Merge branch 'master' into comment

1 files changed, 98 insertions, 19 deletions

diff --git a/builtin.c b/builtin.c
index 875b3e5c..6f8aeb36 100644
--- a/builtin.c
+++ b/builtin.c
@@ -1112,7 +1112,7 @@ out0:
 
 				memset(& state, 0, sizeof(state));
 				count = mbrlen(cp, arg->stlen, & state);
-				if (count > 0) {
+				if (count != (size_t) -1 && count != (size_t) -2 && count > 0) {
 					prec = count;
 					/* may need to increase fw so that padding happens, see pr_tail code */
 					if (fw > 0)
@@ -2454,8 +2454,14 @@ do_rand(int nargs ATTRIBUTE_UNUSED)
  	 */
  
 	do {
-	 	tmprand = 0.5 + ( (random()/RAND_DIVISOR + random())
-					/ RAND_DIVISOR);
+		long d1, d2;
+		/*
+		 * Do the calls in predictable order to avoid
+		 * compiler differences in order of evaluation.
+		 */
+		d1 = random();
+		d2 = random();
+	 	tmprand = 0.5 + ( (d1/RAND_DIVISOR + d2) / RAND_DIVISOR );
 		tmprand -= 0.5;
 	} while (tmprand == 1.0);
 
@@ -2702,23 +2708,28 @@ do_match(int nargs)
  * 2001 standard:
  * 
  * sub(ere, repl[, in ])
- *  Substitute the string repl in place of the first instance of the extended regular
- *  expression ERE in string in and return the number of substitutions. An ampersand
- *  ('&') appearing in the string repl shall be replaced by the string from in that
- *  matches the ERE. An ampersand preceded with a backslash ('\') shall be
- *  interpreted as the literal ampersand character. An occurrence of two consecutive
- *  backslashes shall be interpreted as just a single literal backslash character. Any
- *  other occurrence of a backslash (for example, preceding any other character) shall
- *  be treated as a literal backslash character. Note that if repl is a string literal (the
- *  lexical token STRING; see Grammar (on page 170)), the handling of the
- *  ampersand character occurs after any lexical processing, including any lexical
- *  backslash escape sequence processing. If in is specified and it is not an lvalue (see
- *  Expressions in awk (on page 156)), the behavior is undefined. If in is omitted, awk
- *  shall use the current record ($0) in its place.
+ *  Substitute the string repl in place of the first instance of the
+ *  extended regular expression ERE in string in and return the number of
+ *  substitutions. An ampersand ('&') appearing in the string repl shall
+ *  be replaced by the string from in that matches the ERE. An ampersand
+ *  preceded with a backslash ('\') shall be interpreted as the literal
+ *  ampersand character. An occurrence of two consecutive backslashes shall
+ *  be interpreted as just a single literal backslash character. Any other
+ *  occurrence of a backslash (for example, preceding any other character)
+ *  shall be treated as a literal backslash character. Note that if repl is a
+ *  string literal (the lexical token STRING; see Grammar (on page 170)), the
+ *  handling of the ampersand character occurs after any lexical processing,
+ *  including any lexical backslash escape sequence processing. If in is
+ *  specified and it is not an lvalue (see Expressions in awk (on page 156)),
+ *  the behavior is undefined. If in is omitted, awk shall use the current
+ *  record ($0) in its place.
+ *
+ * 11/2010: The text in the 2008 standard is the same as just quoted.
+ * However, POSIX behavior is now the default.  This can change the behavior
+ * of awk programs.  The old behavior is not available.
  *
- * 11/2010: The text in the 2008 standard is the same as just quoted.  However, POSIX behavior
- * is now the default.  This can change the behavior of awk programs.  The old behavior
- * is not available.
+ * 7/2011: Reverted backslash handling to what it used to be. It was in
+ * gawk for too long. Should have known better.
  */
 
 /*
@@ -2829,9 +2840,11 @@ set_how_many:
 	repl = s->stptr;
 	replend = repl + s->stlen;
 	repllen = replend - repl;
+
 	emalloc(buf, char *, buflen + 2, "do_sub");
 	buf[buflen] = '\0';
 	buf[buflen + 1] = '\0';
+
 	ampersands = 0;
 
 	/*
@@ -3599,6 +3612,72 @@ do_bindtextdomain(int nargs)
 	return make_string(the_result, strlen(the_result));
 }
 
+/* do_div --- do integer division, return quotient and remainder in dest array */
+
+/*
+ * We define the semantics as:
+ * 	numerator = int(numerator)
+ *	denominator = int(denonmator)
+ *	quotient = int(numerator / denomator)
+ *	remainder = int(numerator % denomator)
+ */
+
+NODE *
+do_div(int nargs)
+{
+	NODE *numerator, *denominator, *result;
+	double num, denom, quotient, remainder;
+	NODE *sub, **lhs;
+
+	result = POP_PARAM();
+	if (result->type != Node_var_array)
+		fatal(_("div: third argument is not an array"));
+	assoc_clear(result);
+
+	denominator = POP_SCALAR();
+	numerator = POP_SCALAR();
+
+	if (do_lint) {
+		if ((numerator->flags & (NUMCUR|NUMBER)) == 0)
+			lintwarn(_("div: received non-numeric first argument"));
+		if ((denominator->flags & (NUMCUR|NUMBER)) == 0)
+			lintwarn(_("div: received non-numeric second argument"));
+	}
+
+	(void) force_number(numerator);
+	(void) force_number(denominator);
+	num = double_to_int(get_number_d(numerator));
+	denom = double_to_int(get_number_d(denominator));
+
+	if (denom == 0.0)
+		fatal(_("div: division by zero attempted"));
+
+	quotient = double_to_int(num / denom);
+	/*
+	 * FIXME: This code is duplicated, factor it out to a
+	 * separate function.
+	 */
+#ifdef HAVE_FMOD
+	remainder = fmod(num, denom);
+#else	/* ! HAVE_FMOD */
+	(void) modf(num / denom, & remainder);
+	remainder = num - remainder * denom;
+#endif	/* ! HAVE_FMOD */
+	remainder = double_to_int(remainder);
+
+	sub = make_string("quotient", 8);
+	lhs = assoc_lookup(result, sub);
+	unref(*lhs);
+	*lhs = make_number((AWKNUM) quotient);
+
+	sub = make_string("remainder", 9);
+	lhs = assoc_lookup(result, sub);
+	unref(*lhs);
+	*lhs = make_number((AWKNUM) remainder);
+
+	return make_number((AWKNUM) 0.0);
+}
+
 
 /* mbc_byte_count --- return number of bytes for corresponding numchars multibyte characters */