git: 9front

Info  •  Files  •  Log  •  Branches

awk: make tolower and toupper builtins unicode-aware

--- a/sys/src/cmd/awk/run.c

+++ b/sys/src/cmd/awk/run.c

@@ -1538,13 +1538,14 @@

 {

 	Cell *x, *y;

 	Awkfloat u, tmp;

-	int t;

+	int n, t;

 	Rune wc;

-	char *p, *buf;

+	char *p, *s, *buf, *rbuf;

 	char mbc[50];

 	Node *nextarg;

 	Biobuf *fp;

 	void flush_all(void);

+	Rune (*conv)(Rune);

 	t = ptoi(a[0]);

 	x = execute(a[1]);

@@ -1600,21 +1601,22 @@

 		break;

 	case FTOUPPER:

 	case FTOLOWER:

-		buf = tostring(getsval(x));

-		if (t == FTOUPPER) {

-			for (p = buf; *p; p++)

-				if (islower(*p))

-					*p = toupper(*p);

-		} else {

-			for (p = buf; *p; p++)

-				if (isupper(*p))

-					*p = tolower(*p);

+		buf = getsval(x);

+		n = utflen(buf) * UTFmax + 1;	/* just in case size differs... */

+		if ((rbuf = malloc(n)) == nil)

+			FATAL("out of space in %s", t == FTOUPPER ? "toupper" : "tolower");

+		conv = t == FTOUPPER ? toupperrune : tolowerrune;

+		for (p = rbuf, s = buf; *s != '\0';) {

+			s += chartorune(&wc, s);

+			wc = conv(wc);

+			p += runetochar(p, &wc);

 		}

+		*p = 0;

 		if (istemp(x))

 			tfree(x);

 		x = gettemp();

-		setsval(x, buf);

-		free(buf);

+		setsval(x, rbuf);

+		free(rbuf);

 		return x;

 	case FFLUSH:

 		if (isrec(x) || strlen(getsval(x)) == 0) {

-- 

⑨