पटलम्:String
"इस मॉड्यूल हेतु प्रलेख पटलम्:String/doc पर बनाया जा सकता है"
--[[
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.
]]
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.
]]
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
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.
]]
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( 'String subset index out of range' );
end
if j < i then
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
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
--[[
escapePattern
This function escapes literal characters that must not adopt their special
role given in Lua patterns (as used by match, gsub, find or replace), and
returns a pattern matching only the specified source string.
Usage:
{{#invoke:String|escape|source_string}}
OR
{{#invoke:String|escape|s=source_string}}
For information on constructing Lua patterns, a form of [regular expression], see:
* http://www.lua.org/manual/5.1/manual.html#5.4.1
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns
]]
function str.escape( frame )
local new_args = str._getParameters( frame.args, { 's' } );
local s = new_args['s'] or '';
return str._escapePattern( s );
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}}
OR
{{#invoke:String|pos|s=source_string|pattern=pattern_string|start=start_index
|match=match_number|plain=plain_flag|nomatch=nomatch_output}}
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.
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:
* http://www.lua.org/manual/5.1/manual.html#5.4.1
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Patterns
* http://www.mediawiki.org/wiki/Extension:Scribunto/Lua_reference_manual#Ustring_patterns
]]
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( 'Target string is empty' );
end
if pattern == '' then
return str._error( 'Pattern string is empty' );
end
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
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( 'Match not found' );
else
return nomatch;
end
else
return result;
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.
]]
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( '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
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
--[[
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
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
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.
]]
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
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}}
OR
{{#invoke:String|replace|source=source_string|pattern=pattern_string|replace=replace_string|
count=replacement_count|plain=plain_flag}}
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
--[[
simpletitle
This function returns the current page title without the homonymy part (the part in parenthesis).
Usage:
{{#invoke:String|simpletitle}}
OR
{{#invoke:String|simpletitle|string}}
Parameters
string: if present this function will treat this string as the title of the page and remove
homonymy part if present in it. If not given the function uses the page title (without namespace)
]]
function str.simpletitle(frame)
-- si un paramètre est indiqué, on l'utilise comme titre à traiter
local page = frame.args[1]
if (page == nil or page == "") then
-- on récupère le title
local titre = mw.title.getCurrentTitle()
if (titre == nil) then return "" end
-- le nom de la page
page = titre.text
if (page == nil or type(page) ~= "string" or page == "") then return "" end
end -- sinon "page" vaut déjà la chaîne à traiter
-- on enlève la partie entre parenthèses
local npage = mw.ustring.gsub(page, " [(][^()]*[)]$", "")
if (npage == nil or npage == "") then return "" end
return npage
end
--[[
uncaesure
This function filters and returns the provided text, by removing from
the end of each line a single dash/hyphen (or other supplied separator) and
the following spaces.
Usage:
{{#invoke:String|uncaesure|text|separator}}
OR
{{#invoke:String|uncaesure|text = text|separator = separator}}
Parameters
text: the string from which caesura should be removed
separator: the string used as ceasure mark (such as '-')
]]
function str.uncaesure( frame )
local new_args = str._getParameters( frame.args, { 'text', 'separator' } );
local text = new_args['text'] or '';
local separator = new_args['separator'] or '';
local unceasured = text:gsub(
str._escapePattern(separator == '' and '-' or separator)
.. '[ \t\v\f]*\r?\n', -- end of caesured line
'')
return unceasured
end
--[[
titledisambig
This function returns the part of the title used for disambiguation,
including the parenthesis themselves and the space just before.
Usage:
{{#invoke:String|titledisambig}}
OR
{{#invoke:String|titledisambig|string}}
Parameters
string: if present this function will treat this string as the title of the page.
If not given the function uses the page title.
]]
function str.titledisambig(frame)
-- si un paramètre est indiqué, on l'utilise comme titre à traiter
local page = frame.args[1]
if (page == nil or page == "") then
-- on récupère le title
local titre = mw.title.getCurrentTitle()
if (titre == nil) then return "" end
-- le nom de la page
page = titre.text
if (page == nil or type(page) ~= "string" or page == "") then return "" end
end -- sinon "page" vaut déjà la chaîne à traiter
-- on enlève la partie entre parenthèses
local disambigStart = string.find(page, " %(")
if disambigStart then
return string.sub(page, disambigStart)
else
return ""
end
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 reported by Module 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">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.
]]
str._knownBooleans = {
--[[ Strings, lowercase, and not numbers, ordered alphabetically. Valid in
these languages: be, bg, br, bs, ca, co, cs, cy, da, de, el, en, eo, es, et,
eu, fi, fr, fy, ga, gd, gl, ha, haw, hmn, hr, hu, hy, id, ig, is, it, ja,
jv, ka, kk, ku, ky, la, lb, lt, lv, mg, mi, mk, mn, mt, nb, nl, nn, no, pl,
pt, ro, ru, sk, sl, sm, sn, sr, st, su, sv, sw, tg, tl, tr, uk, uz, xh, yo,
zu, zh-hans, zh-hant.
Map ambiguous abbreviations as a string to a longer word (also mapped).
Map other strings only to false or true.
--]]
a = 'allowed', --possibly ambiguous:
["a'a"] = false, aa = false,
accept = true, accepte = true, ['accepté'] = true, accepted = true,
accepter = true, accord = true, accorde = true, ['accordé'] = true,
accorder = true, acquiesce = true, ['acquiescé'] = true,
acquiescer = true, actif = true, activate = true, activated = true,
active = true, ['activé'] = true, activer = true, ae = true,
agree = true, agree = true, ['agréé'] = true, agreed = true,
aihwa = false,
['all right'] = true, allright = true, allow = true, allowed = true,
always = true, alright = true, ano = true, ['áno'] = true,
ao = false, aole = false, ['aʻole'] = false,
approuve = true, ['approuvé'] = true, approuver = true, approve = true,
approved = true, authorise = true, ['authorisé'] = true,
authoriser = true, authorize = true, authorized = true,
b = 'bon',
bai = true, bene = true, beeni = true, ['bẹẹni'] = true, bien = true,
['bien sur'] = true, ['bien sûr'] = true, bom = true, bon = true,
bra = true, bueno = true, buono = true,
c = 'correct', --possibly ambiguous:
correct = true,
cha = false, chan = false, ['chan eil'] = false, che = false,
d = 'disallowed', --possibly ambiguous:
da = true, ["d'accord"] = true, daccord = true,
desactive = false, ['désactive'] = false, ['désactivé'] = false,
disable = false, disabled = false, disallow = false,
disallowed = false, doch = true,
e--[[st: Sesotho unabbreviated, no alternate]] = true, --possibly ambiguous:
ec = true, ee = true, eh = true, ehe = true,
ei = false,
enable = true, enabled = true, eny = true, enya = true,
ere = false, ['erê'] = false,
est = true, etiam = true, evet = true, ewe = true,
ez = false,
f = 'false', -- possibly ambiguous:
['false'] = false, falsh = false, faux = false,
fine = true,
forbid = false, forbidden = false,
g = 'good',
goed = true, good = true, gut = true,
h = 'ha', -- possibly ambiguous:
ha = true, haa = true,
hapana = false, hindi = false, hayi = false, hayir = false,
['hayır'] = false,
hoc = true, hoch = true,
i = 'inactive', -- possibly ambiguous:
ie = true, ['iè'] = true, igen--[[hu]] = true, immer = true,
impossible = false, inactif = false, inactive = false,
indeed = true,
ingen--[[sv]] = false, invalid = false, invalide = false,
ioe = true, iva = true, iya = true, ['iya nih'] = true,
j = 'ja', -- possibly ambiguous:
ja = true, ['já'] = true, ['jā'] = true, jah = true,
jamais = false,
jes = true,
jo--[[sq: Albanian, no alternate]] = false,
-- jo--[[sv: alternate Swedish, prefered: 'ja']] = true,
joo = true,
k = 'k.o.',
kahore = false, khong = false, ['không'] = false,
['k.o.'] = false, ko = false, kore = false, kwete = false,
l = 'leai', -- possibly ambiguous:
le = false, leai--[[sm]] = false,
legal = true, ['légal'] = true, legit = true, legitime = true,
['légitime'] = true,
m = 'mba', -- possibly ambiguous:
maya = false, mba = false,
mire = true, ['mirë'] = true,
n = 'non', -- possibly ambiguous:
na = false, nan = false, nann = false, nao = false, ['não'] = false,
nay = false,
ndiyo = true,
ne = false, ['nē'] = false, nee = false, nei = false, nein = false,
nej = false, nem = false, nenni = false, never = false,
nicht = false, nihil = false, nincs = false, nie = false,
['nié'] = false, nier = false, niet = false, no = false, non = false,
none = false, nu = false, nuk = false,
o = 'oui', -- possibly ambiguous:
oc = true, ['òc'] = true, oil = true, ['oïl'] = true, ['o.k.'] = true,
ok = true, okay = true, ['oké'] = true, okey = true, oo = true,
ou = true, ouais = true, ['ouè'] = true, oui = true,
ora = false,
p = 'permis', -- possibly ambiguous:
pas = false,
permettre = true, permis = true, permit = true, permitted = true,
po = true, possible = true,
r = 'right', -- possibly ambiguous:
ready = true, recht = true,
refus = false, refuse = false, ['refusé'] = false,
reject = false, rejected = false, rejet = false, ['rejeté'] = false,
rejeter = false,
right = true,
s = 'si',
semper = true, si = true, ['sì'] = true, ['sí'] = true, sim = true,
sur = true, ['sûr'] = true, sure = true, surely = true,
surement = true,
t = 'true', -- possibly ambiguous:
ta = true, ['tá'] = true, taip = true, tak = true,
teu = false,
tha = true,
tidak = false,
toujours = true, ['true'] = true,
tsia = false, ['tsis muaj'] = false, ['tsy misy'] = false,
v = 'vrai',
valid = true, valide = true, vang = true, ['vâng'] = true,
vrai = true,
y = 'yes', -- possibly ambiguous:
ya = true, yah = true, ye = true, yea = true, yeah = true, yebo = true,
yep = true, yes = true, yog = true, yup = true, yus = true,
['yok hayır'] = false, yoq = false, ["yo'q"] = false,
-- Greek
['ν'] = 'ναι',
['ναι'] = true, ['ναί'] = true,
['ο'] = 'όχι',
['ουχι'] = false, ['ουχί'] = false, ['οχι'] = false, ['όχι'] = false,
-- Cyrillic
['б'] = 'бале',
['бале'] = true,
['д'] = 'да',
['да'] = true,
['и'] = 'иә',
['иә'] = true,
['н'] = 'нет',
['не'] = false, ['нет'] = false, ['ні'] = false,
['о'] = 'ооба',
['ооба'] = true,
['т'] = 'так',
['так'] = true, ['тийм ээ'] = true, ['тиймээ'] = true,
['ү'] = 'үгүй',
['үгүй'] = false,
['ж'] = 'жоқ',
['жоқ'] = false,
['ҳ'] = 'ҳа',
['ҳа'] = true,
-- Armenian
['ա']--[[hy-abbrev: a]] = 'այո',
['այո']--[[hy: ayo]] = true,
['ո']--[[hy-abbrev: (v)o]] = 'ոչ',
['ոչ']--[[hy: voch']] = false,
-- Georgian
['დ']--[[ka-abbrev: d]] = 'დიახ',
['დიახ']--[[ka: diakh]] = true,
['ა']--[[ka-abbrev: a]] = 'არა',
['არა']--[[ka: ara]] = false,
-- Hangul
['아']--[[ko-abbrev: a]] = '아니',
['아니']--[[ko: ani]] = false,
['예']--[[ko: ye]] = true,
-- Kanas
['は']--[[ja-abbrev: wa]] = 'はい',
['はい']--[[ja: hai]] = true,
['い']--[[ja-abbrev: i]] = 'いいえ',
['いいえ']--[[ja: īe]] = false,
-- CJK
['是']--[[zh-hans & zh-hant, most common: shi]] = true,
['是的']--[[zh-hans & zh-hant, alt: shì-de]] = true,
['没']--[[zh-hans-abbrev: méi]] = '没有',
['没有']--[[zh-hans: méiyǒu]] = false,
['沒']--[[zh-hant-abbrev: méi]] = '沒有',
['沒有']--[[zh-hant: méiyǒu]] = false,
['不']--[[zh-hant: bù]] = false,
['无']--[[zh-hans: wú]] = false,
['無']--[[zh-hant: wú]] = false,
}
function str._getBoolean( s, byDefault, abbrevsDissalowed )
if type( s ) == 'boolean' then
return s;
end
local n = nil;
if type ( s ) == 'number' then
n = s;
elseif type( s ) == 'string' then
s = mw.ustring.lower( mw.ustring.toNFKC( s ) )
s = mw.ustring.match( s, '^%s*(.*)%s*$' )
if s == '' then -- string was empty
-- if the default is nil, don't raise an error but return false
return byDefault or false;
end
n = str._knownBooleans[s];
if type( n ) == 'boolean' then
-- s was mapped to a boolean value n
return n;
elseif type( n ) == 'string' then
-- s was mapped to as an abbreviation of candidate word n
if not abbrevsDissalowed then
n = str._knownBooleans[n]; -- remap that candidate word
if type( n ) == 'boolean' then
-- remapped word has a boolean value (should be true)
return n;
end -- else s is not a number (n == nil)
end
n = nil -- s is not a number (n == nil)
else -- no known Boolean, try converting to a number
n = tonumber( s );
end
end -- else s is not a number (n == nil)
if n == nil then
-- not a number: return the non-nil default or error
if byDefault == nil then
error( 'Unknown boolean value ('..tostring(s)..')' );
end
return byDefault;
end
-- n==0 or n==NaN are false; don't use (n ~= 0) which is true for n==NaN
return n > 0 or n < 0;
end
--[[
Helper function that escapes all pattern characters so that they will be treated
as plain text.
]]
function str._escapePattern( s )
return s:gsub( '([-%%%[%]().+*?^$])', '%%%1' )
end
return str