问题
Examples:
"Something %d" and "Something else %d" // Compatible
"Something %d" and "Something else %f" // Not Compatible
"Something %d" and "Something %d else %d" // Not Compatible
"Something %d and %f" and "Something %2$f and %1$d" // Compatible
I figured there should be some C function for this, but I'm not getting any relevant search results. I mean the compiler is checking that the format string and the arguments match, so the code for checking this is already written. The only question is how I can call it.
I'm using Objective-C, so if there is an Objective-C specific solution that's fine too.
回答1:
Checking if 2 printf() format strings are compatible is an exercise in format parsing.
C, at least, has no standard run-time compare function such as:
int format_cmp(const char *f1, const char *f2); // Does not exist
Formats like "%d %f" and "%i %e" are obviously compatible in that both expect an int and float/double. Note: float are promoted to double as short and signed char are promoted to int.
Formats "%*.*f" and "%i %d %e" are compatible, but not obvious: both expect an int,int and float/double.
Formats "%hhd" and "%d" both expect an int, even though the first will have it values cast to signed char before printing.
Formats "%d" and "%u" are not compatible. Even though many systems will behaved as hoped. Note: Typically char will promote to int.
Formats "%d" and "%ld" are not strictly compatible. On a 32-bit system there are equivalent, but not in general. Of course code can be altered to accommodate this. OTOH "%lf" and "%f" are compatible due to the usual argument promotions of float to double.
Formats "%lu" and "zu" may be compatible, but that depends on the implementation of unsigned long and size_t. Additions to code could allow this or related equivalences.
Some combinations of modifiers and specifiers are not defined like "zp". The following does not dis-allow such esoteric combinations - but does compare them.
Modifiers like "$" are extensions to standard C and are not implemented in the following.
The compatibility test for printf() differs from scanf().
#include <ctype.h>
#include <limits.h>
#include <stdio.h>
#include <string.h>
typedef enum {
type_none,
type_int,
type_unsigned,
type_float,
type_charpointer,
type_voidpointer,
type_intpointer,
type_unknown,
type_type_N = 0xFFFFFF
} type_type;
typedef struct {
const char *format;
int int_queue;
type_type type;
} format_T;
static void format_init(format_T *state, const char *format);
static type_type format_get(format_T *state);
static void format_next(format_T *state);
void format_init(format_T *state, const char *format) {
state->format = format;
state->int_queue = 0;
state->type = type_none;
format_next(state);
}
type_type format_get(format_T *state) {
if (state->int_queue > 0) {
return type_int;
}
return state->type;
}
const char *seek_flag(const char *format) {
while (strchr("-+ #0", *format) != NULL)
format++;
return format;
}
const char *seek_width(const char *format, int *int_queue) {
*int_queue = 0;
if (*format == '*') {
format++;
(*int_queue)++;
} else {
while (isdigit((unsigned char ) *format))
format++;
}
if (*format == '.') {
if (*format == '*') {
format++;
(*int_queue)++;
} else {
while (isdigit((unsigned char ) *format))
format++;
}
}
return format;
}
const char *seek_mod(const char *format, int *mod) {
*mod = 0;
if (format[0] == 'h' && format[1] == 'h') {
format += 2;
} else if (format[0] == 'l' && format[1] == 'l') {
*mod = ('l' << CHAR_BIT) + 'l';
format += 2;
} else if (strchr("ljztL", *format)) {
*mod = *format;
format++;
} else if (strchr("h", *format)) {
format++;
}
return format;
}
const char *seek_specifier(const char *format, int mod, type_type *type) {
if (strchr("di", *format)) {
*type = type_int;
format++;
} else if (strchr("ouxX", *format)) {
*type = type_unsigned;
format++;
} else if (strchr("fFeEgGaA", *format)) {
if (mod == 'l') mod = 0;
*type = type_float;
format++;
} else if (strchr("c", *format)) {
*type = type_int;
format++;
} else if (strchr("s", *format)) {
*type = type_charpointer;
format++;
} else if (strchr("p", *format)) {
*type = type_voidpointer;
format++;
} else if (strchr("n", *format)) {
*type = type_intpointer;
format++;
} else {
*type = type_unknown;
exit(1);
}
*type |= mod << CHAR_BIT; // Bring in modifier
return format;
}
void format_next(format_T *state) {
if (state->int_queue > 0) {
state->int_queue--;
return;
}
while (*state->format) {
if (state->format[0] == '%') {
state->format++;
if (state->format[0] == '%') {
state->format++;
continue;
}
state->format = seek_flag(state->format);
state->format = seek_width(state->format, &state->int_queue);
int mod;
state->format = seek_mod(state->format, &mod);
state->format = seek_specifier(state->format, mod, &state->type);
return;
} else {
state->format++;
}
}
state->type = type_none;
}
// 0 Compatible
// 1 Not Compatible
// 2 Not Comparable
int format_cmp(const char *f1, const char *f2) {
format_T state1;
format_init(&state1, f1);
format_T state2;
format_init(&state2, f2);
while (format_get(&state1) == format_get(&state2)) {
if (format_get(&state1) == type_none)
return 0;
if (format_get(&state1) == type_unknown)
return 2;
format_next(&state1);
format_next(&state2);
}
if (format_get(&state1) == type_unknown)
return 2;
if (format_get(&state2) == type_unknown)
return 2;
return 1;
}
Note: only minimal testing done. Lots of additional considerations could be added.
Known shortcomings: hh,h,l,ll,j,z,t modifiers with n. l with s,c.
[Edit]
OP comments about security concerns. This changes the nature of the post and the compare from an equality one to a security one. I'd imagine that one of the patterns (A) would be a reference pattern and the next (B) would be the test. The test would be "is B at least as secure as A?". Example A = "%.20s" and B1 = "%.19s", B2 = "%.20s", B3 = "%.21s". B1 and B2 both pass the security test as they do not extract more the 20 char. B3 is a problem as it goes pass the reference limit of 20 char. Further any non-width qualified with %s %[ %c is a security problem - in the reference or test pattern. This answer's code does not address this issue.
As mentioned, code does not yet handle modifiers with "%n".
[2018 edit]
Concerning "Formats "%d" and "%u" are not compatible.": This is for values to be printed in general. For values in the [0..INT_MAX] range, either format may work per C11dr §6.5.2.2 6.
回答2:
My understanding of what you want, is that, you basically want a method which can look at two strings and detect if they both have the same types of values in them. Or something a long those lines.... If so, then try this (or something along the lines of this):
-(int)checkCompatible:(NSString *)string_1 :(NSString *)string_2 {
// Separate the string into single elements.
NSArray *stringArray_1 = [string_1 componentsSeparatedByString:@" "];
NSArray *stringArray_2 = [string_2 componentsSeparatedByString:@" "];
// Store only the numbers for comparison in a new array.
NSMutableArray *numbers_1 = [[NSMutableArray alloc] init];
NSMutableArray *numbers_2 = [[NSMutableArray alloc] init];
// Make sure the for loop below, runs for the appropriate
// number of cycles depending on which array is bigger.
int loopMax = 0;
if ([stringArray_1 count] > [stringArray_2 count]) {
loopMax = (int)[stringArray_1 count];
}
else {
loopMax = (int)[stringArray_2 count];
}
// Now go through the stringArray's and store only the
// numbers in the mutable array's. This will be used
// during the comparison stage.
for (int loop = 0; loop < loopMax; loop++) {
NSCharacterSet *notDigits = [[NSCharacterSet decimalDigitCharacterSet] invertedSet];
if (loop < [stringArray_1 count]) {
if ([[stringArray_1 objectAtindex:loop] rangeOfCharacterFromSet:notDigits].location == NSNotFound) {
// String consists only of the digits 0 through 9.
[numbers_1 addObject:[stringArray_1 objectAtindex:loop]];
}
}
if (loop < [stringArray_2 count]) {
if ([[stringArray_2 objectAtindex:loop] rangeOfCharacterFromSet:notDigits].location == NSNotFound) {
// String consists only of the digits 0 through 9.
[numbers_2 addObject:[stringArray_2 objectAtindex:loop]];
}
}
}
// Now look through the mutable array's
// and perform the type comparison,.
if ([numbers_1 count] != [numbers_2 count]) {
// One of the two strings has more numbers
// than the other, so they are NOT compatible.
return 1;
}
else {
// Both string have the same number of numbers
// numbers so lets go through them to make
// sure the numbers are of the same type.
for (int loop = 0; loop < [numbers_1 count]; loop++) {
// Check to see if the number in the current array index
// is a float or an integer. All the numbers in the array have
// to be the SAME type, in order for the strings to be compatible.
BOOL check_float_1 = [[NSScanner scannerWithString:[numbers_1 objectAtindex:loop]] scanFloat:nil];
BOOL check_int_1 = [[NSScanner scannerWithString:[numbers_1 objectAtindex:loop]] scanInt:nil];
BOOL check_float_2 = [[NSScanner scannerWithString:[numbers_2 objectAtindex:loop]] scanFloat:nil];
BOOL check_int_2 = [[NSScanner scannerWithString:[numbers_2 objectAtindex:loop]] scanInt:nil];
if (check_float_1 == YES) {
if (check_float_2 == NO) {
return 1;
}
}
else if (check_int_1 == YES) {
if (check_int_2 == NO) {
return 1;
}
}
else {
// Error of some sort......
return 1;
}
}
// All the numbers in the strings are of the same
// type (otherwise we would NOT have reached
// this point). Therefore the strings are compatible.
return 0;
}
}
来源：https://stackoverflow.com/questions/28947528/how-to-check-that-two-format-strings-are-compatible