[Tcsh] "Readable" Unicode in setenv

[H.Merijn Brand]

On Fri, 12 Nov 2021 16:32:42 +0100, "H.Merijn Brand" <tcsh at tux.freedom.nl> wrote:

> If I have an environment variable that is to contain something Unicodish,
> I currently have to to something similar to
> 
>  % setenv EURO_CH `perl -CO -e'print "\N{EURO SIGN}"'`
> or
>  % setenv EURO_CH `perl -CO -e'print "\x{20ac}"'`
> 
> so this works
>  % echo $EURO_CH
>  €
> 
> I browsed the tcsh manual, but could not find anything that would hint
> to doing this natively. Is there a (hidden) feature to set Unicode
> characters from the command line by their name or hex value (in the
> current encoding)? Something similar to
> 
>  % setenv EURO_CH "\x{20ac}"
>  % setenv EURO_CH "\u20AC"
> 
> In my digging, I found that
> 
>  % setenv TAB_CH "\t"
> 
> just sets the environment variable TAB_CH to a literal '\' followed by
> a 't'. Which was kinda surprising to me, as I expected a TAB to be in
> there as a literal TAB. That was done in echo in sh.func.c, so
> 
>  % echo $TAB_CH
> 
> translated \t to TAB. To do the same for \x{20ac}, \xbf, and \u0020ac
> I changed sh.func.c like below, but I eventually want those escapes
> to end up literally in the environment. Thoughts welcome
> 
> --8<---
> diff --git a/sh.func.c b/sh.func.c
> index cdfb6d8d..cbc4ff41 100644
> --- a/sh.func.c
> +++ b/sh.func.c
> @@ -1196,6 +1196,22 @@ doglob(Char **v, struct command *c)
>      flush();
>  }
> 
> +static Char
> +parse_hex_range(Char **cp, int l)
> +{
> +    int  ui = 0;
> +    char ub[9];
> +
> +    if (l > 8) return 0; /* Unsupported length */
> +
> +    while (**cp && ui < l && isxdigit(**cp)) {
> +       ub[ui++] = (char)**cp;
> +       (*cp)++;
> +    }
> +    ub[ui] = (char)0;
> +    return strtol (ub, NULL, 16);
> +}
> +
>  static void
>  xecho(int sep, Char **v)
>  {
> @@ -1289,6 +1305,28 @@ xecho(int sep, Char **v)
>                     if (*cp >= '0' && *cp < '8')
>                         c = c * 8 + *cp++ - '0';
>                     break;
> +               case 'x':
> +                   if (*cp == '{' && isxdigit(*(cp + 1))) { /* \x{20ac} */
> +                       cp++;
> +                       c = parse_hex_range (&cp, 8);
> +                       if (*cp != '}')
> +                           stderror(ERR_NAME | ERR_VARBEGIN);
     This needs a proper new error message of course

> +                       cp++;
> +                   }
> +                   else if (isxdigit(*cp)) {   /* \x9f */
> +                       c = parse_hex_range (&cp, 2);
> +                   }
> +                   else /* backward compat */
> +                       xputchar('\\' | QUOTE);
> +                   break;
> +               case 'u':
> +                   if (isxdigit(*cp)) {        /* \u0020ac */
> +                       c = parse_hex_range (&cp, 6);
> +                   }
> +                   else /* backward compat */
> +                       xputchar('\\' | QUOTE);
> +                   break;
> +
>                 case '\0':
>                     c = '\\';
>                     cp--;
> -->8---  

And a demo of course

 % unsetenv EURO
 % echo $EURO
 EURO: Undefined variable.

 % setenv EURO "\u20ac"
 % env | grep EURO
 EURO=\u20ac
 % echo $EURO
 €

 % setenv EURO `echo "\u20ac"`
 % env | grep EURO
 EURO=€
 % echo $EURO
 €

-- 
H.Merijn Brand  https://tux.nl   Perl Monger   http://amsterdam.pm.org/
using perl5.00307 .. 5.33        porting perl5 on HP-UX, AIX, and Linux
https://tux.nl/email.html http://qa.perl.org https://www.test-smoke.org
                           
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 488 bytes
Desc: OpenPGP digital signature
URL: <https://mailman.astron.com/pipermail/tcsh/attachments/20211112/2d701701/attachment.asc>