K (Schützte „Modul:Text“ ([Bearbeiten=Nur angemeldete, nicht neue Benutzer] (unbeschränkt) [Verschieben=Nur Administratoren] (unbeschränkt))) |
Im>PerfektesChaos (update; + Modul:TextUtil) |
||
Zeile 1: | Zeile 1: | ||
− | --[=[ |
+ | --[=[ 2014-02-15 |
Text utilities |
Text utilities |
||
]=] |
]=] |
||
Zeile 9: | Zeile 9: | ||
local patternLatin = false |
local patternLatin = false |
||
local patternTerminated = false |
local patternTerminated = false |
||
+ | |||
+ | |||
+ | |||
+ | Text.concatParams = function ( args, apply ) |
||
+ | -- Concat list items into one string |
||
+ | -- Parameter: |
||
+ | -- args -- table (sequence) with numKey=string |
||
+ | -- apply -- string (optional); separator (default: "|") |
||
+ | -- Returns: string |
||
+ | end -- Text.concatParams() |
||
Zeile 17: | Zeile 27: | ||
-- analyse -- string |
-- analyse -- string |
||
-- Returns: true, if CJK detected |
-- Returns: true, if CJK detected |
||
+ | local r |
||
if not patternCJK then |
if not patternCJK then |
||
patternCJK = mw.ustring.char( 91, |
patternCJK = mw.ustring.char( 91, |
||
Zeile 30: | Zeile 41: | ||
return r |
return r |
||
end -- Text.containsCJK() |
end -- Text.containsCJK() |
||
+ | |||
+ | |||
+ | |||
+ | Text.listToText = function ( args, adapt ) |
||
+ | -- Format list items similar to mw.text.listToText() |
||
+ | -- Parameter: |
||
+ | -- args -- table (sequence) with numKey=string |
||
+ | -- adapt -- string (optional); format including "%s" |
||
+ | -- Returns: string |
||
+ | local collect = { } |
||
+ | for k, v in pairs( args ) do |
||
+ | if type( k ) == "number" then |
||
⚫ | |||
+ | if v ~= "" then |
||
+ | if adapt then |
||
+ | v = mw.ustring.format( adapt, v ) |
||
⚫ | |||
+ | table.insert( collect, v ) |
||
+ | end |
||
+ | end |
||
+ | end |
||
+ | return mw.text.listToText( collect ) |
||
+ | end -- Text.listToText() |
||
Zeile 94: | Zeile 128: | ||
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 c > 64 then |
if flat( c ) then |
if flat( c ) then |
||
if j then |
if j then |
||
Zeile 123: | Zeile 157: | ||
end |
end |
||
end -- for i |
end -- for i |
||
− | if |
+ | if not j or m then |
⚫ | |||
⚫ | |||
r = r .. mw.ustring.sub( adjust, k ) |
r = r .. mw.ustring.sub( adjust, k ) |
||
+ | else |
||
+ | r = form( n ) |
||
end |
end |
||
end |
end |
||
Zeile 139: | Zeile 173: | ||
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.listToText( frame ) |
||
+ | local args |
||
+ | local template = frame.args.template |
||
+ | if type( template ) == "string" then |
||
+ | template = mw.text.trim( template ) |
||
+ | template = ( template == "1" ) |
||
+ | end |
||
+ | if template then |
||
+ | args = frame:getParent().args |
||
+ | else |
||
+ | args = frame.args |
||
+ | end |
||
+ | return Text.listToText( frame.args, frame.args.format ) |
||
end |
end |
||
Version vom 16. Februar 2014, 19:20 Uhr
Die Dokumentation für dieses Modul kann unter Modul:Text/Doku erstellt werden
--[=[ 2014-02-15
Text utilities
]=]
local Text = { }
local patternCJK = false
local patternLatin = false
local patternTerminated = false
Text.concatParams = function ( args, apply )
-- Concat list items into one string
-- Parameter:
-- args -- table (sequence) with numKey=string
-- apply -- string (optional); separator (default: "|")
-- Returns: string
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.listToText = function ( args, adapt )
-- Format list items similar to mw.text.listToText()
-- Parameter:
-- args -- table (sequence) with numKey=string
-- 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
return mw.text.listToText( collect )
end -- Text.listToText()
Text.sentenceTerminated = function ( analyse )
-- Is string terminated by dot, question or exclamation mark?
-- Quotation, link termination and so on granted
-- Parameter:
-- analyse -- string
-- Returns: true, if sentence terminated
local r
if not patternTerminated then
patternTerminated = mw.ustring.char( 91,
12290,
65281,
65294,
65311 )
.. "!%.%?…][\"'%]‹›«»‘’“”]*$"
end
if mw.ustring.find( analyse, patternTerminated ) then
r = true
else
r = false
end
return r
end -- Text.sentenceTerminated()
Text.uprightNonlatin = function ( adjust )
-- Ensure non-italics for non-latin text parts
-- One single greek letter might be granted
-- Precondition:
-- adjust -- string
-- Returns: string with non-latin parts enclosed in <span>
local r
if not patternLatin then
patternLatin = mw.ustring.char( 94, 91,
7, 45, 591,
8194, 45, 8250,
93, 42, 36 )
end
if mw.ustring.match( adjust, patternLatin ) then
-- latin only, horizontal dashes, quotes
r = adjust
else
local c
local j = false
local k = 1
local m = false
local n = mw.ustring.len( adjust )
local span = "%s%s<span style='font-style:normal'>%s</span>"
local flat = function ( a )
-- isLatin
return a <= 591 or ( a >= 8194 and a <= 8250 )
end -- flat()
local form = function ( a )
return string.format( span,
r,
mw.ustring.sub( adjust, k, j - 1 ),
mw.ustring.sub( adjust, j, a ) )
end -- form()
r = ""
for i = 1, n do
c = mw.ustring.codepoint( adjust, i, i )
if c > 64 then
if flat( c ) then
if j then
if m then
if i == m then
-- single greek letter.
j = false
end
m = false
end
if j then
r = form( i - 1 )
j = false
k = i
end
end
elseif not j then
j = i
if c >= 880 and c <= 1023 then
-- single greek letter?
m = i + 1
else
m = false
end
end
elseif m then
m = m + 1
end
end -- for i
if not j or m then
r = r .. mw.ustring.sub( adjust, k )
else
r = form( n )
end
end
return r
end -- Text.uprightNonlatin()
-- Export
local p = { }
function p.containsCJK( frame )
return Text.containsCJK( frame.args[ 1 ] or "" ) and "1" or ""
end
function p.listToText( frame )
local args
local template = frame.args.template
if type( template ) == "string" then
template = mw.text.trim( template )
template = ( template == "1" )
end
if template then
args = frame:getParent().args
else
args = frame.args
end
return Text.listToText( frame.args, frame.args.format )
end
function p.sentenceTerminated( frame )
return Text.sentenceTerminated( frame.args[ 1 ] or "" ) and "1" or ""
end
function p.uprightNonlatin( frame )
return Text.uprightNonlatin( frame.args[ 1 ] or "" )
end
p.Text = function ()
return Text
end -- p.Text
return p