From mboxrd@z Thu Jan  1 00:00:00 1970
Message-ID: <a911fbfff731b0a56b03c75d36097e47@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
From: Sape Mullender <sape@plan9.bell-labs.com>
In-Reply-To: <5d1294dbc2ec360ffbcdcc8fd86e829f@voidness.de>
MIME-Version: 1.0
Content-Type: multipart/mixed;
	boundary="upas-rnqcmfrnbcfovfvtkaogtwfuxx"
Topicbox-Message-UUID: fed69936-eacf-11e9-9d60-3106f5b1d025

This is a multi-part message in MIME format.
--upas-rnqcmfrnbcfovfvtkaogtwfuxx
Content-Disposition: inline
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

This might help to change you umlauts into real ones :-)

	Sape

--upas-rnqcmfrnbcfovfvtkaogtwfuxx
Content-Disposition: attachment; filename=utf2latin.c
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

#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;
}
--upas-rnqcmfrnbcfovfvtkaogtwfuxx
Content-Disposition: attachment; filename=latin2utf.c
Content-Type: text/plain; charset="US-ASCII"
Content-Transfer-Encoding: 7bit

#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;
}
--upas-rnqcmfrnbcfovfvtkaogtwfuxx--