Modul:Citation/utilities: Unterschied zwischen den Versionen
(+ci.texts.wrongChars) |
K (51 Versionen von wikivoyage:Modul:Citation/utilities importiert) |
||
(34 dazwischenliegende Versionen von einem anderen Benutzer werden nicht angezeigt) | |||
Zeile 1: | Zeile 1: | ||
-- documentation | -- documentation | ||
local | local citationUtilities = { | ||
suite = 'Citation', | suite = 'Citation', | ||
sub = 'utilities', | sub = 'utilities', | ||
serial = ' | serial = '2022-10-21' | ||
} | } | ||
-- module variable | -- module variable and administration | ||
local cu = {} | local cu = { | ||
moduleInterface = citationUtilities | |||
} | |||
-- module import | -- module import | ||
-- require( 'strict' ) | |||
local ci = require( 'Module:Citation/i18n' ) | local ci = require( 'Module:Citation/i18n' ) | ||
Zeile 24: | Zeile 27: | ||
local mult = 10^( decimalPlaces or 0 ) | local mult = 10^( decimalPlaces or 0 ) | ||
return math.floor( num * mult + 0.5 ) / mult | return math.floor( num * mult + 0.5 ) / mult | ||
end | |||
-- converts string to number | |||
function cu.getNumber( s ) | |||
if not cu.isSet( s ) then | |||
return 0 | |||
end | |||
if s:find( '[sic!]', 1, true ) then | |||
return 0 | |||
end | |||
local kb = s:gsub( ci.texts.decimalPoint, '%.' ) | |||
return tonumber( kb ) or 0 | |||
end | end | ||
Zeile 33: | Zeile 48: | ||
-- make complete message from message array | -- make complete message from message array | ||
function cu.getErrorMsgs() | function cu.getErrorMsgs() | ||
-- remove duplicates | -- remove duplicates | ||
for i = #errorMsgs, 1, -1 do | for i = #errorMsgs, 1, -1 do | ||
Zeile 44: | Zeile 58: | ||
end | end | ||
result = table.concat( errorMsgs, ' ' ) | local result = table.concat( errorMsgs, ' ' ) | ||
if result ~= '' then | if result ~= '' then | ||
result = result .. ' ' | result = result .. ' ' | ||
Zeile 66: | Zeile 80: | ||
end | end | ||
for index, value in ipairs( tab ) do | for index, value in ipairs( tab ) do | ||
if value == val then | if value == val then | ||
Zeile 78: | Zeile 91: | ||
-- convert values t from list if translated | -- convert values t from list if translated | ||
function cu.getKey( t, list ) | function cu.getKey( t, list ) | ||
local result = '' | local result = '' | ||
for key, tab in pairs( list ) do | for key, tab in pairs( list ) do | ||
if cu.inArray( tab, t ) then | if cu.inArray( tab, t ) then | ||
Zeile 90: | Zeile 103: | ||
-- returns a single value from frame argument table | -- returns a single value from frame argument table | ||
function cu.getArgValue( list, param, args ) | function cu.getArgValue( list, param, args ) | ||
value = '' | local value = '' | ||
if list[ param ] then | if list[ param ] then | ||
for k, v in ipairs( list[ param ] ) do | for k, v in ipairs( list[ param ] ) do | ||
Zeile 105: | Zeile 118: | ||
function cu.parameterCleanup( s ) | function cu.parameterCleanup( s ) | ||
if not cu.isSet( s ) then | if not cu.isSet( s ) then | ||
return s | return s -- nil or '' should be kept | ||
end | end | ||
Zeile 114: | Zeile 127: | ||
-- remove tags | -- remove tags | ||
s = mw.ustring.gsub( s, '</*br[^/>]*/*>', '' ) -- <br> | s = mw.ustring.gsub( s, '</*br[^/>]*/*>', '' ) -- <br> tag | ||
s = mw.ustring.gsub( s, '</*p[^/>]*/*>', '' ) -- <p> tag | s = mw.ustring.gsub( s, '</*p[^/>]*/*>', '' ) -- <p> tag | ||
s = mw.ustring.gsub( s, '</*div[^/>]*/*>', '' ) -- <div> tag | s = mw.ustring.gsub( s, '</*div[^/>]*/*>', '' ) -- <div> tag | ||
Zeile 122: | Zeile 135: | ||
end | end | ||
-- replace character references and entities | |||
s = mw.text.decode( s, true ) | |||
-- replace characters | -- replace characters | ||
s = mw.ustring.gsub( s, '%.%.%.', '…' ) | s = mw.ustring.gsub( s, '%.%.%.', '…' ) | ||
Zeile 128: | Zeile 143: | ||
end | end | ||
-- remove illegal chars from pages parameters | |||
function cu.cleanupPageNumbers( pages ) | |||
if not cu.isSet( pages ) then | |||
return '' | |||
end | |||
-- replace dashes with hyphens | |||
return mw.ustring.gsub( '' .. pages, '[–‒—]', '-' ); | |||
end | |||
-- string cleanup before COinS creation | |||
function cu.coinsCleanup( s ) | function cu.coinsCleanup( s ) | ||
if not cu.isSet( s ) then | if not cu.isSet( s ) then | ||
return | return '' | ||
end | end | ||
-- replace characters | -- replace characters | ||
s = s:gsub( '\226\128\138', ' ' ); -- hair space | s = s:gsub( '\226\128\138', ' ' ); -- hair space | ||
s = mw.ustring.gsub( s, '[\226\128\141\226\128\139\194\173]', '' ); -- zero-width joiner, zero-width space, soft hyphen | s = mw.ustring.gsub( s, '[\226\128\141\226\128\139\194\173]', '' ); | ||
-- zero-width joiner, zero-width space, soft hyphen | |||
-- | -- remove characters: soft hyphen, LTR mark, RTL mark | ||
for i, value in ipairs( { '', '', '' } ) do | |||
for i, value in ipairs( { ' | |||
s = mw.ustring.gsub( s, value, '' ) | s = mw.ustring.gsub( s, value, '' ) | ||
end | end | ||
-- replace Wiki syntax | -- replace Wiki syntax | ||
Zeile 165: | Zeile 182: | ||
end | end | ||
-- remove | -- remove adjoining punctuation marks etc. | ||
function cu. | function cu.finalCleanup( s ) | ||
s = s:gsub( '%.+%.', '.' ):gsub( '%s%s+', ' ' ):gsub( '([,;:])(%s%.+)', '.' ) | |||
for _, replacement in ipairs( ci.replacements ) do | |||
s = mw.ustring.gsub( s, replacement.s, replacement.r ) | |||
end | end | ||
s = s:gsub( '#b#', '.' ) -- restore bibcode | |||
return | return s | ||
end | end | ||
function cu.makeLink( url, text ) | function cu.makeLink( url, text ) | ||
return | return mw.ustring.format( '[%s %s]', url, text ) | ||
end | end | ||
Zeile 188: | Zeile 199: | ||
local function formatDate( aDate, aFormat ) | local function formatDate( aDate, aFormat ) | ||
return mw.getContentLanguage():formatDate( aFormat, aDate, true ) | return mw.getContentLanguage():formatDate( aFormat, aDate, true ) | ||
end | |||
if aFormat == 'R' then | |||
return aDate | |||
end | end | ||
if aDate ~='' then | if aDate ~='' then | ||
local | local success, t = pcall( formatDate, aDate, aFormat ) | ||
if success then | if success then | ||
return t | return t | ||
Zeile 210: | Zeile 224: | ||
return url:match( ext .. '$' ) or url:match( ext .. '[%?#]' ) or | return url:match( ext .. '$' ) or url:match( ext .. '[%?#]' ) or | ||
url:match( ext .. '#' ); -- # is # | url:match( ext .. '#' ); -- # is # | ||
end | end | ||
Zeile 266: | Zeile 273: | ||
return '' | return '' | ||
end | end | ||
end | |||
function cu.templateStyles( frame ) | |||
return frame:extensionTag( 'templatestyles', '', { src = ci.styleSrc } ); | |||
end | |||
-- Check digit estimation for countries at, ch, de, and fi | |||
-- See: https://github.com/bohnelang/URN-Pruefziffer | |||
-- Description of the algorithm: http://www.pruefziffernberechnung.de/U/URN.shtml | |||
function cu.getNbnCheckDigit( urn ) | |||
-- two-digits codes for ascii characters starting from - == '-' | |||
local code='3947450102030405060708094117############1814191516212223242542262713282931123233113435363738########43' | |||
local sum = 0 | |||
local pos = 1 | |||
local digit1, digit2, x | |||
urn = urn:upper():sub( 1, -2 ) -- remove last character | |||
for i = 1, urn:len() do | |||
x = 2 * ( urn:byte( i ) - 45 ); -- - == '-' | |||
digit1 = tonumber( code:sub( x + 1, x + 1 ) ); | |||
digit2 = tonumber( code:sub( x + 2, x + 2 ) ); | |||
if digit1 == 0 then | |||
sum = sum + digit2 * pos | |||
pos = pos + 1 | |||
else | |||
sum = sum + digit1 * pos + digit2 * ( pos + 1 ) | |||
pos = pos + 2 | |||
end | |||
end | |||
return tostring( math.floor( sum / digit2 ) % 10 ); | |||
end | |||
function cu.check_UrnNbn( urn ) | |||
urn = urn:gsub( '/fragment/.+$', '' ) -- remove fragment | |||
return urn:sub( -1 ) == cu.getNbnCheckDigit( urn ) | |||
end | end | ||
return cu | return cu |
Aktuelle Version vom 11. Februar 2023, 20:58 Uhr
Die Dokumentation für dieses Modul kann unter Modul:Citation/utilities/doc erstellt werden
-- documentation local citationUtilities = { suite = 'Citation', sub = 'utilities', serial = '2022-10-21' } -- module variable and administration local cu = { moduleInterface = citationUtilities } -- module import -- require( 'strict' ) local ci = require( 'Module:Citation/i18n' ) -- global variable local errorMsgs = {} -- helper functions function cu.isSet( param ) return param and param ~= ''; end -- math function round function cu.round( num, decimalPlaces ) local mult = 10^( decimalPlaces or 0 ) return math.floor( num * mult + 0.5 ) / mult end -- converts string to number function cu.getNumber( s ) if not cu.isSet( s ) then return 0 end if s:find( '[sic!]', 1, true ) then return 0 end local kb = s:gsub( ci.texts.decimalPoint, '%.' ) return tonumber( kb ) or 0 end -- adds error message to array function cu.addErrorMsg( msg ) table.insert( errorMsgs, msg ) end -- make complete message from message array function cu.getErrorMsgs() -- remove duplicates for i = #errorMsgs, 1, -1 do for j = 1, #errorMsgs - 1, 1 do if errorMsgs[ i ] == errorMsgs[ j ] then table.remove( errorMsgs, i ) break end end end local result = table.concat( errorMsgs, ' ' ) if result ~= '' then result = result .. ' ' end return result end -- get first item of a delimiter-separated list function cu.getFirst( s, delimiter ) local at = s:find( delimiter ) if at then s = mw.text.trim( s:sub( 1, at - 1 ) ) end return s end -- check if table contains the value function cu.inArray( tab, val ) if type( tab ) == 'string' then return tab == val end for index, value in ipairs( tab ) do if value == val then return true end end return false end -- convert values t from list if translated function cu.getKey( t, list ) local result = '' for key, tab in pairs( list ) do if cu.inArray( tab, t ) then result = key break end end return result end -- returns a single value from frame argument table function cu.getArgValue( list, param, args ) local value = '' if list[ param ] then for k, v in ipairs( list[ param ] ) do if cu.isSet( args[ v ] ) then value = args[ v ] break end end end return value end -- string cleanup function cu.parameterCleanup( s ) if not cu.isSet( s ) then return s -- nil or '' should be kept end local orig = s -- replace control characters s = s:gsub( '[\009\010\013]', ' ' ) -- horizontal tab, line feed, carriage return s = s:gsub( '[%z%c]', '' ) -- control characters -- remove tags s = mw.ustring.gsub( s, '</*br[^/>]*/*>', '' ) -- <br> tag s = mw.ustring.gsub( s, '</*p[^/>]*/*>', '' ) -- <p> tag s = mw.ustring.gsub( s, '</*div[^/>]*/*>', '' ) -- <div> tag if orig ~= s then cu.addErrorMsg( ci.texts.wrongChars ) end -- replace character references and entities s = mw.text.decode( s, true ) -- replace characters s = mw.ustring.gsub( s, '%.%.%.', '…' ) s = mw.ustring.gsub( s, '%.%.', '‥' ) return s:gsub( '%s%s+', ' ' ) -- multiple spaces end -- remove illegal chars from pages parameters function cu.cleanupPageNumbers( pages ) if not cu.isSet( pages ) then return '' end -- replace dashes with hyphens return mw.ustring.gsub( '' .. pages, '[–‒—]', '-' ); end -- string cleanup before COinS creation function cu.coinsCleanup( s ) if not cu.isSet( s ) then return '' end -- replace characters s = s:gsub( '\226\128\138', ' ' ); -- hair space s = mw.ustring.gsub( s, '[\226\128\141\226\128\139\194\173]', '' ); -- zero-width joiner, zero-width space, soft hyphen -- remove characters: soft hyphen, LTR mark, RTL mark for i, value in ipairs( { '', '', '' } ) do s = mw.ustring.gsub( s, value, '' ) end -- replace Wiki syntax s = s:gsub( "''+", '' ) -- multiple apostrophes s = mw.ustring.gsub( s, '</*span[^/>]*/*>', '' ) -- span tags s = mw.ustring.gsub( s, '%[%[[^%[%]]*|([^%[%]]*)%]%]', '%1' ) -- MediaWiki links s = mw.ustring.gsub( s, '%[%[([^%[%]]*)%]%]', '%1' ) s = mw.ustring.gsub( s, '%[%a*:?//[^ ]+%s+([^%]]+)%]', '%1' ) -- web links s = mw.ustring.gsub( s, '%[mailto:[^ ]+%s+([^%]]+)%]', '%1' ) s = mw.ustring.gsub( s, '%[%a*:?//([^%]]+)%]', '%1' ) s = mw.ustring.gsub( s, '%[mailto:([^%]]+)%]', '%1' ) return s:gsub( '%s%s+', ' ' ) -- multiple spaces end -- remove adjoining punctuation marks etc. function cu.finalCleanup( s ) s = s:gsub( '%.+%.', '.' ):gsub( '%s%s+', ' ' ):gsub( '([,;:])(%s%.+)', '.' ) for _, replacement in ipairs( ci.replacements ) do s = mw.ustring.gsub( s, replacement.s, replacement.r ) end s = s:gsub( '#b#', '.' ) -- restore bibcode return s end function cu.makeLink( url, text ) return mw.ustring.format( '[%s %s]', url, text ) end function cu.getDate( aDate, aFormat, errorMsg ) local function formatDate( aDate, aFormat ) return mw.getContentLanguage():formatDate( aFormat, aDate, true ) end if aFormat == 'R' then return aDate end if aDate ~='' then local success, t = pcall( formatDate, aDate, aFormat ) if success then return t else cu.addErrorMsg( errorMsg ) return '' end else return '' end end -- check if url contains a file extension function cu.hasExtension( url, ext ) ext = '%.' .. ext:upper() url = url:upper() return url:match( ext .. '$' ) or url:match( ext .. '[%?#]' ) or url:match( ext .. '#' ); -- # is # end function cu.insertItem( tab, s, formatStr ) if cu.isSet( s ) then if formatStr then table.insert( tab, mw.ustring.format( formatStr, s ) ) else table.insert( tab, s ) end end end function cu.insertItem2( tab, s1, s2, formatStr ) if cu.isSet( s1 ) and cu.isSet( s2 ) then if formatStr then table.insert( tab, mw.ustring.format( formatStr, s1, s2 ) ) else table.insert( tab, s1 ) table.insert( tab, s2 ) end end end function cu.formatItem( s, formatStr ) if cu.isSet( s ) then if formatStr then return mw.ustring.format( formatStr, s ) else return s end else return '' end end function cu.formatItem2( s1, s2, formatStr ) if cu.isSet( s1 ) and cu.isSet( s2 ) then if formatStr then return mw.ustring.format( formatStr, s1, s2 ) else return s1 .. ' ' .. s2 end else return '' end end function cu.templateStyles( frame ) return frame:extensionTag( 'templatestyles', '', { src = ci.styleSrc } ); end -- Check digit estimation for countries at, ch, de, and fi -- See: https://github.com/bohnelang/URN-Pruefziffer -- Description of the algorithm: http://www.pruefziffernberechnung.de/U/URN.shtml function cu.getNbnCheckDigit( urn ) -- two-digits codes for ascii characters starting from - == '-' local code='3947450102030405060708094117############1814191516212223242542262713282931123233113435363738########43' local sum = 0 local pos = 1 local digit1, digit2, x urn = urn:upper():sub( 1, -2 ) -- remove last character for i = 1, urn:len() do x = 2 * ( urn:byte( i ) - 45 ); -- - == '-' digit1 = tonumber( code:sub( x + 1, x + 1 ) ); digit2 = tonumber( code:sub( x + 2, x + 2 ) ); if digit1 == 0 then sum = sum + digit2 * pos pos = pos + 1 else sum = sum + digit1 * pos + digit2 * ( pos + 1 ) pos = pos + 2 end end return tostring( math.floor( sum / digit2 ) % 10 ); end function cu.check_UrnNbn( urn ) urn = urn:gsub( '/fragment/.+$', '' ) -- remove fragment return urn:sub( -1 ) == cu.getNbnCheckDigit( urn ) end return cu