Last active
April 6, 2017 17:16
-
-
Save reubenjohn/295e4534d35103e785619c9d7195beb5 to your computer and use it in GitHub Desktop.
99 line lex analyser
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 <stdio.h> | |
#include <string.h> | |
#include <regex.h> | |
FILE *in,*out; | |
int nextChar(char buf[], int* cnt){ | |
buf[*cnt+1] = '\0'; | |
return fscanf(in,"%c",&buf[(*cnt)++]) > 0; | |
} | |
typedef struct{ | |
const char *pattern; | |
const char* follow[100]; | |
int toBeOutput; | |
}TokenPattern; | |
int compare(const char* pattern, const char* follow, char* s){ | |
char patternFollow[120]; | |
regex_t regex; | |
switch(follow[0]){ | |
case '+':case '-':case '*':case '/':case '%':case '=':case '(':case ')':case '{':case '}':case '\n': | |
sprintf(patternFollow,"^%s\\%s$",pattern,follow); | |
//getchar(); | |
//printf("%s",patternFollow); | |
break; | |
default: | |
sprintf(patternFollow,"^%s%s$",pattern,follow); | |
} | |
if (regcomp(®ex, patternFollow, REG_EXTENDED)) { | |
printf("Could not compile regex\n"); | |
return 0; | |
} | |
if(!regexec(®ex,s,0,NULL,0)){ | |
printf("Matched (%s) == (%s) with result: %d\n",patternFollow,s,1); | |
return 1; | |
} | |
return 0; | |
} | |
#define SPECIALS " ",";",",","+","-","*","/","%","=","(",")","{","}","<",">" | |
#define NUMS "0","1","2","3","4","5","6","7","8","9" | |
#define ALPHAS "q","w","e","r","t","y","u","i","o","p","a","s","d","f","g","h","j","k","l","z","x","c","v","b","n","m" | |
#define RELOPS "==","!=","<",">","<=",">=" | |
const TokenPattern patterns[] = { | |
{"//(.)*\n|/\\*(.)*\\*/",{"","$"},0}, | |
{"asdl",{"","$"},0}, | |
{"#include",{"","$"},1}, | |
{"<(.)+>",{"\n","$"},1}, | |
{"(if|int|float|char|double|void|for|while|do)",{" ","(","\n","$"},1}, | |
{"[a-zA-Z_][a-zA-Z_0-9]*",{SPECIALS,RELOPS,"$"},1}, | |
{"[1-9][0-9]*",{SPECIALS,RELOPS,"$"},1}, | |
{"(;|,|\\+|\\-|\\*|\\/|\\%|\\=|\\(|\\)|\\{|\\}|==|!=|<|>|<=|>=|\\+\\+|\\-\\-)",{"\n",")",";",ALPHAS,NUMS,"$"},1}, | |
{"( |\t)",{"","$"},0}, | |
{"\n",{"","$"},0}, | |
//{"(.)+",{"\n","$"},0}, | |
{"$",{}} | |
}; | |
const char* tokenIds[] = {"mcom","com","include","header","key","id","num","sp","nl","*"}; | |
typedef enum{MCOM, COM, INCLUDE, HEADER, KEY, ID, NUM, SP, NL}PatternType; | |
int tokenize(char buf[], int *cnt){ | |
for(unsigned int i=0;patterns[i].pattern[0]!='$';i++) { | |
TokenPattern pattern = patterns[i]; | |
for(unsigned int j=0;pattern.follow[j][0]!='$';j++) { | |
char patternBuf[100], followBuf[10]; | |
strcpy(followBuf, &buf[*cnt - strlen(pattern.follow[j])]); | |
strcpy(patternBuf,buf); | |
patternBuf[*cnt - strlen(followBuf)] = '\0'; | |
if(compare(pattern.pattern,pattern.follow[j],buf)) { | |
if(pattern.toBeOutput) | |
fprintf(out,"<%s>%s\t",patternBuf,tokenIds[i]); | |
strcpy(buf, followBuf); | |
*cnt = strlen(pattern.follow[j]); | |
return 1; | |
} | |
} | |
} | |
return 0; | |
} | |
int main(){ | |
in = fopen("in.c","r"); | |
out = fopen("out.c","w"); | |
char buf[100];int cnt=0; | |
while(nextChar(buf,&cnt)){ | |
printf("(%s,%d)\n",buf,cnt); | |
while(tokenize(buf,&cnt)); | |
} | |
printf("---\n"); | |
fclose(in); | |
fclose(out); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment