Fix whitespace in number parsing (#3195)

* Handle input errors for --indent

Handle malformed and overflowing arguments. Also, forbid leading and
trailing spaces to match the behavior of tonumber from commit ce0e788
(improve tonumber/0 performance by parsing input as number literal,
2024-03-02).

* Do not skip leading whitespace in jvp_strtod

`jvp_strtod` skips leading whitespace, but its decnum counterpart
`decNumberFromString` (called within `jv_number_with_literal`) does not.
Those two are called interchangeably, so it leads to inconsistent
behavior depending on whether the decnum feature is enabled.
Additionally, `classify`, used in the token scanner, only considers
[ \t\n\r] to be whitespace, but `jvp_strtod` consumes the larger set
[ \t\n\v\f\r], so those extra characters are considered literals.

Changing this deviates from the behavior of `strdod` from <stdlib.h> and
is technically a breaking API change, since it is a public symbol.

Author: thaliaarchi

src/jv_dtoa.c

@@ -2368,29 +2368,21 @@ jvp_strtod
 
 	sign = nz0 = nz1 = nz = bc.dplen = bc.uflchk = 0;
 	dval(&rv) = 0.;
-	for(s = s00;;s++) switch(*s) {
+	switch(*(s = s00)) {
 		case '-':
 			sign = 1;
 			/* no break */
 			JQ_FALLTHROUGH;
 		case '+':
 			if (*++s)
-				goto break2;
+				break;
 			/* no break */
 			JQ_FALLTHROUGH;
 		case 0:
 			goto ret0;
-		case '\t':
-		case '\n':
-		case '\v':
-		case '\f':
-		case '\r':
-		case ' ':
-			continue;
 		default:
-			goto break2;
+			break;
 		}
- break2:
 	if (*s == '0') {
 #ifndef NO_HEX_FP /*{*/
 		switch(s[1]) {

src/main.c

@@ -422,12 +422,15 @@ int main(int argc, char* argv[]) {
             fprintf(stderr, "jq: --indent takes one parameter\n");
             die();
           }
-          dumpopts &= ~(JV_PRINT_TAB | JV_PRINT_INDENT_FLAGS(7));
-          int indent = atoi(argv[i+1]);
-          if (indent < -1 || indent > 7) {
+          char* end = NULL;
+          errno = 0;
+          long indent = strtol(argv[i+1], &end, 10);
+          if (errno || indent < -1 || indent > 7 ||
+              isspace(*argv[i+1]) || end == argv[i+1] || *end) {
             fprintf(stderr, "jq: --indent takes a number between -1 and 7\n");
             die();
           }
+          dumpopts &= ~(JV_PRINT_TAB | JV_PRINT_INDENT_FLAGS(7));
           dumpopts |= JV_PRINT_INDENT_FLAGS(indent);
           i++;
         } else if (isoption(&text, 0, "seq", is_short)) {

tests/jq.test

@@ -2342,8 +2342,8 @@ null
 2
 
 .[] |= try tonumber
-["1", "2a", "3", " 4 ", "5.67", ".89", "-876", "+5.43", 21]
-[1, 3, 5.67, 0.89, -876, 5.43, 21]
+["1", "2a", "3", " 4", "5 ", "6.7", ".89", "-876", "+5.43", 21]
+[1, 3, 6.7, 0.89, -876, 5.43, 21]
 
 # Also 1859, but from 2073
 any(keys[]|tostring?;true)