10 дек. 2015 г. 18:51 пользователь "Ingo Schwarze" <schwa...@usta.de>
написал:
>
> Hi,
>
> here is a simple one. The uniq(1) utility only needs UTF-8 support
> to distinguish blank and non-blank characters with -f and to skip
> characters with -s. The former is easy to implement with mbtowc(3)
> and iswblank(3), the latter with mblen(3). There is no need for
> wrapper functions or a seperate utf8.c file.
>
> OK?
> Ingo
>
>
> Index: uniq.1
> ===================================================================
> RCS file: /cvs/src/usr.bin/uniq/uniq.1,v
> retrieving revision 1.17
> diff -u -p -r1.17 uniq.1
> --- uniq.1 3 Sep 2010 11:09:29 -0000 1.17
> +++ uniq.1 10 Dec 2015 15:37:02 -0000
> @@ -114,6 +114,14 @@ A file name of
> .Ql -
> denotes the standard input or the standard output
> .Pq depending on its position on the command line .
> +.Sh ENVIRONMENT
> +.Bl -tag -width LC_CTYPE
> +.It Ev LC_CTYPE
> +The character set
> +.Xr locale 1 .
> +Determines which groups of bytes are treated as characters
> +and which characters are considered blank.
> +.El
> .Sh EXIT STATUS
> .Ex -std uniq
> .Sh SEE ALSO
> Index: uniq.c
> ===================================================================
> RCS file: /cvs/src/usr.bin/uniq/uniq.c,v
> retrieving revision 1.23
> diff -u -p -r1.23 uniq.c
> --- uniq.c 2 Nov 2015 20:25:42 -0000 1.23
> +++ uniq.c 10 Dec 2015 15:37:02 -0000
> @@ -37,10 +37,13 @@
> #include <err.h>
> #include <errno.h>
> #include <limits.h>
> +#include <locale.h>
> #include <stdio.h>
> #include <stdlib.h>
> #include <string.h>
> #include <unistd.h>
> +#include <wchar.h>
> +#include <wctype.h>
>
> #define MAXLINELEN (8 * 1024)
>
> @@ -61,6 +64,8 @@ main(int argc, char *argv[])
> int ch;
> char *prevline, *thisline;
>
> + setlocale(LC_CTYPE, "");
> +
> if (pledge("stdio rpath wpath cpath", NULL) == -1)
> err(1, "pledge");
>
> @@ -176,16 +181,38 @@ show(FILE *ofp, char *str)
> char *
> skip(char *str)
> {
> + wchar_t wc;
> int nchars, nfields;
> + int len;
>
> for (nfields = numfields; nfields && *str; nfields--) {
> - while (isblank((unsigned char)*str))
> - str++;
> - while (*str && !isblank((unsigned char)*str))
> - str++;
> +
> + /* Skip blanks before the next field. */
> + do {
> + if ((len = mbtowc(&wc, str, MB_CUR_MAX)) == -1) {
> + (void)mbtowc(NULL, NULL, MB_CUR_MAX);
> + wc = L'?';
> + len = 1;
> + }
> + str += len;
> + } while (*str != '\0' && iswblank(wc));
> +
> + /* Skip one field. */
> + while (*str != '\0' && !iswblank(wc)) {
> + if ((len = mbtowc(&wc, str, MB_CUR_MAX)) == -1) {
> + (void)mbtowc(NULL, NULL, MB_CUR_MAX);
> + wc = L'?';
> + len = 1;
> + }
> + str += len;
> + }
> }
> - for (nchars = numchars; nchars-- && *str && *str != '\n'; ++str)
> - ;
> +
> + /* Skip some additional characters. */
> + for (nchars = numchars; nchars-- && *str != '\0'; str += len)
> + if ((len = mblen(str, MB_CUR_MAX)) == -1)
> + len = 1;
> +
> return (str);
> }
Reads good to me, okay zhuk@.
--
Vadim Zhukov
