Last active
August 29, 2015 14:14
-
-
Save incertia/9d8671c6841bb51046b4 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include "parser.h" | |
#include <ctype.h> | |
#include <stdlib.h> | |
#include <string.h> | |
typedef int BOOL; | |
#define TRUE 1 | |
#define FALSE 0 | |
char *s = NULL; | |
char *cur = NULL; | |
/* nextarg is like strtok, but it has its own delimiter set. | |
nextarg will never return NULL when cmd is non-NULL. | |
if cmd == NULL, then nextarg returns the next argument from the | |
previous call to nextarg. | |
the pointer returned from nextarg should be freed by the caller. | |
char *s = "a bc \"def' `ghi\""; | |
char *c = nextarg(s); | |
while(c){ | |
printf("%s\n", c); | |
free(c); | |
c = nextarg(NULL); | |
} */ | |
char * nextarg(const char *cmd){ | |
int i = 0, j = 0; | |
BOOL in_token = FALSE; | |
char *r, *b, quote = '\0'; | |
/* we operate on our own local copy cur */ | |
if(cmd){ | |
if(cur) free(cur); | |
s = cur = strdup(cmd); | |
} | |
if(!cur || !s) return NULL; | |
/* search s, which will point to the end of the current token */ | |
b = s; | |
while(*s){ | |
if(!in_token){ | |
/* we encountered what might not be a token */ | |
if(!isspace(*s)){ | |
in_token = TRUE; | |
if(*s == '"' || *s == '\'' || *s == '`') quote = *s, b = s; | |
else i++, b = s; /* increment char count */ | |
if(*s == '\\'){ | |
/* fix edge case where the last char is \ */ | |
if(!*(s + 1)){ | |
*s = '\0'; | |
if(i > 1) break; | |
else { | |
free(cur); | |
return cur = s = NULL; | |
} | |
} | |
s++; /* skip the escaped character */ | |
} | |
} | |
} else { | |
/* we are inside a token */ | |
if(quote){ | |
if(quote == *s){ | |
// we found the end | |
quote = '\0'; | |
s++; | |
continue; | |
} | |
} else { | |
if(isspace(*s)){ | |
// this is the end | |
break; | |
} else if(*s == '"' || *s == '\'' || *s == '`'){ | |
quote = *s++; | |
continue; | |
} | |
} | |
if(*s == '\\'){ | |
/* this covers the other edge case where last char is \ */ | |
if(!*(s + 1)){ | |
*s = '\0'; | |
if(i) break; | |
else { | |
free(cur); | |
return cur = s = NULL; | |
} | |
} | |
s++; /* skip the escaped character */ | |
} | |
i++; | |
} | |
s++; | |
} | |
/* allocate the string */ | |
r = malloc((i + 1) * sizeof(char)); | |
/* fill the string */ | |
r[i] = '\0'; | |
quote = '\0'; | |
while(j < i){ | |
if(*b == '\\'){ | |
b++; | |
r[j++] = *b++; | |
} else if(*b == '"' || *b == '\'' || *b == '`') | |
if(!quote) quote = *b++; | |
else if(quote == *b) quote = '\0', b++; | |
else r[j++] = *b++; | |
else r[j++] = *b++; | |
} | |
while(*s && isspace(*s)) s++; | |
if(!*s){ | |
free(cur); | |
s = cur = NULL; | |
} | |
return r; | |
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#ifndef __PARSER_H__ | |
#define __PARSER_H__ | |
char * nextarg(const char *cmd); | |
#endif /* #ifndef __PARSER_H__ */ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment