Module:String: Difference between revisions

Line 1:

--[[

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.

]]

Line 39:

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

trailing whitespace from the target string.

]]

function str.len( frame )

local new_args = str._getParameters( frame.args, {'s'} )

local new_args = str._getParameters( frame.args, {'s'} );

local s = new_args['s'] or ''

local s = new_args['s'] or '';

return mw.ustring.len( s )

end

Line 61:

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.

]]

function str.sub( frame )

local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } )

local new_args = str._getParameters( frame.args, { 's', 'i', 'j' } );

local s = new_args['s'] or ''

local s = new_args['s'] or '';

local i = tonumber( new_args['i'] ) or 1

local i = tonumber( new_args['i'] ) or 1;

local j = tonumber( new_args['j'] ) or -1

local j = tonumber( new_args['j'] ) or -1;

local len = mw.ustring.len( s )

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( 'String subset index out of range' )

end

if j < i then

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

end

-- Convert negatives for range checking

return mw.ustring.sub( s, i, j )

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

Line 101:

]]

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

Line 109:

match

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

specified pattern.

Line 115:

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

OR

{{#invoke:String|~~match~~|s=source_string|pattern=pattern_string|start=start_index

{{#invoke:String|pos|s=source_string|pattern=pattern_string|start=start_index

|match=match_number|plain=plain_flag|nomatch=nomatch_output}}

Line 123:

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.

Line 133:

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.

Line 148:

]]

-- This sub-routine is exported for use in other modules

function str._match( s, pattern, start, match_index, plain_flag, nomatch )

if s == '' then

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

end

if pattern == '' then

return str._error( 'Pattern string is empty' )

end

start = tonumber(start) or 1

if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then

return str._error( 'Requested start is out of range' )

end

if match_index == 0 then

return str._error( 'Match index is out of range' )

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

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

if result == nil then

if nomatch == nil then

return str._error( 'Match not found' )

else

return nomatch

end

else

return result

end

-- This is the entry point for #invoke:String|match

function str.match( frame )

local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} )

local new_args = str._getParameters( frame.args, {'s', 'pattern', 'start', 'match', 'plain', 'nomatch'} );

local s = new_args['s'] or ''

local s = new_args['s'] or '';

local start = tonumber( new_args['start'] ) or 1

local start = tonumber( new_args['start'] ) or 1;

local plain_flag = str._getBoolean( new_args['plain'] or false )

local plain_flag = str._getBoolean( new_args['plain'] or false );

local pattern = new_args['pattern'] or ''

local pattern = new_args['pattern'] or '';

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

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

local nomatch = new_args['nomatch']

local nomatch = new_args['nomatch'];

if s == '' then

return str._match( s, pattern, start, match_index, plain_flag, nomatch )

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

-- 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

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

if result == nil then

if nomatch == nil then

return str._error( '找不到匹配' );

else

return nomatch;

end

else

return result;

end

Line 237:

Line 231:

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.

Line 248:

Line 242:

]]

function str.pos( frame )

local new_args = str._getParameters( frame.args, {'target', 'pos'} )

local new_args = str._getParameters( frame.args, {'target', 'pos'} );

local target_str = new_args['target'] or ''

local target_str = new_args['target'] or '';

local pos = tonumber( new_args['pos'] ) or 0

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~~ )

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

Line 263:

Line 257:

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.

Line 274:

Line 268:

]]

function str.str_find( frame )

local new_args = str._getParameters( frame.args, {'source', 'target'} )

local new_args = str._getParameters( frame.args, {'source', 'target'} );

local source_str = new_args['source'] or ''

local source_str = new_args['source'] or '';

local target_str = new_args['target'] or ''

local target_str = new_args['target'] or '';

if target_str == '' then

return 1

return 1;

end

local start = mw.ustring.find( source_str, target_str, 1, true )

if start == nil then

start = -1

end

return start

end

Line 309:

Line 303:

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.

Line 320:

Line 314:

]]

function str.find( frame )

local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } )

local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } );

local source_str = new_args['source'] or ''

local source_str = new_args['source'] or '';

local pattern = new_args['target'] or ''

local pattern = new_args['target'] or '';

local start_pos = tonumber(new_args['start']) or 1

local start_pos = tonumber(new_args['start']) or 1;

local plain = new_args['plain'] or true

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 source_str == '' or pattern == '' then

if start == nil then

return 0

start = 0

end

plain = str._getBoolean( plain )

return start

local start = mw.ustring.find( source_str, pattern, start_pos, plain )

if start == nil then

start = 0

end

return start

end

Line 358:

Line 352:

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 new_args = str._getParameters( frame.args, {'source', 'pattern', 'replace', 'count', 'plain' } );

local source_str = new_args['source'] or ''

local source_str = new_args['source'] or '';

local pattern = new_args['pattern'] or ''

local pattern = new_args['pattern'] or '';

local replace = new_args['replace'] or ''

local replace = new_args['replace'] or '';

local count = tonumber( new_args['count'] )

local count = tonumber( new_args['count'] );

local plain = new_args['plain'] or true

local plain = new_args['plain'] or true;

if source_str == '' or pattern == '' then

return source_str;

end

plain = str._getBoolean( plain );

if ~~source_str~~ == '' ~~or pattern ==~~ '' then

if plain then

pattern = str._escapePattern( pattern );

return source_str

replace = mw.ustring.gsub( replace, "%%", "%%%%" ); --Only need to escape replacement sequences.

end

plain = str._getBoolean( plain )

local result;

if ~~plain~~ then

if count ~= nil then

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

pattern = str._escapePattern( pattern )

else

replace = mw.ustring.gsub( replace, "%%", "%%%%" ) --Only need to escape replacement sequences.

result = mw.ustring.gsub( source_str, pattern, 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

return result;

end

--[[

simple function to pipe string.rep to templates.

]]

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

--[[

escapePattern

function str.split(inputstr, sep, no_pattern, ignore_null)

This function escapes special characters from a Lua string pattern. See [1]

--#invoke 支援

for details on how patterns work.

if type(inputstr) == type({table}) then

if not getArgs then getArgs = require('Module:Arguments').getArgs end

[1] https://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns

args = getArgs(inputstr, {parentFirst=true})

for arg_name, arg_value in pairs( args ) do

Usage:

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

Parameters

separ = arg_value

pattern_string: The pattern string to escape.

elseif arg_name == 3 or arg_name == '3' or arg_name == "no_pattern" or arg_name == "no pattern" then

]]

no_pattern_flag = arg_value

function str.escapePattern( frame )

elseif arg_name == 4 or arg_name == '4' or arg_name == "ignore_null" or arg_name == "ignore null" then

local pattern_str = frame.args[1]

ignore_null_flag = arg_value

if not pattern_str then

elseif arg_name == 5 or arg_name == '5' or arg_name == "format" then

return str._error( 'No pattern string specified' )

format = arg_value or "*{{{1}}}\n";

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 ''

local result = str._escapePattern( pattern_str )

separ = separ or "%s"

return result

if no_pattern_flag == nil then no_pattern_flag = true end

end

if ignore_null_flag == nil then ignore_null_flag = false end

length = mw.ustring.len(input_str)

--[[

--split函數起點

count

if no_pattern_flag then

This function counts the number of occurrences of one string in another.

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,

]]

"%[", "%["), "%]", "%]"), "%{", "%{"), "%}", "%}"), "%%", "%%%%"), "%)", "%)"), "%-", "%-"),

function str.count(frame)

"%^", "%^"), "%$", "%$"), "%(", "%("), "%.", "%."), "%*", "%*"), "%+", "%+"), "%|", "%|");

local args = str._getParameters(frame.args, {'source', 'pattern', 'plain'})

local source = args.source or ''

local pattern = args.pattern or ''

local plain = str._getBoolean(args.plain or true)

if plain then

pattern = str._escapePattern(pattern)

end

iterator = 1 ; i = 1 ; flag = true

local _, count = mw.ustring.gsub(source, pattern, '')

result = {}

return count

separ_str_begin, separ_str_end = mw.ustring.find(input_str, separ, iterator)

end

--

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)

endswith

This function determines whether a string ends with another string.

]]

function str.endswith(frame)

local args = str._getParameters(frame.args, {'source', 'pattern'})

local source = args.source or ''

local pattern = args.pattern or ''

if pattern == '' then

-- All strings end with the empty string.

return "yes"

end

if is_invoke then

if mw.ustring.sub(source, -mw.ustring.len(pattern), -1) == pattern then

~~return~~ ~~"yes"~~

body = ''

for i, result_str in pairs( result ) do

else

body = body .. mw.ustring.gsub(format, "%%s", result_str)

return ""

end

return body

end

return result;

end

Line 487:

Line 503:

]]

function str._getParameters( frame_args, arg_list )

local new_args = {}

local new_args = {};

local index = 1

local index = 1;

local value

local value;

for _, arg in ipairs( arg_list ) do

for i,arg in ipairs( arg_list ) do

value = frame_args[arg]

if value == nil then

value = frame_args[index]

value = frame_args[index];

index = index + 1

index = index + 1;

end

new_args[arg] = value

new_args[arg] = value;

end

return new_args

return new_args;

end

--[[

Line 507:

Line 523:

]]

function str._error( error_str )

local frame = mw.getCurrentFrame()

local frame = mw.getCurrentFrame();

local error_category = frame.args.error_category or '~~Errors reported by Module String~~'

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 ignore_errors = frame.args.ignore_errors or false;

local no_category = frame.args.no_category or false

local no_category = frame.args.no_category or false;

if str._getBoolean(ignore_errors) then

return ''

return '';

end

local error_str = '<strong class="error">~~String Module Error:~~ ' .. error_str .. '</strong>'

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

error_str = '[[Category:' .. error_category .. ']]' .. error_str;

end

return error_str

return error_str;

end

Line 528:

Line 544:

]]

function str._getBoolean( boolean_str )

local boolean_value

local boolean_value;

if type( boolean_str ) == 'string' then

boolean_str = boolean_str:lower()

boolean_str = boolean_str:lower();

if boolean_str == 'false' or boolean_str == 'no' or boolean_str == '0'

or boolean_str == '' then

boolean_value = false

boolean_value = false;

else

boolean_value = true

boolean_value = true;

end

elseif type( boolean_str ) == 'boolean' then

boolean_value = boolean_str

boolean_value = boolean_str;

else

error( '布尔值找不到' );

error( 'No boolean value found' )

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" )

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

end