Modul:Text: Unterschied zwischen den Versionen
Zur Navigation springen
Zur Suche springen
te>PerfektesChaos (2015-05-22) |
K (30 Versionen importiert) |
||
(9 dazwischenliegende Versionen von 3 Benutzern werden nicht angezeigt) | |||
Zeile 1: | Zeile 1: | ||
− | --[=[ | + | local Text = { serial = "2018-11-14", |
+ | suite = "Text" } | ||
+ | --[=[ | ||
Text utilities | Text utilities | ||
]=] | ]=] | ||
Zeile 5: | Zeile 7: | ||
− | local | + | -- local globals |
local PatternCJK = false | local PatternCJK = false | ||
local PatternCombined = false | local PatternCombined = false | ||
local PatternLatin = false | local PatternLatin = false | ||
local PatternTerminated = false | local PatternTerminated = false | ||
− | |||
− | |||
local RangesLatin = false | local RangesLatin = false | ||
local SeekQuote = false | local SeekQuote = false | ||
Zeile 19: | Zeile 19: | ||
local function factoryQuote() | local function factoryQuote() | ||
-- Create quote definitions | -- Create quote definitions | ||
− | + | if not Text.quoteLang then | |
− | + | local lucky, quoting = pcall( mw.loadData, | |
− | + | "Module:Text/quoting" ) | |
− | + | if type( quoting ) == "table" then | |
− | + | Text.quoteLang = quoting.langs | |
− | + | Text.quoteType = quoting.types | |
− | + | end | |
− | + | if type( Text.quoteLang ) ~= "table" then | |
− | + | Text.quoteLang = { } | |
− | + | end | |
− | + | if type( Text.quoteType ) ~= "table" then | |
− | + | Text.quoteType = { } | |
− | + | end | |
− | + | if type( Text.quoteLang.en ) ~= "string" then | |
− | + | Text.quoteLang.en = "ld" | |
− | + | end | |
− | + | if type( Text.quoteType[ Text.quoteLang.en ] ) ~= "table" then | |
− | + | Text.quoteType[ Text.quoteLang.en ] = { { 8220, 8221 }, | |
− | + | { 8216, 8217 } } | |
− | + | end | |
− | + | end | |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
end -- factoryQuote() | end -- factoryQuote() | ||
Zeile 97: | Zeile 52: | ||
local r = apply | local r = apply | ||
local suite | local suite | ||
− | + | factoryQuote() | |
− | + | suite = Text.quoteLang[ alien ] | |
− | |||
− | suite = | ||
if not suite then | if not suite then | ||
local slang = alien:match( "^(%l+)-" ) | local slang = alien:match( "^(%l+)-" ) | ||
if slang then | if slang then | ||
− | suite = | + | suite = Text.quoteLang[ slang ] |
end | end | ||
if not suite then | if not suite then | ||
− | suite = | + | suite = Text.quoteLang.en |
end | end | ||
end | end | ||
if suite then | if suite then | ||
− | local quotes = | + | local quotes = Text.quoteType[ suite ] |
if quotes then | if quotes then | ||
+ | local space | ||
+ | if quotes[ 3 ] then | ||
+ | space = " " | ||
+ | else | ||
+ | space = "" | ||
+ | end | ||
quotes = quotes[ advance ] | quotes = quotes[ advance ] | ||
if quotes then | if quotes then | ||
− | r = mw.ustring.format( "%s%s%s", | + | r = mw.ustring.format( "%s%s%s%s%s", |
mw.ustring.char( quotes[ 1 ] ), | mw.ustring.char( quotes[ 1 ] ), | ||
+ | space, | ||
apply, | apply, | ||
+ | space, | ||
mw.ustring.char( quotes[ 2 ] ) ) | mw.ustring.char( quotes[ 2 ] ) ) | ||
end | end | ||
Zeile 126: | Zeile 87: | ||
return r | return r | ||
end -- fiatQuote() | end -- fiatQuote() | ||
+ | |||
+ | |||
+ | |||
+ | Text.char = function ( apply, again, accept ) | ||
+ | -- Create string from codepoints | ||
+ | -- Parameter: | ||
+ | -- apply -- table (sequence) with numerical codepoints, or nil | ||
+ | -- again -- number of repetitions, or nil | ||
+ | -- accept -- true, if no error messages to be appended | ||
+ | -- Returns: string | ||
+ | local r | ||
+ | if type( apply ) == "table" then | ||
+ | local bad = { } | ||
+ | local codes = { } | ||
+ | local s | ||
+ | for k, v in pairs( apply ) do | ||
+ | s = type( v ) | ||
+ | if s == "number" then | ||
+ | if v < 32 and v ~= 9 and v ~= 10 then | ||
+ | v = tostring( v ) | ||
+ | else | ||
+ | v = math.floor( v ) | ||
+ | s = false | ||
+ | end | ||
+ | elseif s ~= "string" then | ||
+ | v = tostring( v ) | ||
+ | end | ||
+ | if s then | ||
+ | table.insert( bad, v ) | ||
+ | else | ||
+ | table.insert( codes, v ) | ||
+ | end | ||
+ | end -- for k, v | ||
+ | if #bad == 0 then | ||
+ | if #codes > 0 then | ||
+ | r = mw.ustring.char( unpack( codes ) ) | ||
+ | if again then | ||
+ | if type( again ) == "number" then | ||
+ | local n = math.floor( again ) | ||
+ | if n > 1 then | ||
+ | r = r:rep( n ) | ||
+ | elseif n < 1 then | ||
+ | r = "" | ||
+ | end | ||
+ | else | ||
+ | s = "bad repetitions: " .. tostring( again ) | ||
+ | end | ||
+ | end | ||
+ | end | ||
+ | else | ||
+ | s = "bad codepoints: " .. table.concat( bad, " " ) | ||
+ | end | ||
+ | if s and not accept then | ||
+ | r = tostring( mw.html.create( "span" ) | ||
+ | :addClass( "error" ) | ||
+ | :wikitext( s ) ) | ||
+ | end | ||
+ | end | ||
+ | return r or "" | ||
+ | end -- Text.char() | ||
Zeile 147: | Zeile 168: | ||
end | end | ||
end | end | ||
− | end | + | end -- for k, v |
return table.concat( collect, apply or "|" ) | return table.concat( collect, apply or "|" ) | ||
end -- Text.concatParams() | end -- Text.concatParams() | ||
Zeile 172: | Zeile 193: | ||
return r | return r | ||
end -- Text.containsCJK() | end -- Text.containsCJK() | ||
+ | |||
+ | |||
+ | |||
+ | Text.getPlain = function ( adjust ) | ||
+ | -- Remove wikisyntax from string, except templates | ||
+ | -- Parameter: | ||
+ | -- adjust -- string | ||
+ | -- Returns: string | ||
+ | local i = adjust:find( "<!--", 1, true ) | ||
+ | local r = adjust | ||
+ | local j | ||
+ | while i do | ||
+ | j = r:find( "-->", i + 3, true ) | ||
+ | if j then | ||
+ | r = r:sub( 1, i ) .. r:sub( j + 3 ) | ||
+ | else | ||
+ | r = r:sub( 1, i ) | ||
+ | end | ||
+ | i = r:find( "<!--", i, true ) | ||
+ | end -- "<!--" | ||
+ | r = r:gsub( "(</?%l[^>]*>)", "" ) | ||
+ | :gsub( "'''(.+)'''", "%1" ) | ||
+ | :gsub( "''(.+)''", "%1" ) | ||
+ | :gsub( " ", " " ) | ||
+ | return r | ||
+ | end -- Text.getPlain() | ||
Zeile 262: | Zeile 309: | ||
end | end | ||
end | end | ||
− | end | + | end -- for k, v |
return mw.text.listToText( collect ) | return mw.text.listToText( collect ) | ||
end -- Text.listToText() | end -- Text.listToText() | ||
+ | |||
+ | |||
+ | |||
+ | Text.quote = function ( apply, alien, advance ) | ||
+ | -- Quote text | ||
+ | -- Parameter: | ||
+ | -- apply -- string, with text | ||
+ | -- alien -- string, with language code, or nil | ||
+ | -- advance -- number, with level 1 or 2, or nil | ||
+ | -- Returns: quoted string | ||
+ | local mode, slang | ||
+ | if type( alien ) == "string" then | ||
+ | slang = mw.text.trim( alien ):lower() | ||
+ | else | ||
+ | slang = mw.title.getCurrentTitle().pageLanguage | ||
+ | if not slang then | ||
+ | -- TODO FIXME: Introduction expected 2017-04 | ||
+ | slang = mw.language.getContentLanguage():getCode() | ||
+ | end | ||
+ | end | ||
+ | if advance == 2 then | ||
+ | mode = 2 | ||
+ | else | ||
+ | mode = 1 | ||
+ | end | ||
+ | return fiatQuote( mw.text.trim( apply ), slang, mode ) | ||
+ | end -- Text.quote() | ||
Text.quoteUnquoted = function ( apply, alien, advance ) | Text.quoteUnquoted = function ( apply, alien, advance ) | ||
− | -- Quote text, if not yet quoted | + | -- Quote text, if not yet quoted and not empty |
-- Parameter: | -- Parameter: | ||
-- apply -- string, with text | -- apply -- string, with text | ||
Zeile 277: | Zeile 351: | ||
local r = mw.text.trim( apply ) | local r = mw.text.trim( apply ) | ||
local s = mw.ustring.sub( r, 1, 1 ) | local s = mw.ustring.sub( r, 1, 1 ) | ||
− | if s ~= "" and not Text.isQuote( s ) then | + | if s ~= "" and not Text.isQuote( s, advance ) then |
s = mw.ustring.sub( r, -1, 1 ) | s = mw.ustring.sub( r, -1, 1 ) | ||
if not Text.isQuote( s ) then | if not Text.isQuote( s ) then | ||
− | + | r = Text.quote( r, alien, advance ) | |
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
− | |||
end | end | ||
end | end | ||
Zeile 424: | Zeile 487: | ||
end -- for i | end -- for i | ||
end -- flat() | end -- flat() | ||
+ | local focus = function ( a ) | ||
+ | -- char is not ambivalent | ||
+ | local r = ( a > 64 ) | ||
+ | if r then | ||
+ | r = ( a < 8192 or a > 8212 ) | ||
+ | else | ||
+ | r = ( a == 38 or a == 60 ) -- '&' '<' | ||
+ | end | ||
+ | return r | ||
+ | end -- focus() | ||
local form = function ( a ) | local form = function ( a ) | ||
return string.format( span, | return string.format( span, | ||
Zeile 433: | Zeile 506: | ||
for i = 1, n do | for i = 1, n do | ||
c = mw.ustring.codepoint( adjust, i, i ) | c = mw.ustring.codepoint( adjust, i, i ) | ||
− | if c | + | if focus( c ) then |
if flat( c ) then | if flat( c ) then | ||
if j then | if j then | ||
Zeile 488: | Zeile 561: | ||
if about == "quote" then | if about == "quote" then | ||
factoryQuote() | factoryQuote() | ||
− | r = { | + | r = { QuoteLang = Text.quoteLang, |
− | + | QuoteType = Text.quoteType } | |
− | |||
end | end | ||
return r | return r | ||
Zeile 499: | Zeile 571: | ||
-- Export | -- Export | ||
local p = { } | local p = { } | ||
+ | |||
+ | function p.char( frame ) | ||
+ | local params = frame:getParent().args | ||
+ | local story = params[ 1 ] | ||
+ | local codes, lenient, multiple | ||
+ | if not story then | ||
+ | params = frame.args | ||
+ | story = params[ 1 ] | ||
+ | end | ||
+ | if story then | ||
+ | local items = mw.text.split( story, "%s+" ) | ||
+ | if #items > 0 then | ||
+ | local j | ||
+ | lenient = ( params.errors == "0" ) | ||
+ | codes = { } | ||
+ | multiple = tonumber( params[ "*" ] ) | ||
+ | for k, v in pairs( items ) do | ||
+ | if v:sub( 1, 1 ) == "x" then | ||
+ | j = tonumber( "0" .. v ) | ||
+ | elseif v == "" then | ||
+ | v = false | ||
+ | else | ||
+ | j = tonumber( v ) | ||
+ | end | ||
+ | if v then | ||
+ | table.insert( codes, j or v ) | ||
+ | end | ||
+ | end -- for k, v | ||
+ | end | ||
+ | end | ||
+ | return Text.char( codes, multiple, lenient ) | ||
+ | end | ||
function p.concatParams( frame ) | function p.concatParams( frame ) | ||
Zeile 519: | Zeile 623: | ||
function p.containsCJK( frame ) | function p.containsCJK( frame ) | ||
return Text.containsCJK( frame.args[ 1 ] or "" ) and "1" or "" | return Text.containsCJK( frame.args[ 1 ] or "" ) and "1" or "" | ||
+ | end | ||
+ | |||
+ | function p.getPlain( frame ) | ||
+ | return Text.getPlain( frame.args[ 1 ] or "" ) | ||
end | end | ||
function p.isLatinRange( frame ) | function p.isLatinRange( frame ) | ||
− | return Text.isLatinRange( frame.args[1] or "" ) and "1" or "" | + | return Text.isLatinRange( frame.args[ 1 ] or "" ) and "1" or "" |
end | end | ||
function p.isQuote( frame ) | function p.isQuote( frame ) | ||
− | return Text.isQuote( frame.args[1] or "" ) and "1" or "" | + | return Text.isQuote( frame.args[ 1 ] or "" ) and "1" or "" |
end | end | ||
+ | |||
+ | |||
+ | |||
+ | function p.listToFormat(frame) | ||
+ | local lists = {} | ||
+ | local pformat = frame.args["format"] | ||
+ | local sep = frame.args["sep"] or ";" | ||
+ | |||
+ | -- Parameter parsen: Listen | ||
+ | for k, v in pairs(frame.args) do | ||
+ | local knum = tonumber(k) | ||
+ | if knum then lists[knum] = v end | ||
+ | end | ||
+ | |||
+ | -- Listen splitten | ||
+ | local maxListLen = 0 | ||
+ | for i = 1, #lists do | ||
+ | lists[i] = mw.text.split(lists[i], sep) | ||
+ | if #lists[i] > maxListLen then maxListLen = #lists[i] end | ||
+ | end | ||
+ | |||
+ | -- Ergebnisstring generieren | ||
+ | local result = "" | ||
+ | local result_line = "" | ||
+ | for i = 1, maxListLen do | ||
+ | result_line = pformat | ||
+ | for j = 1, #lists do | ||
+ | result_line = mw.ustring.gsub(result_line, "%%s", lists[j][i], 1) | ||
+ | end | ||
+ | result = result .. result_line | ||
+ | end | ||
+ | |||
+ | return result | ||
+ | end | ||
+ | |||
+ | |||
function p.listToText( frame ) | function p.listToText( frame ) | ||
Zeile 543: | Zeile 687: | ||
return Text.listToText( args, frame.args.format ) | return Text.listToText( args, frame.args.format ) | ||
end | end | ||
+ | |||
+ | |||
+ | |||
+ | function p.quote( frame ) | ||
+ | local slang = frame.args[2] | ||
+ | if type( slang ) == "string" then | ||
+ | slang = mw.text.trim( slang ) | ||
+ | if slang == "" then | ||
+ | slang = false | ||
+ | end | ||
+ | end | ||
+ | return Text.quote( frame.args[ 1 ] or "", | ||
+ | slang, | ||
+ | tonumber( frame.args[3] ) ) | ||
+ | end | ||
+ | |||
+ | |||
function p.quoteUnquoted( frame ) | function p.quoteUnquoted( frame ) | ||
Zeile 548: | Zeile 709: | ||
if type( slang ) == "string" then | if type( slang ) == "string" then | ||
slang = mw.text.trim( slang ) | slang = mw.text.trim( slang ) | ||
+ | if slang == "" then | ||
+ | slang = false | ||
+ | end | ||
end | end | ||
− | return Text.quoteUnquoted( frame.args[1] or "", | + | return Text.quoteUnquoted( frame.args[ 1 ] or "", |
slang, | slang, | ||
tonumber( frame.args[3] ) ) | tonumber( frame.args[3] ) ) | ||
end | end | ||
+ | |||
+ | |||
function p.removeDiacritics( frame ) | function p.removeDiacritics( frame ) | ||
− | return Text.removeDiacritics( frame.args[1] or "" ) | + | return Text.removeDiacritics( frame.args[ 1 ] or "" ) |
end | end | ||
Zeile 564: | Zeile 730: | ||
function p.ucfirstAll( frame ) | function p.ucfirstAll( frame ) | ||
return Text.ucfirstAll( frame.args[ 1 ] or "" ) | return Text.ucfirstAll( frame.args[ 1 ] or "" ) | ||
+ | end | ||
+ | |||
+ | function p.unstrip( frame ) | ||
+ | return mw.text.trim( mw.text.unstrip( frame.args[ 1 ] or "" ) ) | ||
end | end | ||
Zeile 569: | Zeile 739: | ||
return Text.uprightNonlatin( frame.args[ 1 ] or "" ) | return Text.uprightNonlatin( frame.args[ 1 ] or "" ) | ||
end | end | ||
+ | |||
+ | |||
function p.zip(frame) | function p.zip(frame) | ||
− | + | local lists = {} | |
− | + | local seps = {} | |
− | + | local defaultsep = frame.args["sep"] or "" | |
− | + | local innersep = frame.args["isep"] or "" | |
− | + | local outersep = frame.args["osep"] or "" | |
− | + | -- Parameter parsen | |
− | + | for k, v in pairs(frame.args) do | |
− | + | local knum = tonumber(k) | |
− | + | if knum then lists[knum] = v else | |
− | + | if string.sub(k, 1, 3) == "sep" then | |
− | + | local sepnum = tonumber(string.sub(k, 4)) | |
− | + | if sepnum then seps[sepnum] = v end | |
− | + | end | |
− | + | end | |
− | + | end | |
− | + | -- sofern keine expliziten Separatoren angegeben sind, den Standardseparator verwenden | |
− | + | for i = 1, math.max(#seps, #lists) do | |
− | + | if not seps[i] then seps[i] = defaultsep end | |
− | + | end | |
− | + | -- Listen splitten | |
− | + | local maxListLen = 0 | |
− | + | for i = 1, #lists do | |
− | + | lists[i] = mw.text.split(lists[i], seps[i]) | |
− | + | if #lists[i] > maxListLen then maxListLen = #lists[i] end | |
− | + | end | |
− | + | local result = "" | |
− | + | for i = 1, maxListLen do | |
− | + | if i ~= 1 then result = result .. outersep end | |
− | + | for j = 1, #lists do | |
− | + | if j ~= 1 then result = result .. innersep end | |
− | + | result = result .. (lists[j][i] or "") | |
− | + | end | |
− | + | end | |
− | + | return result | |
end | end | ||
+ | |||
+ | |||
+ | |||
+ | function p.failsafe() | ||
+ | return Text.serial | ||
+ | end | ||
+ | |||
+ | |||
p.Text = function () | p.Text = function () |
Aktuelle Version vom 6. September 2019, 12:54 Uhr
local Text = { serial = "2018-11-14",
suite = "Text" }
--[=[ Text utilities ]=]
-- local globals local PatternCJK = false local PatternCombined = false local PatternLatin = false local PatternTerminated = false local RangesLatin = false local SeekQuote = false
local function factoryQuote()
-- Create quote definitions if not Text.quoteLang then local lucky, quoting = pcall( mw.loadData, "Module:Text/quoting" ) if type( quoting ) == "table" then Text.quoteLang = quoting.langs Text.quoteType = quoting.types end if type( Text.quoteLang ) ~= "table" then Text.quoteLang = { } end if type( Text.quoteType ) ~= "table" then Text.quoteType = { } end if type( Text.quoteLang.en ) ~= "string" then Text.quoteLang.en = "ld" end if type( Text.quoteType[ Text.quoteLang.en ] ) ~= "table" then Text.quoteType[ Text.quoteLang.en ] = { { 8220, 8221 }, { 8216, 8217 } } end end
end -- factoryQuote()
local function fiatQuote( apply, alien, advance )
-- Quote text -- Parameter: -- apply -- string, with text -- alien -- string, with language code -- advance -- number, with level 1 or 2 local r = apply local suite factoryQuote() suite = Text.quoteLang[ alien ] if not suite then local slang = alien:match( "^(%l+)-" ) if slang then suite = Text.quoteLang[ slang ] end if not suite then suite = Text.quoteLang.en end end if suite then local quotes = Text.quoteType[ suite ] if quotes then local space if quotes[ 3 ] then space = " " else space = "" end quotes = quotes[ advance ] if quotes then r = mw.ustring.format( "%s%s%s%s%s", mw.ustring.char( quotes[ 1 ] ), space, apply, space, mw.ustring.char( quotes[ 2 ] ) ) end else mw.log( "fiatQuote() " .. suite ) end end return r
end -- fiatQuote()
Text.char = function ( apply, again, accept )
-- Create string from codepoints -- Parameter: -- apply -- table (sequence) with numerical codepoints, or nil -- again -- number of repetitions, or nil -- accept -- true, if no error messages to be appended -- Returns: string local r if type( apply ) == "table" then local bad = { } local codes = { } local s for k, v in pairs( apply ) do s = type( v ) if s == "number" then if v < 32 and v ~= 9 and v ~= 10 then v = tostring( v ) else v = math.floor( v ) s = false end elseif s ~= "string" then v = tostring( v ) end if s then table.insert( bad, v ) else table.insert( codes, v ) end end -- for k, v if #bad == 0 then if #codes > 0 then r = mw.ustring.char( unpack( codes ) ) if again then if type( again ) == "number" then local n = math.floor( again ) if n > 1 then r = r:rep( n ) elseif n < 1 then r = "" end else s = "bad repetitions: " .. tostring( again ) end end end else s = "bad codepoints: " .. table.concat( bad, " " ) end if s and not accept then r = tostring( mw.html.create( "span" ) :addClass( "error" ) :wikitext( s ) ) end end return r or ""
end -- Text.char()
Text.concatParams = function ( args, apply, adapt )
-- Concat list items into one string -- Parameter: -- args -- table (sequence) with numKey=string -- apply -- string (optional); separator (default: "|") -- adapt -- string (optional); format including "%s" -- Returns: string local collect = { } for k, v in pairs( args ) do if type( k ) == "number" then v = mw.text.trim( v ) if v ~= "" then if adapt then v = mw.ustring.format( adapt, v ) end table.insert( collect, v ) end end end -- for k, v return table.concat( collect, apply or "|" )
end -- Text.concatParams()
Text.containsCJK = function ( analyse )
-- Is any CJK code within? -- Parameter: -- analyse -- string -- Returns: true, if CJK detected local r if not patternCJK then patternCJK = mw.ustring.char( 91, 13312, 45, 40959, 131072, 45, 178207, 93 ) end if mw.ustring.find( analyse, patternCJK ) then r = true else r = false end return r
end -- Text.containsCJK()
Text.getPlain = function ( adjust )
-- Remove wikisyntax from string, except templates -- Parameter: -- adjust -- string -- Returns: string local i = adjust:find( "", i + 3, true ) if j then r = r:sub( 1, i ) .. r:sub( j + 3 ) else r = r:sub( 1, i ) end i = r:find( "