; utf8_to_utf16.lsp
; http://www.newlispfanclub.alh.net/forum/viewtopic.php?f=9&t=3656&p=18353#p18353

(constant 'SIZEOF_WCHAR 2) ; assumption
(constant 'CP_UTF8 65001)

(define (utf8->16 lpMultiByteStr , cchWideChar lpWideCharStr ret)
   (if (not MultiByteToWideChar)
      (begin
      (import "kernel32.DLL" "MultiByteToWideChar")
      )
   )
   ; calculate the size of buffer (in WCHAR's)
   (setq cchWideChar 
      (
      MultiByteToWideChar
      CP_UTF8 ; from UTF-8
      0       ; no flags necessary
      lpMultiByteStr
      -1      ; convert until NULL is encountered
      0
      0
      )
   )
   
   ; allocate the buffer
   (setq lpWideCharStr (dup " " (* cchWideChar SIZEOF_WCHAR)))
   
   ; convert
   (setq ret 
      (
      MultiByteToWideChar
      CP_UTF8 ; from UTF-8
      0       ; no flags necessary
      lpMultiByteStr
      -1      ; convert until NULL is encountered
      lpWideCharStr
      cchWideChar
      )
   )
   (if (> ret 0) lpWideCharStr nil)
)

; test.lsp (Save this file with UTF-8 encoding)
(module "utf8_to_utf16.lsp")
(import "user32.dll" "MessageBoxW")
(MessageBoxW 0 (utf8->16 "中文") (utf8->16 "title") 0)
(exit)

Thanks lexikos! The MultiByteToWideChar works :). I found below code from newLISP forum:

[size=150]utf8_to_utf16.lsp[/size]
[code=newlisp file=utf8_to_utf16.lsp]; utf8_to_utf16.lsp
; http://www.newlispfanclub.alh.net/forum/viewtopic.php?f=9&t=3656&p=18353#p18353

(constant 'SIZEOF_WCHAR 2) ; assumption
(constant 'CP_UTF8 65001)

(define (utf8->16 lpMultiByteStr , cchWideChar lpWideCharStr ret)
(if (not MultiByteToWideChar)
(begin
(import "kernel32.DLL" "MultiByteToWideChar")
)
)
; calculate the size of buffer (in WCHAR's)
(setq cchWideChar
(
MultiByteToWideChar
CP_UTF8 ; from UTF-8
0 ; no flags necessary
lpMultiByteStr
-1 ; convert until NULL is encountered
0
0
)
)

; allocate the buffer
(setq lpWideCharStr (dup " " (* cchWideChar SIZEOF_WCHAR)))

; convert
(setq ret
(
MultiByteToWideChar
CP_UTF8 ; from UTF-8
0 ; no flags necessary
lpMultiByteStr
-1 ; convert until NULL is encountered
lpWideCharStr
cchWideChar
)
)
(if (> ret 0) lpWideCharStr nil)
)[/code]

[size=150]test.lsp[/size]
[code=newlisp file=test.lsp]; test.lsp (Save this file with UTF-8 encoding)
(module "utf8_to_utf16.lsp")
(import "user32.dll" "MessageBoxW")
(MessageBoxW 0 (utf8->16 "中文") (utf8->16 "title") 0)
(exit)[/code]

Put the [b]utf8_to_utf16.lsp[/b] into [b]<path of newlisp.exe>\modules\[/b] folder
Then run with [color=#008000][c]newlisp.exe test.lsp[/c][/color].:superhappy:

I haven't used newLISP, but was interested in what difference there is to LISP and how they handle FFI, so I've had a look.

I think you've misunderstood what the [c]unicode[/c] function does:
[quote]Converts ASCII/UTF-8 character strings in str to [b]UCS-4–encoded[/b] Unicode of [b]4-byte[/b] integers per character. [/quote]It is UTF-32, not UTF-16. So "c" is 0x63 00 00 00 instead of 0x63 00.

I don't see a function for UTF-16, but I suppose you can call MultiByteToWideChar.

(import "user32.dll" "MessageBoxW")
(MessageBoxW 0 "text" "title" 0)

newLISP: http://www.newlisp.org/

I just found this incredible scripting language. But I'm having problems dealing with unicode.

[code=newlisp file=test.lsp](import "user32.dll" "MessageBoxW")
(MessageBoxW 0 "text" "title" 0)[/code]

It displays incorrect strings:
[img]http://i13.tietuku.com/58f6176396800718.png[/img]

If I use [c](MessageBoxW 0 (unicode "content") (unicode "title") 0)[/c], the result turns a little better, that the first character has displayed:
[img]http://i13.tietuku.com/c5b9e9f722e554e3.png[/img]

Anyone can help, please! Thanks in advance.

OS Version: win7 x64, Chinese language
newLISP Version: newLISP v.10.6.2 32-bit on Win32 IPv4/6 UTF-8 libffi