From mboxrd@z Thu Jan  1 00:00:00 1970
From: quanstro@speakeasy.net
To: 9fans@cse.psu.edu
Message-ID: <W841833196585841125485492@webmail2>
Date: Wed, 31 Aug 2005 10:51:32 +0000
Subject: [9fans] tcs bug.
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Topicbox-Message-UUID: 81dce4c0-ead0-11e9-9d60-3106f5b1d025

i just had a similar problem a day or two ago.

i needed to change some capitalization and the 
tr 'A-Z' 'a-z' idiom doesn't work on random utf.

i solved it a bit differently -- lifting the fullrune()
check into the main loop. so i don't have a readu() 
function. also (unlike tcs) at the cost of 1 extra check 
at the end-of-input, the output buffer is dumped only 
when full. on japanese, greek or other text with 
>1 byte/char, this will save calls to OUT() --
or in my case print().

okay, total overkill. i know. but it was more interesting
to do that way. 

here's upper.c. convert to upper/lower/title case:



#include <u.h>
#include <libc.h>

enum { BLOCK = 1024*4 };

typedef Rune (*Rconv)(Rune);

void output(Rune* r, int nrunes, Rconv R){
	int i;

	for(i=0; i<nrunes; i++){
		r[i] = R(r[i]);
	}
	print("%.*S", nrunes, r);
}

const char* casify(int fd, Rconv R){
	char in[BLOCK + UTFmax];
	Rune r[BLOCK + UTFmax];
	long rem_len;
	long blen;
	long j;
	long i;

	rem_len=0;
	j = 0;
again:	while (0 < (blen = read(fd, in + rem_len, BLOCK))){
		blen += rem_len;

		for(i=0; i<blen; ){
			if (!fullrune(in + i, blen - i)){
				rem_len = blen - i;
				memcpy(in, in + i, rem_len);
				goto again;
			}
			i += chartorune(r + j++, in + i);
			if (j > BLOCK){
				output(r, j, R);
				j=0;
			}
		}
	}

	if (rem_len){
		// non unicode garbage.
		fprint(2, "non-utf8 garbage %.*s at eof\n", rem_len, in);
	}

	if (j){
		output(r, j, R);
	}

	if (blen>0){
		return 0;
	}
	return "read";
}

void main(int argc, /* pfft const */ char** argv){
	Rconv R;
	const char* v;
	const char* status;
	const char* s;
	int fd;

	v = strrchr(argv[0], '/');
	if (v){
		v++;
	} else {
		v = argv[0];
	}
	
	if (0 == strcmp(v, "tolower")){
		R = tolowerrune;
	} else if (0 == strcmp(v, "totitle")){
		R = totitlerune;
	} else {
		R = toupperrune;
	}

	ARGBEGIN{
	case 'u':
		R = toupperrune;
		break;
	case 'l':
		R = tolowerrune;
		break;
	case 't':
		R = totitlerune;
		break;
	default:
		fprint(2, "%s: bad option %c\n", argv0, ARGC());
		fprint(2, "usage: %s -[ult]\n", argv0);
		exits("usage");
	} ARGEND

	if (!*argv){
		s = casify(0, R);
	} else {
		for(status = 0; *argv; argv++){
			fd = open(*argv, OREAD);
			if (-1 == fd){
				if (s && !status){
					status = "open";
				}
				continue;
			}
			s = casify(fd, R);
			if (s && !status){
				status = s;
			}
			close(fd);
		}
	}

	exits(status ? status : "");
}