Re: [Dev-luatex] Unicode in \pdfinfo

1 Jul 2008


      Jonathan Sauer wrote:
...
function convertPDFstring(s)
  -- UTF-16 BOM
  sprint(char(0x110000 + 254))
  sprint(char(0x110000 + 255))
-- The string
  for c in string.utfvalues(s) do
      if c < 0x10000 then
      	sprint(char(0x110000 + c / 256))
      	sprint(char(0x110000 + c % 256))
      else
      	c = c - 0x10000
      	local c1 = c / 1024 + 0xD800
      	local c2 = c % 1024 + 0xDC00
      	sprint(char(0x110000 + c1 / 256))
      	sprint(char(0x110000 + c1 % 256))
      	sprint(char(0x110000 + c2 / 256))
      	sprint(char(0x110000 + c2 % 256))
      end
  end
end
slightly more efficient ... (char and byte accept multiple arguments) 
and you can use write which is faster too)

local char = unicode.utf8.char
local write = tex.write

function convertPDFstring(s)
	write(char(0x110000+254,0x110000+255))
	for c in string.utfvalues(s) do
		if c < 0x10000 then
			write(char(0x110000+c/256,0x110000+c%256))
		else
			c = c - 0x10000
			local c1 = c / 1024 + 0xD800
			local c2 = c % 1024 + 0xDC00
		 
write(char(0x110000+c1/256,0x110000+c1%256,0x110000+c2/256,0x110000+c2%256))
		end
	end
end
...
\pdfinfo{/Title(\directlua0{convertPDFstring('my title')})}
in context i use something quick and dirty (no > 0x10000 checking but 
from your function i can deduce the magic umbers -)

function pdf.hexify(str)
     texwrite("feff")
     for b in str:utfvalues() do
         texwrite(("%04x"):format(b))
     end
end

\pdfinfo{/Title(\directlua0{pdf.hexify<'my title'>})}

so <> instead of () as string delimiter

-----------------------------------------------------------------
                                           Hans Hagen | PRAGMA ADE
               Ridderstraat 27 | 8061 GH Hasselt | The Netherlands
      tel: 038 477 53 69 | fax: 038 477 53 74 | www.pragma-ade.com
                                              | www.pragma-pod.nl
-----------------------------------------------------------------