How can I compare strings in C using a `switch` statement?
In C there is a switch construct which enables one to execute different conditional branches of code based on an test integer value, e.g.,
int a;
/* Read the value of "a" from some source, e.g. user input */
swi开发者_StackOverflowtch (a) {
case 100:
// Code
break;
case 200:
// Code
break;
default:
// Code
break;
}
How is it possible to obtain the same behavior (i.e. avoid the so-called "if-else ladder") for a string value, i.e., a char *?
If you mean, how to write something similar to this:
// switch statement
switch (string) {
case "B1":
// do something
break;
/* more case "xxx" parts */
}
Then the canonical solution in C is to use an if-else ladder:
if (strcmp(string, "B1") == 0)
{
// do something
}
else if (strcmp(string, "xxx") == 0)
{
// do something else
}
/* more else if clauses */
else /* default: */
{
}
If you have many cases and do not want to write a ton of strcmp() calls, you could do something like:
switch(my_hash_function(the_string)) {
case HASH_B1: ...
/* ...etc... */
}
You just have to make sure your hash function has no collisions inside the set of possible values for the string.
There is no way to do this in C. There are a lot of different approaches. Typically the simplest is to define a set of constants that represent your strings and do a look up by string on to get the constant:
#define BADKEY -1
#define A1 1
#define A2 2
#define B1 3
#define B2 4
typedef struct { char *key; int val; } t_symstruct;
static t_symstruct lookuptable[] = {
{ "A1", A1 }, { "A2", A2 }, { "B1", B1 }, { "B2", B2 }
};
#define NKEYS (sizeof(lookuptable)/sizeof(t_symstruct))
int keyfromstring(char *key)
{
int i;
for (i=0; i < NKEYS; i++) {
t_symstruct *sym = lookuptable[i];
if (strcmp(sym->key, key) == 0)
return sym->val;
}
return BADKEY;
}
/* ... */
switch (keyfromstring(somestring)) {
case A1: /* ... */ break;
case A2: /* ... */ break;
case B1: /* ... */ break;
case B2: /* ... */ break;
case BADKEY: /* handle failed lookup */
}
There are, of course, more efficient ways to do this. If you keep your keys sorted, you can use a binary search. You could use a hashtable too. These things change your performance at the expense of maintenance.
My preferred method for doing this is via a hash function (borrowed from here). This allows you to utilize the efficiency of a switch statement even when working with char *'s:
#include "stdio.h"
#define LS 5863588
#define CD 5863276
#define MKDIR 210720772860
#define PWD 193502992
const unsigned long hash(const char *str) {
unsigned long hash = 5381;
int c;
while ((c = *str++))
hash = ((hash << 5) + hash) + c;
return hash;
}
int main(int argc, char *argv[]) {
char *p_command = argv[1];
switch(hash(p_command)) {
case LS:
printf("Running ls...\n");
break;
case CD:
printf("Running cd...\n");
break;
case MKDIR:
printf("Running mkdir...\n");
break;
case PWD:
printf("Running pwd...\n");
break;
default:
printf("[ERROR] '%s' is not a valid command.\n", p_command);
}
}
Of course, this approach requires that the hash values for all possible accepted char *'s are calculated in advance. I don't think this is too much of an issue; however, since the switch statement operates on fixed values regardless. A simple program can be made to pass char *'s through the hash function and output their results. These results can then be defined via macros as I have done above.
I think the best way to do this is separate the 'recognition' from the functionality:
struct stringcase { char* string; void (*func)(void); };
void funcB1();
void funcAzA();
stringcase cases [] =
{ { "B1", funcB1 }
, { "AzA", funcAzA }
};
void myswitch( char* token ) {
for( stringcases* pCase = cases
; pCase != cases + sizeof( cases ) / sizeof( cases[0] )
; pCase++ )
{
if( 0 == strcmp( pCase->string, token ) ) {
(*pCase->func)();
break;
}
}
}
I have published a header file to perform the switch on the strings in C. It contains a set of macro that hide the call to the strcmp() (or similar) in order to mimic a switch-like behaviour. I have tested it only with GCC in Linux, but I'm quite sure that it can be adapted to support other environment.
EDIT: added the code here, as requested
This is the header file you should include:
#ifndef __SWITCHS_H__
#define __SWITCHS_H__
#include <string.h>
#include <regex.h>
#include <stdbool.h>
/** Begin a switch for the string x */
#define switchs(x) \
{ char *ss__sw = (x); bool ss__done = false; bool ss__cont = false; \
regex_t ss__regex; regcomp(&ss__regex, ".*", 0); do {
/** Check if the string matches the cases argument (case sensitive) */
#define cases(x) } if ( ss__cont || !strcmp ( ss__sw, x ) ) \
{ ss__done = true; ss__cont = true;
/** Check if the string matches the icases argument (case insensitive) */
#define icases(x) } if ( ss__cont || !strcasecmp ( ss__sw, x ) ) { \
ss__done = true; ss__cont = true;
/** Check if the string matches the specified regular expression using regcomp(3) */
#define cases_re(x,flags) } regfree ( &ss__regex ); if ( ss__cont || ( \
0 == regcomp ( &ss__regex, x, flags ) && \
0 == regexec ( &ss__regex, ss__sw, 0, NULL, 0 ) ) ) { \
ss__done = true; ss__cont = true;
/** Default behaviour */
#define defaults } if ( !ss__done || ss__cont ) {
/** Close the switchs */
#define switchs_end } while ( 0 ); regfree(&ss__regex); }
#endif // __SWITCHS_H__
And this is how you use it:
switchs(argv[1]) {
cases("foo")
cases("bar")
printf("foo or bar (case sensitive)\n");
break;
icases("pi")
printf("pi or Pi or pI or PI (case insensitive)\n");
break;
cases_re("^D.*",0)
printf("Something that start with D (case sensitive)\n");
break;
cases_re("^E.*",REG_ICASE)
printf("Something that start with E (case insensitive)\n");
break;
cases("1")
printf("1\n");
// break omitted on purpose
cases("2")
printf("2 (or 1)\n");
break;
defaults
printf("No match\n");
break;
} switchs_end;
Please notice that there is no colon (':') after each case nor after the defaults.
There is a way to perform the string search faster. Assumptions: since we are talking about a switch statement, I can assume that the values won't be changing during runtime.
The idea is to use the C stdlib's qsort and bsearch.
I'll be working on xtofl's code.
struct stringcase { char* string; void (*func)(void); };
void funcB1();
void funcAzA();
struct stringcase cases [] =
{ { "B1", funcB1 }
, { "AzA", funcAzA }
};
struct stringcase work_cases* = NULL;
int work_cases_cnt = 0;
// prepare the data for searching
void prepare() {
// allocate the work_cases and copy cases values from it to work_cases
qsort( cases, i, sizeof( struct stringcase ), stringcase_cmp );
}
// comparator function
int stringcase_cmp( const void *p1, const void *p2 )
{
return strcasecmp( ((struct stringcase*)p1)->string, ((struct stringcase*)p2)->string);
}
// perform the switching
void myswitch( char* token ) {
struct stringcase val;
val.string=token;
void* strptr = bsearch( &val, work_cases, work_cases_cnt, sizeof( struct stringcase), stringcase_cmp );
if (strptr) {
struct stringcase* foundVal = (struct stringcase*)strptr;
(*foundVal->func)();
return OK;
}
return NOT_FOUND;
}
To add to Phimueme's answer above, if your string is always two characters, then you can build a 16-bit int out of the two 8-bit characters - and switch on that (to avoid nested switch/case statements).
We cannot escape if-else ladder in order to compare a string with others. Even regular switch-case is also an if-else ladder (for integers) internally. We might only want to simulate the switch-case for string, but can never replace if-else ladder. The best of the algorithms for string comparison cannot escape from using strcmp function. Means to compare character by character until an unmatch is found. So using if-else ladder and strcmp are inevitable.
DEMO
And here are simplest macros to simulate the switch-case for strings.
#ifndef SWITCH_CASE_INIT
#define SWITCH_CASE_INIT
#define SWITCH(X) for (char* __switch_p__ = X, int __switch_next__=1 ; __switch_p__ ; __switch_p__=0, __switch_next__=1) { {
#define CASE(X) } if (!__switch_next__ || !(__switch_next__ = strcmp(__switch_p__, X))) {
#define DEFAULT } {
#define END }}
#endif
And you can use them as
char* str = "def";
SWITCH (str)
CASE ("abc")
printf ("in abc\n");
break;
CASE ("def") // Notice: 'break;' statement missing so the control rolls through subsequent CASE's until DEFAULT
printf("in def\n");
CASE ("ghi")
printf ("in ghi\n");
DEFAULT
printf("in DEFAULT\n");
END
Output:
in def
in ghi
in DEFAULT
Below is nested SWITCH usage:
char* str = "def";
char* str1 = "xyz";
SWITCH (str)
CASE ("abc")
printf ("in abc\n");
break;
CASE ("def")
printf("in def\n");
SWITCH (str1) // <== Notice: Nested SWITCH
CASE ("uvw")
printf("in def => uvw\n");
break;
CASE ("xyz")
printf("in def => xyz\n");
break;
DEFAULT
printf("in def => DEFAULT\n");
END
CASE ("ghi")
printf ("in ghi\n");
DEFAULT
printf("in DEFAULT\n");
END
Output:
in def
in def => xyz
in ghi
in DEFAULT
Here is reverse string SWITCH, where in you can use a variable (rather than a constant) in CASE clause:
char* str2 = "def";
char* str3 = "ghi";
SWITCH ("ghi") // <== Notice: Use of variables and reverse string SWITCH.
CASE (str1)
printf ("in str1\n");
break;
CASE (str2)
printf ("in str2\n");
break;
CASE (str3)
printf ("in str3\n");
break;
DEFAULT
printf("in DEFAULT\n");
END
Output:
in str3
If it is a 2 byte string you can do something like in this concrete example where I switch on ISO639-2 language codes.
LANIDX_TYPE LanCodeToIdx(const char* Lan)
{
if(Lan)
switch(Lan[0]) {
case 'A': switch(Lan[1]) {
case 'N': return LANIDX_AN;
case 'R': return LANIDX_AR;
}
break;
case 'B': switch(Lan[1]) {
case 'E': return LANIDX_BE;
case 'G': return LANIDX_BG;
case 'N': return LANIDX_BN;
case 'R': return LANIDX_BR;
case 'S': return LANIDX_BS;
}
break;
case 'C': switch(Lan[1]) {
case 'A': return LANIDX_CA;
case 'C': return LANIDX_CO;
case 'S': return LANIDX_CS;
case 'Y': return LANIDX_CY;
}
break;
case 'D': switch(Lan[1]) {
case 'A': return LANIDX_DA;
case 'E': return LANIDX_DE;
}
break;
case 'E': switch(Lan[1]) {
case 'L': return LANIDX_EL;
case 'N': return LANIDX_EN;
case 'O': return LANIDX_EO;
case 'S': return LANIDX_ES;
case 'T': return LANIDX_ET;
case 'U': return LANIDX_EU;
}
break;
case 'F': switch(Lan[1]) {
case 'A': return LANIDX_FA;
case 'I': return LANIDX_FI;
case 'O': return LANIDX_FO;
case 'R': return LANIDX_FR;
case 'Y': return LANIDX_FY;
}
break;
case 'G': switch(Lan[1]) {
case 'A': return LANIDX_GA;
case 'D': return LANIDX_GD;
case 'L': return LANIDX_GL;
case 'V': return LANIDX_GV;
}
break;
case 'H': switch(Lan[1]) {
case 'E': return LANIDX_HE;
case 'I': return LANIDX_HI;
case 'R': return LANIDX_HR;
case 'U': return LANIDX_HU;
}
break;
case 'I': switch(Lan[1]) {
case 'S': return LANIDX_IS;
case 'T': return LANIDX_IT;
}
break;
case 'J': switch(Lan[1]) {
case 'A': return LANIDX_JA;
}
break;
case 'K': switch(Lan[1]) {
case 'O': return LANIDX_KO;
}
break;
case 'L': switch(Lan[1]) {
case 'A': return LANIDX_LA;
case 'B': return LANIDX_LB;
case 'I': return LANIDX_LI;
case 'T': return LANIDX_LT;
case 'V': return LANIDX_LV;
}
break;
case 'M': switch(Lan[1]) {
case 'K': return LANIDX_MK;
case 'T': return LANIDX_MT;
}
break;
case 'N': switch(Lan[1]) {
case 'L': return LANIDX_NL;
case 'O': return LANIDX_NO;
}
break;
case 'O': switch(Lan[1]) {
case 'C': return LANIDX_OC;
}
break;
case 'P': switch(Lan[1]) {
case 'L': return LANIDX_PL;
case 'T': return LANIDX_PT;
}
break;
case 'R': switch(Lan[1]) {
case 'M': return LANIDX_RM;
case 'O': return LANIDX_RO;
case 'U': return LANIDX_RU;
}
break;
case 'S': switch(Lan[1]) {
case 'C': return LANIDX_SC;
case 'K': return LANIDX_SK;
case 'L': return LANIDX_SL;
case 'Q': return LANIDX_SQ;
case 'R': return LANIDX_SR;
case 'V': return LANIDX_SV;
case 'W': return LANIDX_SW;
}
break;
case 'T': switch(Lan[1]) {
case 'R': return LANIDX_TR;
}
break;
case 'U': switch(Lan[1]) {
case 'K': return LANIDX_UK;
case 'N': return LANIDX_UN;
}
break;
case 'W': switch(Lan[1]) {
case 'A': return LANIDX_WA;
}
break;
case 'Z': switch(Lan[1]) {
case 'H': return LANIDX_ZH;
}
break;
}
return LANIDX_UNDEFINED;
}
LANIDX_* being constant integers used to index in arrays.
This is generally how I do it.
void order_plane(const char *p)
{
switch ((*p) * 256 + *(p+1))
{
case 0x4231 : /* B1 */
{
printf("Yes, order this bomber. It's a blast.\n");
break;
}
case 0x5354 : /* ST */
{
printf("Nah. I just can't see this one.\n");
break;
}
default :
{
printf("Not today. Can I interest you in a crate of SAMs?\n";
}
}
}
Assuming little endianness and sizeof(char) == 1, you could do that (something like this was suggested by MikeBrom).
char* txt = "B1";
int tst = *(int*)txt;
if ((tst & 0x00FFFFFF) == '1B')
printf("B1!\n");
It could be generalized for BE case.
This is how you do it. No, not really.
#include <stdio.h>
#include <string.h>
#include <assert.h>
#include <stdint.h>
#define p_ntohl(u) ({const uint32_t Q=0xFF000000; \
uint32_t S=(uint32_t)(u); \
(*(uint8_t*)&Q)?S: \
( (S<<24)| \
((S<<8)&0x00FF0000)| \
((S>>8)&0x0000FF00)| \
((S>>24)&0xFF) ); })
main (void)
{
uint32_t s[0x40];
assert((unsigned char)1 == (unsigned char)(257));
memset(s, 0, sizeof(s));
fgets((char*)s, sizeof(s), stdin);
switch (p_ntohl(s[0])) {
case 'open':
case 'read':
case 'seek':
puts("ok");
break;
case 'rm\n\0':
puts("not authorized");
break;
default:
puts("unrecognized command");
}
return 0;
}
Macro relies on a compiler extension else you may receive
warning: ISO C forbids braced-groups within expressions
'open' is a multi-character character constant and its value is implementation dependent.
Function pointers are a great way to do this, e.g.
result = switchFunction(someStringKey); //result is an optional return value
...this calls a function that you have set by string key (one function per case):
setSwitchFunction("foo", fooFunc);
setSwitchFunction("bar", barFunc);
Use a pre-existing hashmap/table/dictionary implementation such as khash, return that pointer to a function inside of switchFunction(), and execute it (or just return it from switchFunction() and execute it yourself). If the map implementation doesn't store that, just use a uint64_t instead that you cast accordingly to a pointer.
Comparing using an if () else if () chain is a linear search, offering O(n) time complexity. For a large number of strings, one option is using bsearch() (binary search) to achieve O(log n) time complexity. Below is an example of my use of bsearch to perform a given action based on an input string. (Specifically, my example finds a given mathematical function by name).
static int c(const void *const restrict a, const void *const restrict b) {
return strcmp(*(const char *const *)a, *(const char *const *)b);
}
static double (*func(const char *const str))(double) {
static const char *const s[] = {"abs", "acos", "acosh", "asin", "asinh", "atan", "atanh", "cbrt", "cos", "cosh", "ln", "log", "sin", "sinh", "sqrt", "tan", "tanh"};
static double (*const f[])(double) = {fabs, acos, acosh, asin, asinh, atan, atanh, cbrt, cos, cosh, log, log10, sin, sinh, sqrt, tan, tanh};
const char *const *const r = bsearch(&str, s, sizeof(s)/sizeof(*s), sizeof(*s), c);
return r ? f[r-s] : NULL;
}
Hi this is the easy and fast way if you have this case :
[QUICK Mode]
int concated;
char ABC[4]="";int a=1,b=4,c=2; //char[] Initializing
ABC<-sprintf(ABC,"%d%d%d",a,b,c); //without space between %d%d%d
printf("%s",ABC); //value as char[] is =142
concated=atoi(ABC); //result is 142 as int, not 1,4,2 (separeted)
//now use switch case on 142 as an integer and all possible cases
[EXPLAINED Mode]
for example : i have many menus, each choice on the 1st menu takes u to the 2nd menu, the same thing with the 2nd menu and the 3rd menu.but the Options are diferent so you know that the user has choised finnaly. exemple :
menu 1: 1 ==> menu 2: 4==> menu 3: 2 (...)the choice is 142. other cases : 111,141,131,122...
sollution: store the first 1st in a,2nd in b,3rd on c. a=1, b=4, c=2
char ABC[4]="";
ABC<-sprintf(ABC,"%d%d%d",a,b,c); //without space between %d%d%d
printf("%s",ABC); //value as char[]=142
//now you want to recover your value(142) from char[] to int as int value 142
concated=atoi(ABC); //result is 142 as int, not 1,4,2 (separeted)
加载中,请稍侯......
精彩评论