Finding the attributes of Chinese filenames using NewLISP?

Question

The following NewLISP code shows me the file attributes of files under Win32. However, some of the filenames retrieved have Chinese characters in the name. When the GetFileAttributesA function encounters them, it gives me a -1 for the attribute. I looked at GetFileAttributesW but don't know how to make the contents of the fname available to the function in a form it recognises.

How does one handle this situation? (I am willing to consider trying another language)

(define (get-archive-flag file-name)
    (if (not GetFileAttributesA)
        (begin
        (import "kernel32.DLL" "GetFileAttributesA")
        )
    )
    (setq fname file-name file-attrib (GetFileAttributesA (address fname)))   
    (append fname " " ( string file-attrib))    
)

; walks a disk directory and prints all path-file names
;
(define (show-tree dir)
    (if (directory dir)
        (dolist (nde (directory dir))
            (if (and (directory? (append dir "/" nde))
                (!= nde ".") (!= nde ".."))
                (show-tree (append dir "/" nde))
                (println (get-archive-flag (append dir "/" nde)))
            )
        )
    )
)

(show-tree "z:\\working files\\Cathy")

Answer 1

For the sake of completeness, here's the solution, found in consultation with the folk on the NewLISP forum.

I haven't replaced the bits slice reverse technique on the attribute bit with the more appropriate & operator. That's left for the reader.

(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)
)

; resets the Win32 archive flag on a file
; By CaveGuy 2009

(define (get-archive-flag file-name)
    (if (not GetFileAttributesW)
        (begin
        (import "kernel32.DLL" "GetFileAttributesW")
        )
    )
    (setq fname file-name
        file-attrib (GetFileAttributesW (utf8->16 fname))
    )   
    file-attrib   
)

; walks a disk directory and prints all path-file names where archive bit is set
;
(define (show-tree dir)
    (if (directory dir)
        (dolist (nde (directory dir))
            (if (and (directory? (append dir "/" nde)) (!= nde ".") (!= nde "..") )
                (show-tree (append dir "/" nde))
                (if (not (or (= nde ".") (= nde "..")))
                    (begin
                    (setq fname (append dir "/" nde))
                    (setq fflag (get-archive-flag fname))
                    (setq fbits (bits fflag))
                    (if (= (slice (reverse fbits) 5 1) "1") (println fname))
                    )
                )
            )
        )
    )
)

(show-tree "//server/folder")

Answer 2

Maybe you do not use Unicode version of Newlisp. Anycase, there are very few Newlispers here. Try Newlisp forum instead.

Answer 3

Since version 10.3.2, relased July 20th 2011, 10.3.2 , MultiByteToWideChar is handled internally by newLISP when reading path/file names.