Hi
This doesn't account for UTF-8 double width characters, so they will
still throw the column widths off?
On Fri, Oct 23, 2015 at 08:42:52AM -0400, Ted Unangst wrote:
> So, third diff to ponder as we evaluate this approach. This one also uses a
> u8len() function to help get the column widths correct.
>
> (Still not dealing with combining or otherwise not 1 width glyphs.)
>
> Index: ls.c
> ===================================================================
> RCS file: /cvs/src/bin/ls/ls.c,v
> retrieving revision 1.43
> diff -u -p -r1.43 ls.c
> --- ls.c 9 Oct 2015 01:37:06 -0000 1.43
> +++ ls.c 23 Oct 2015 12:39:52 -0000
> @@ -410,6 +410,8 @@ traverse(int argc, char *argv[], int opt
> fts_close(ftsp);
> }
>
> +extern size_t u8len(char *);
> +
> /*
> * Display() takes a linked list of FTSENT structures and passes the list
> * along with any other necessary information to the print function. P
> @@ -474,8 +476,8 @@ display(FTSENT *p, FTSENT *list)
> continue;
> }
> }
> - if (cur->fts_namelen > maxlen)
> - maxlen = cur->fts_namelen;
> + if (u8len(cur->fts_name) > maxlen)
> + maxlen = u8len(cur->fts_name);
> if (needstats) {
> sp = cur->fts_statp;
> if (sp->st_blocks > maxblock)
> Index: util.c
> ===================================================================
> RCS file: /cvs/src/bin/ls/util.c,v
> retrieving revision 1.16
> diff -u -p -r1.16 util.c
> --- util.c 21 Nov 2013 15:54:45 -0000 1.16
> +++ util.c 23 Oct 2015 12:39:57 -0000
> @@ -46,12 +46,31 @@
> #include "extern.h"
>
> int
> +isu8cont(unsigned char c)
> +{
> + return ((c & (0x80 | 0x40)) == 0x80);
> +}
> +size_t
> +u8len(const char *s)
> +{
> + size_t len = 0;
> +
> + for (; *s; s++)
> + if (!isu8cont(*s))
> + len++;
> + return len;
> +}
> +
> +int
> putname(char *name)
> {
> int len;
>
> - for (len = 0; *name; len++, name++)
> - putchar((!isprint((unsigned char)*name) && f_nonprint) ? '?' :
> *name);
> + for (len = 0; *name; name++) {
> + if (!isu8cont(*name))
> + len++;
> + putchar(*name);
> + }
> return len;
> }
>
>
