Wiktionary

Modul:string: Redaktələr arasındakı fərq

Tarixə interaktiv şəkildə baxın
← Əvvəlki redaktəSonrakı redaktə →
Silinən məzmun Əlavə edilmiş məzmun
k Drabdullayev17 moved page Module:String to Module:string without leaving a redirect
Redaktənin izahı yoxdur
Sətir 1:
local str = {}
--[[
 
-- Cannot include null byte.
This module is intended to provide access to basic string functions.
local UTF8_char = "[\1-\127\194-\244][\128-\191]*"
 
--[[
Most of the functions provided here can be invoked with named parameters,
ulen
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.
 
Counts UTF-8 characters. Faster than mw.ustring.len.
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.
]]
 
Assumes that the encoding is correct. Unlike mw.ustring.len, does not return nil
local str = {}
if encoding is invalid.
 
Does not count the bytes 192, 193, and 245-255. They are not used in UTF-8 and
will not occur if the string is valid. They are replaced with the replacement
character (U+FFFD) on MediaWiki pages.
--]]
function str.ulen(text)
local _, length = string.gsub(text, UTF8_char, "")
return length
end
 
--[[
Sətir 31 ⟶ 27:
 
Usage:
{{#invoke:Stringstring|len|target_string|}}
OR
{{#invoke:Stringstring|len|s=target_string}}
 
Parameters
Sətir 39 ⟶ 35:
 
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 s = new_args['s'] or '';
return mw.ustring.len( s )
end
 
Sətir 53 ⟶ 49:
 
Usage:
{{#invoke:Stringstring|sub|target_string|start_index|end_index}}
OR
{{#invoke:Stringstring|sub|s=target_string|i=start_index|j=end_index}}
 
Parameters
Sətir 63 ⟶ 59:
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 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( 'SətiraltıString indeksininsubset mənasıindex icazəout verilənof sərhədlərdən kənara çıxırrange' );
end
if j < i then
return str._error( 'SətiraltıString indekslərininsubset yanlışindices düzülüşüout of order' );
end
return mw.ustring.sub( s, i, j )
end
 
Sətir 100 ⟶ 96:
to maintain these older templates.
]]
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
 
Sətir 109 ⟶ 105:
match
 
This function returns a substring from the source string that matches a
specified pattern.
 
Usage:
{{#invoke:Stringstring|match|source_string|pattern_string|start_index|match_number|plain_flag|nomatch_output}}
OR
{{#invoke:Stringstring|pos|s=source_string|pattern=pattern_string|start=start_index
|match=match_number|plain=plain_flag|nomatch=nomatch_output}}
 
Sətir 123 ⟶ 119:
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.
Sətir 133 ⟶ 129:
 
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.
 
Sətir 148 ⟶ 144:
 
]]
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( 'BoşTarget axtarışstring xanasıis empty' );
end
if pattern == '' then
return str._error( 'BoşPattern axtarışstring şablonuis empty' );
end
if math.abs(start) < 1 or math.abs(start) > mw.ustring.len( s ) then
return str._error( 'AxtarışınRequested başlanğıcstart indeksiis icazəout verilənof sərhədlərdən kənara çıxırrange' );
end
if match_index == 0 then
return str._error( 'UyğunluqMatch indeksiindex icazəis verilənout sərhədlərdənof kənara çıxırrange' );
end
if plain_flag then
pattern = str._escapePatternpattern_escape( 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
end
end
else
-- Reverse search
local result_table = {};
local count = 1;
for w in iterator do
result_table[count] = w;
count = count + 1;
end
end
result = result_table[ count + match_index ];
end
end
end
if result == nil then
if nomatch == nil then
return str._error( 'UyğunluqMatch müəyyənnot edilməmişdirfound' );
else
return nomatch;
end
else
return result;
end
end
 
Sətir 222 ⟶ 218:
 
Usage:
{{#invoke:Stringstring|pos|target_string|index_value}}
OR
{{#invoke:Stringstring|pos|target=target_string|pos=index_value}}
 
Parameters
Sətir 231 ⟶ 227:
 
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.
]]
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( 'SətirinString indeksininindex mənasıout icazəof verilən sərhədlərdən kənara çıxırrange' );
end
return mw.ustring.sub( target_str, pos, pos );
end
 
Sətir 257 ⟶ 253:
 
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.
 
Sətir 267 ⟶ 263:
separatetly.
]]
function str.str_find( frame )
local new_args = str._getParameters( frame.args, { 'source', 'target'} });
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
 
Sətir 291 ⟶ 287:
 
Usage:
{{#invoke:Stringstring|find|source_str|target_string|start_index|plain_flag}}
OR
{{#invoke:Stringstring|find|source=source_str|target=target_str|start=start_index|plain=plain_flag}}
 
Parameters
Sətir 303 ⟶ 299:
 
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 0an empty string. If either "source" or "target" are missing / empty, this
function also returns 0an empty string.
 
This function should be safe for UTF-8 strings.
]]
function str.find( frame )
local params = {
local new_args = str._getParameters( frame.args, {'source', 'target', 'start', 'plain' } );
[1] = { required = true },
local source_str = new_args['source'] or '';
[2] = { required = true },
local pattern = new_args['target'] or '';
[3] = { type = "number" },
local start_pos = tonumber(new_args['start']) or 1;
[4] = { type = "boolean" },
local plain = new_args['plain'] or true;
}
if source_str == '' or pattern == '' then
local args = require("Module:parameters").process(frame.args, params)
return 0;
end
return mw.ustring.find(args[1], args[2], args[3], args[4])
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
 
Sətir 341 ⟶ 329:
 
Usage:
{{#invoke:Stringstring|replace|source_str|pattern_string|replace_string|replacement_count|plain_flag}}
OR
{{#invoke:Stringstring|replace|source=source_string|pattern=pattern_string|replace=replace_string|
count=replacement_count|plain=plain_flag}}
 
Sətir 352 ⟶ 340:
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
 
--[[
This function adds support for escaping parts of the patterns when using [plain=false].
]]
function str.escapereplace( 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.pattern_escape(pattern);
replace = mw.ustring.gsub(replace, "%%", "%%%%"); --Only need to escape replacement sequences.
end
local result;
result = mw.ustring.gsub(source_str, pattern, replace, count);
local result = '';
result = str._escapePattern( pattern );
return result;
end
 
 
--[[
function str.gsub(frame)
Internal compare string function
local params = {
]]
[1] = { required = true, allow_empty = true, allow_whitespace = true},
function str._strcmp(a , b)
[2] = { required = true, allow_empty = true, allow_whitespace = true},
local s1c = mw.ustring.gcodepoint( a );
[3] = { required = true, allow_empty = true, allow_whitespace = true},
local s2c = mw.ustring.gcodepoint( b );
[4] = { type = "number" },
while true do
}
local c1 = s1c();
local c2 = s2c();
local args = require("Module:parameters").process(frame.args, params)
if c1 == nil then
if c2 == nil then
return (mw.ustring.gsub(args[1], args[2], args[3], args[4]))
return 0
else
return -1
end
else
if c2 ~= nil then
if c1 ~= c2 then
return c1 < c2 and -1 or 1
end
else
return 1
end
end
end
return 0
end
--[[
compare
 
This function compare two UTF-8 strings
 
--[[
Usage:
simple function to pipe string.rep to templates.
{{#invoke:String|compare|str1|str2}}
]]
 
function str.rep(frame)
Returns:
local repetitions = tonumber(frame.args[2])
0 - if strings are equal
1 - if st1not >repetitions str2then
return str._error('function rep expects a number as second parameter, received "' .. (frame.args[2] or '') .. '"')
-1 - if str1 < str2
end
]]
return string.rep(frame.args[1] or '', repetitions)
function str.compare(frame)
local str1 = frame.args[1] or '';
local str2 = frame.args[2] or '';
return str._strcmp(str1 , str2)
end
 
function str.lower(frame)
--[[
local text = frame.args[1] or ''
simple function to pipe string.rep to templates.
return mw.ustring.lower(text)
]]
function str.rep( frame )
local repetitions = tonumber( frame.args[2] )
if not repetitions then
return str._error( 'ger funksiyası ikinci parametrdə rəqəm gözləyir, amma alınıb "' .. ( frame.args[2] or '' ) .. '"' )
end
return string.rep( frame.args[1] or '', repetitions )
end
 
str.lc = str.lower
 
--[[
Sətir 459 ⟶ 407:
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 'StringErrors modulununreported xətaby verdiyiModule səhifələrString';
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 modulununModule xətasıError: ' .. error_str .. '</strong>';
if error_category ~= '' and not str._getBoolean( no_category ) then
error_str = '[[KateqoriyaCategory:' .. error_category .. ']]' .. error_str;
end
end
return error_str;
end
 
Sətir 500 ⟶ 448:
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
end
elseif type( boolean_str ) == 'boolean' then
boolean_value = boolean_str;
else
error( 'MəntiqiNo mənasıboolean tapılmayıbvalue found' );
end
return boolean_value
end
 
--[[
Helper function that escapes all pattern characters – ().%+-*?[^$] – so that they will be treated
as plain text.
]]
function str._escapePatternpattern_escape( pattern_str )
local invoked = false
return mw.ustring.gsub( pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1" );
if type(pattern_str) == "table" then
if pattern_str.args then
local frame = pattern_str
invoked = true
if frame.args[1] then
pattern_str = frame.args[1]
else
pattern_str = frame:getParent().args[1]
end
else
error("First argument to pattern_escape should be a string, a number, or a frame object.")
end
elseif not (type(pattern_str) == "string" or type(pattern_str) == "number") then
error("First argument to pattern_escape should be a string or a number.")
end
if invoked then
local escaped = mw.ustring.gsub(pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1")
return escaped
else
return mw.ustring.gsub(pattern_str, "([%(%)%.%%%+%-%*%?%[%^%$%]])", "%%%1");
end
end
 
function str.count(text, pattern, plain)
if not (type(text) == "string" or type(text) == "number") then
error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.')
end
if not (type(pattern) == "string" or type(pattern) == "number") then
error('The first argument to the function "count" must be a string or a number, not a ' .. type(text) .. '.')
end
if plain then
pattern = str.pattern_escape(pattern)
end
local _, count = mw.ustring.gsub(text, pattern, "")
return count
end
 
function str.plain_gsub(text, pattern, replacement)
local invoked = false
if type(text) == "table" then
invoked = true
if text.args then
local frame = text
local params = {
[1] = {},
[2] = {},
[3] = { allow_empty = true },
}
local args = require("Module:parameters").process(frame.args, params)
text = args[1]
pattern = args[2]
replacement = args[3]
else
error("If the first argument to plain_gsub is a table, it should be a frame object.")
end
else
if not (type(pattern) == "string" or type(pattern) == "number") then
error("The second argument to plain_gsub should be a string or a number.")
end
if not (type(replacement) == "string" or type(replacement) == "number") then
error("The third argument to plain_gsub should be a string or a number.")
end
end
pattern = str.pattern_escape(pattern)
if invoked then
text = mw.ustring.gsub(text, pattern, replacement)
return text
else
return mw.ustring.gsub(text, pattern, replacement)
end
end
 
function str.matchToArray(text, pattern)
local invoked = false
if type(text) == "table" then
invoked = true
if text.args then
local frame = text
local params = {
[1] = { required = true },
[2] = { required = true },
}
local args = require("Module:parameters").process(frame.args, params)
text = args[1]
pattern = args[2]
else
error("If the first argument to matchToArray is a table, it should be a frame object.")
end
else
if not (type(pattern) == "string" or type(pattern) == "number") then
error("The second argument to matchToArray should be a string or a number.")
end
end
local matches = {}
local i = 0
for match in mw.ustring.gmatch(text, pattern) do
i = i + 1
matches[i] = match
end
if i > 0 then
if invoked then
return table.concat(matches, ", ")
else
return matches
end
else
if invoked then
return ""
else
return nil
end
end
end
 
--[=[
Similar to gmatch, but it returns the count of the match in addition to the
list of captures, something like ipairs().
If the pattern doesn't contain any captures, the whole match is returned.
Invoke thus:
for i, whole_match in require("Module:string").imatch(text, pattern) do
[ do something with i and whole_match ]
end
or
for i, capture1[, capture2[, capture3[, ...]]] in require("Module:string").imatch(text, pattern) do
[ do something with i and capture1 ]
end
For example, this code
for i, whole_match in require("Module:string").imatch("a b c", "[a-z]") do
mw.log(i, whole_match)
end
will log
1 a
2 b
3 c
]=]
function str.imatch(text, pattern, pos, plain, use_basic_Lua_function)
local i = 0
pos = pos or 0
if not string.find(pattern, "%b()") then
pattern = "(" .. pattern .. ")"
end
local find = use_basic_Lua_function and string.find or mw.ustring.find
return function()
i = i + 1
local return_values = { find(text, pattern, pos, plain) }
local j = return_values[2]
if return_values[3] then
pos = j + 1
-- Skip the first two returned values, which are the indices of the
-- whole match.
return i, unpack(return_values, 3)
end
end
end
 
function str.escapebytes(s)
return (string.gsub(s,
'.',
function(char)
return ('\\%03d'):format(string.byte(char))
end))
end
 
function str.URIdecode(frame)
return mw.uri.decode(frame.args[1], frame.args[2] or "PATH")
end
 
Mənbə — "https://az.wiktionary.org/wiki/Modul:string"