shithub: trueawk

Info  •  Files  •  Log  •  Branches

Merge branch 'master' into improve-gototab

--- a/FIXES

+++ b/FIXES

@@ -25,6 +25,15 @@

 This file lists all bug fixes, changes, etc., made since the 

 second edition of the AWK book was published in September 2023.

+Oct 30, 2023:

+	multiple fixes and a minor code cleanup.

+	disabled utf-8 for non-multibyte locales, such as C or POSIX.

+	fixed a bad char * cast that causes incorrect results on big-endian

+	systems. also fixed an out-of-bounds read for empty CCL.

+	fixed a buffer overflow in substr with utf-8 strings.

+	many thanks to Todd C Miller.

+	

+

 Sep 24, 2023:

 	fnematch and getrune have been overhauled to solve issues around

 	unicode FS and RS. also fixed gsub null match issue with unicode.

--- a/awk.h

+++ b/awk.h

@@ -64,6 +64,8 @@

 #define	RECSIZE	(8 * 1024)	/* sets limit on records, fields, etc., etc. */

 extern int	recsize;	/* size of current record, orig RECSIZE */

+extern size_t	awk_mb_cur_max;	/* max size of a multi-byte character */

+

 extern char	EMPTY[];	/* this avoid -Wwritable-strings issues */

 extern char	**FS;

 extern char	**RS;

--- a/b.c

+++ b/b.c

@@ -530,7 +530,7 @@

 			setvec[lp] = 1;

 			setcnt++;

 		}

-		if (type(p) == CCL && (*(char *) right(p)) == '\0')

+		if (type(p) == CCL && (*(int *) right(p)) == 0)

 			return(0);		/* empty CCL */

 		return(1);

 	case PLUS:

@@ -846,7 +846,7 @@

 	c = getc(fp);

 	if (c == EOF)

 		return result;	// result.rune == 0 --> EOF

-	else if (c < 128) {

+	else if (c < 128 || awk_mb_cur_max == 1) {

 		result.bytes[0] = c;

 		result.len = 1;

 		result.rune = c;

@@ -1038,7 +1038,7 @@

 		rtok = relex();

 		if (rtok == ')') {	/* special pleading for () */

 			rtok = relex();

-			return unary(op2(CCL, NIL, (Node *) tostring("")));

+			return unary(op2(CCL, NIL, (Node *) cclenter("")));

 		}

 		np = regexp();

 		if (rtok == ')') {

@@ -1061,7 +1061,7 @@

 		return (concat(op2(CAT, np, primary())));

 	case EMPTYRE:

 		rtok = relex();

-		return (concat(op2(CAT, op2(CCL, NIL, (Node *) tostring("")),

+		return (concat(op2(CAT, op2(CCL, NIL, (Node *) cclenter("")),

 				primary())));

 	}

 	return (np);

--- a/main.c

+++ b/main.c

@@ -22,7 +22,7 @@

 THIS SOFTWARE.

 ****************************************************************/

-const char	*version = "version 20231001";

+const char	*version = "version 20231030";

 #define DEBUG

 #include <stdio.h>

@@ -53,6 +53,8 @@

 bool	safe = false;	/* true => "safe" mode */

+size_t	awk_mb_cur_max = 1;

+

 static noreturn void fpecatch(int n

 #ifdef SA_SIGINFO

 	, siginfo_t *si, void *uc

@@ -116,6 +118,7 @@

 	setlocale(LC_CTYPE, "");

 	setlocale(LC_NUMERIC, "C"); /* for parsing cmdline & prog */

+	awk_mb_cur_max = MB_CUR_MAX;

 	cmdname = argv[0];

 	if (argc == 1) {

 		fprintf(stderr,

--- a/run.c

+++ b/run.c

@@ -605,7 +605,7 @@

 	unsigned char c;

 	c = s[0];

-	if (c < 128)

+	if (c < 128 || awk_mb_cur_max == 1)

 		return 1; /* what if it's 0? */

 	n = strlen(s);

@@ -632,7 +632,7 @@

 	unsigned char c;

 	c = s[0];

-	if (c < 128) {

+	if (c < 128 || awk_mb_cur_max == 1) {

 		*rune = c;

 		return 1;

 	}

@@ -679,7 +679,7 @@

 	totlen = 0;

 	for (i = 0; i < n; i += len) {

 		c = s[i];

-		if (c < 128) {

+		if (c < 128 || awk_mb_cur_max == 1) {

 			len = 1;

 		} else {

 			len = u8_nextlen(&s[i]);

@@ -985,7 +985,7 @@

 	if (a[2] != NULL)

 		z = execute(a[2]);

 	s = getsval(x);

-	k = strlen(s) + 1;

+	k = u8_strlen(s) + 1;

 	if (k <= 1) {

 		tempfree(x);

 		tempfree(y);

@@ -1289,7 +1289,7 @@

 				int charval = (int) getfval(x);

 				if (charval != 0) {

-					if (charval < 128)

+					if (charval < 128 || awk_mb_cur_max == 1)

 						snprintf(p, BUFSZ(p), fmt, charval);

 					else {

 						// possible unicode character

@@ -1349,7 +1349,7 @@

 			int i;

 			if (ljust) { // print one char from t, then pad blanks

-				for (int i = 0; i < n; i++)

+				for (i = 0; i < n; i++)

 					*p++ = t[i];

 				for (i = 0; i < pad; i++) {

 					//printf(" ");

@@ -1360,7 +1360,7 @@

 					//printf(" ");

 					*p++ = ' ';

 				}

-				for (int i = 0; i < n; i++)

+				for (i = 0; i < n; i++)

 					*p++ = t[i];

 			}

 			*p = 0;

@@ -1977,7 +1977,7 @@

 	const char *ps = NULL;

 	size_t n       = 0;

 	wchar_t wc;

-	size_t sz = MB_CUR_MAX;

+	const size_t sz = awk_mb_cur_max;

 	int unused;

 	if (sz == 1) {

-- 

⑨