a value greater than the length of the string returns an error.<br />
]]<br />
function str.pos( frame )<br />
local new_args = str._getParameters( frame.args, {'target', 'pos'} )<br />
local target_str = new_args['target'] or ''<br />
local pos = tonumber( new_args['pos'] ) or 0<br />
<br />
if pos == 0 or math.abs(pos) > mw.ustring.len( target_str ) then<br />
return str._error( 'String index out of range' )<br />
end<br />
<br />
return mw.ustring.sub( target_str, pos, pos )<br />
end<br />
<br />
--[[<br />
str_find<br />
<br />
This function duplicates the behavior of {{str_find}}, including all of its quirks.<br />
This is provided in order to support existing templates, but is NOT RECOMMENDED for<br />
new code and templates. New code is recommended to use the "find" function instead.<br />
<br />
Returns the first index in "source" that is a match to "target". Indexing is 1-based,<br />
and the function returns -1 if the "target" string is not present in "source".<br />
<br />
Important Note: If the "target" string is empty / missing, this function returns a<br />
value of "1", which is generally unexpected behavior, and must be accounted for<br />
separatetly.<br />
]]<br />
function str.str_find( frame )<br />
local new_args = str._getParameters( frame.args, {'source', 'target'} )<br />
local source_str = new_args['source'] or ''<br />
local target_str = new_args['target'] or ''<br />
<br />
if target_str == '' then<br />
return 1<br />
end<br />
<br />
local start = mw.ustring.find( source_str, target_str, 1, true )<br />
if start == nil then<br />
start = -1<br />
end<br />
<br />
return start<br />
end<br />
<br />
--[[<br />
find<br />
<br />
This function allows one to search for a target string or pattern within another<br />
string.<br />
<br />
Usage:<br />
{{#invoke:String|find|source_str|target_string|start_index|plain_flag}}<br />
OR<br />
{{#invoke:String|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}<br />
<br />
Parameters<br />
source: The string to search<br />
target: The string or pattern to find within source<br />
start: The index within the source string to start the search, defaults to 1<br />
plain: Boolean flag indicating that target should be understood as plain<br />
text and not as a Lua style regular expression, defaults to true<br />
<br />
If invoked using named parameters, Mediawiki will automatically remove any leading or<br />
trailing whitespace from the parameter. In some circumstances this is desirable, in<br />
other cases one may want to preserve the whitespace.<br />
<br />
This function returns the first index >= "start" where "target" can be found<br />
within "source". Indices are 1-based. If "target" is not found, then this<br />
function returns 0. If either "source" or "target" are missing / empty, this<br />
function also returns 0.<br />
<br />
This function should be safe for UTF-8 strings.<br />
]]<br />
function str.find( frame )<br />
local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } )<br />
local source_str = new_args['source'] or ''<br />
local pattern = new_args['target'] or ''<br />
local start_pos = tonumber(new_args['start']) or 1<br />
local plain = new_args['plain'] or true<br />
<br />
if source_str == '' or pattern == '' then<br />
return 0<br />
end<br />
<br />
plain = str._getBoolean( plain )<br />
<br />
local start = mw.ustring.find( source_str, pattern, start_pos, plain )<br />
if start == nil then<br />
start = 0<br />
end<br />
<br />
return start<br />
end<br />
<br />
--[[<br />
replace<br />
<br />
This function allows one to replace a target string or pattern within another<br />
string.<br />
<br />
Usage:<br />
{{#invoke:String|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}<br />
OR<br />
{{#invoke:String|replace|source=source_string|pattern=pattern_string|replace=replace_string|<br />
count=replacement_count|plain=plain_flag}}<br />
<br />
Parameters<br />
source: The string to search<br />
pattern: The string or pattern to find within source<br />
replace: The replacement text<br />
count: The number of occurences to replace, defaults to all.<br />
plain: Boolean flag indicating that pattern should be understood as plain<br />
text and not as a Lua style regular expression, defaults to true<br />
]]<br />
function str.replace( frame )<br />
local new_args = str._getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } )<br />
local source_str = new_args['source'] or ''<br />
local pattern = new_args['pattern'] or ''<br />
local replace = new_args['replace'] or ''<br />
local count = tonumber( new_args['count'] )<br />
local plain = new_args['plain'] or true<br />
<br />
if source_str == '' or pattern == '' then<br />
return source_str<br />
end<br />
plain = str._getBoolean( plain )<br />
<br />
if plain then<br />
pattern = str._escapePattern( pattern )<br />
replace = mw.ustring.gsub( replace, "%%", "%%%%" ) --Only need to escape replacement sequences.<br />
end<br />
<br />
local result<br />
<br />
if count ~= nil then<br />
result = mw.ustring.gsub( source_str, pattern, replace, count )<br />
else<br />
result = mw.ustring.gsub( source_str, pattern, replace )<br />
end<br />
<br />
return result<br />
end<br />
<br />
--[[<br />
simple function to pipe string.rep to templates.<br />
]]<br />
function str.rep( frame )<br />
local repetitions = tonumber( frame.args[2] )<br />
if not repetitions then<br />
return str._error( 'function rep expects a number as second parameter, received "' .. ( frame.args[2] or '' ) .. '"' )<br />
end<br />
return string.rep( frame.args[1] or '', repetitions )<br />
end<br />
<br />
--[[<br />
escapePattern<br />
<br />
This function escapes special characters from a Lua string pattern. See [1]<br />
for details on how patterns work.<br />
<br />
[1] https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns<br />
<br />
Usage:<br />
{{#invoke:String|escapePattern|pattern_string}}<br />
<br />
Parameters<br />
pattern_string: The pattern string to escape.<br />
]]<br />
function str.escapePattern( frame )<br />
local pattern_str = frame.args[1]<br />
if not pattern_str then<br />
return str._error( 'No pattern string specified' )<br />
end<br />
local result = str._escapePattern( pattern_str )<br />
return result<br />
end<br />
<br />
--[[<br />
count<br />
This function counts the number of occurrences of one string in another.<br />
]]<br />
function str.count(frame)<br />
local args = str._getParameters(frame.args, {'source', 'pattern', 'plain'})<br />
local source = args.source or ''<br />
local pattern = args.pattern or ''<br />
local plain = str._getBoolean(args.plain or true)<br />
if plain then<br />
pattern = str._escapePattern(pattern)<br />
end<br />
local _, count = mw.ustring.gsub(source, pattern, '')<br />
return count<br />
end<br />
<br />
--[[<br />
endswith<br />
This function determines whether a string ends with another string.<br />
]]<br />
function str.endswith(frame)<br />
local args = str._getParameters(frame.args, {'source', 'pattern'})<br />
local source = args.source or ''<br />
local pattern = args.pattern or ''<br />
if pattern == '' then<br />
-- All strings end with the empty string.<br />
return "yes"<br />
end<br />
if mw.ustring.sub(source, -mw.ustring.len(pattern), -1) == pattern then<br />
return "yes"<br />
else<br />
return ""<br />
end<br />
end<br />
<br />
--[[<br />
join<br />
<br />
Join all non empty arguments together; the first argument is the separator.<br />
Usage:<br />
{{#invoke:String|join|sep|one|two|three}}<br />
]]<br />
function str.join(frame)<br />
local args = {}<br />
local sep<br />
for _, v in ipairs( frame.args ) do<br />
if sep then<br />
if v ~= '' then<br />
table.insert(args, v)<br />
end<br />
else<br />
sep = v<br />
end<br />
end<br />
return table.concat( args, sep or '' )<br />
end<br />
<br />
--[[<br />
Helper function that populates the argument list given that user may need to use a mix of<br />
named and unnamed parameters. This is relevant because named parameters are not<br />
identical to unnamed parameters due to string trimming, and when dealing with strings<br />
we sometimes want to either preserve or remove that whitespace depending on the application.<br />
]]<br />
function str._getParameters( frame_args, arg_list )<br />
local new_args = {}<br />
local index = 1<br />
local value<br />
<br />
for _, arg in ipairs( arg_list ) do<br />
value = frame_args[arg]<br />
if value == nil then<br />
value = frame_args[index]<br />
index = index + 1<br />
end<br />
new_args[arg] = value<br />
end<br />
<br />
return new_args<br />
end<br />
<br />
--[[<br />
Helper function to handle error messages.<br />
]]<br />
function str._error( error_str )<br />
local frame = mw.getCurrentFrame()<br />
local error_category = frame.args.error_category or 'Errors reported by Module String'<br />
local ignore_errors = frame.args.ignore_errors or false<br />
local no_category = frame.args.no_category or false<br />
<br />
if str._getBoolean(ignore_errors) then<br />
return ''<br />
end<br />
<br />
local error_str = '<strong class="error">String Module Error: ' .. error_str .. '</strong>'<br />
if error_category ~= '' and not str._getBoolean( no_category ) then<br />
error_str = '[[Category:' .. error_category .. ']]' .. error_str<br />
end<br />
<br />
return error_str<br />
end<br />
<br />
--[[<br />
Helper Function to interpret boolean strings<br />
]]<br />
function str._getBoolean( boolean_str )<br />
local boolean_value<br />
<br />
if type( boolean_str ) == 'string' then<br />
boolean_str = boolean_str:lower()<br />
if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0'<br />
or boolean_str == '' then<br />
boolean_value = false<br />
else<br />
boolean_value = true<br />
end<br />
elseif type( boolean_str ) == 'boolean' then<br />
boolean_value = boolean_str<br />
else<br />
error( 'No boolean value found' )<br />
end<br />
return boolean_value<br />
end<br />
<br />
--[[<br />
Helper function that escapes all pattern characters so that they will be treated<br />
as plain text.<br />
]]<br />
function str._escapePattern( pattern_str )<br />
return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" )<br />
end<br />
<br />
return str</div>Webadmin