From: Sape Mullender <sape@plan9.bell-labs.com>
To: 9fans@cse.psu.edu
Subject: Re: [9fans] conversion of charsets in upas/fs
Date: Tue, 1 Feb 2005 15:41:16 -0500 [thread overview]
Message-ID: <a911fbfff731b0a56b03c75d36097e47@plan9.bell-labs.com> (raw)
In-Reply-To: <5d1294dbc2ec360ffbcdcc8fd86e829f@voidness.de>
[-- Attachment #1: Type: text/plain, Size: 67 bytes --]
This might help to change you umlauts into real ones :-)
Sape
[-- Attachment #2: utf2latin.c --]
[-- Type: text/plain, Size: 1858 bytes --]
#include <stdio.h>
FILE *f;
main(int argc, char ** argv)
{ int c, c1, c2;
unsigned int r;
char buf[8];
if (argc > 2) {
fprintf(stderr, "Usage: %s [ file ]\n", argv[0]);
return;
}
if (argc == 2) {
f = fopen(argv[1],"r");
if (f == NULL) {
fprintf(stderr, "Can't open %s\n", argv[1]);
return;
}
} else {
f = stdin;
}
while ((c = getc(f)) != EOF) {
if (c < 0x80) putchar(c);
else if ((c & 0xe0) == 0xc0) {
/* two-char rune */
c1 = c;
r = (c & 0x1f) << 6;
if ((c = getc(f)) == EOF) {
fprintf(stderr, "EOF in rune\n");
putchar(c1);
break;
}
if ((c & 0xc0) != 0x80) {
fprintf(stderr, "Bad rune %x, %x\n", r, c);
putchar(c1);
putchar(c);
continue;
}
r = r | (c & 0x3f);
if (r < 0x100) putchar(r);
else {
fprintf(stderr, "Rune too big %x\n", r);
putchar(c1);
putchar(c);
}
} else if ((c & 0xf0) == 0xe0) {
/* three-char rune */
r = (c & 0xf) << 12;
c1 = c;
if ((c = getc(f)) == EOF) {
fprintf(stderr, "EOF in rune\n");
putchar(c1);
break;
}
if ((c & 0xc0) != 0x80) {
fprintf(stderr, "Bad rune %x, %x\n", r, c);
putchar(c1);
putchar(c);
continue;
}
c2 = c;
r = r | ((c & 0x3f) << 6);
if ((c = getc(f)) == EOF) {
fprintf(stderr, "EOF in rune\n");
putchar(c1);
putchar(c2);
break;
}
if ((c & 0xc0) != 0x80) {
fprintf(stderr, "Bad rune %x, %x\n", r, c);
putchar(c1);
putchar(c2);
putchar(c);
continue;
}
r = r | (c & 0x3f);
if (r < 0x100) putchar(r);
else {
fprintf(stderr, "Rune too big %x\n", r);
putchar(c1);
putchar(c2);
putchar(c);
}
} else {
fprintf(stderr, "Bad rune %x, %x\n", r, c);
putchar(c);
}
}
fflush(f);
return;
}
[-- Attachment #3: latin2utf.c --]
[-- Type: text/plain, Size: 555 bytes --]
#include <stdio.h>
FILE *f;
main(int argc, char ** argv)
{ int c;
unsigned int r;
char buf[8];
if (argc > 2) {
fprintf(stderr, "Usage: %s [ file ]\n", argv[0]);
return;
}
if (argc == 2) {
f = fopen(argv[1],"r");
if (f == NULL) {
fprintf(stderr, "Can't open %s\n", argv[1]);
return;
}
} else {
f = stdin;
}
while ((c = getc(f)) != EOF) {
if (c < 0x80) putchar(c);
else {
/* print a two-char rune */
putchar(0xc0 | (c >> 6));
putchar(0x80 | (c & 0x3f));
}
}
fflush(f);
return;
}
next prev parent reply other threads:[~2005-02-01 20:41 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-01-29 13:57 Heiko Dudzus
2005-01-31 1:21 ` Kenji Okamoto
2005-01-31 14:05 ` Heiko Dudzus
2005-01-31 18:40 ` Russ Cox
2005-01-31 19:19 ` boyd, rounin
2005-02-01 8:24 ` Heiko Dudzus
2005-02-01 10:29 ` Heiko Dudzus
2005-02-01 17:11 ` Heiko Dudzus
2005-02-01 20:41 ` Sape Mullender [this message]
2005-02-01 20:45 ` boyd, rounin
2005-02-01 18:26 ` Russ Cox
2005-02-01 18:37 ` rog
2005-02-01 19:50 ` boyd, rounin
2005-02-02 10:59 ` Heiko Dudzus
2005-02-02 13:48 ` Russ Cox
2005-02-02 23:41 ` Heiko Dudzus
2005-02-01 1:42 ` Kenji Okamoto
2005-02-01 3:42 ` Russ Cox
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=a911fbfff731b0a56b03c75d36097e47@plan9.bell-labs.com \
--to=sape@plan9.bell-labs.com \
--cc=9fans@cse.psu.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).