Files
assm-test/src/tokenizer.c
T

139 lines
2.9 KiB
C

#include "../includes/tokenizer.h"
#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
List* TokenizeLine(char *);
TokenType GetOperatorType(char);
char* SplitOnWhiteSpace(char*);
List* TokenizeString(const char *file_path) {
FILE *file;
char* line = NULL;
size_t len = 0;
ssize_t bytes_read;
List* tokens = CreateList();
file = fopen(file_path, "r");
if (!file) {
printf("Failed to open '%s' for reading.\n", file_path);
return NULL;
}
while((bytes_read = getline(&line, &len, file)) != -1) {
List* tokens = TokenizeLine(line);
// for(int i = 0; i < tokens->size; i++) {
// printf("Token type '%d' with value '%s'\n", ((Token* ) tokens->content[i])->type, ((Token*) tokens->content[i])->value);
// }
}
fclose(file);
if (line) free(line);
return tokens;
}
List* TokenizeLine(char *line) {
if (!line) return NULL;
if (strlen(line) == 0) return NULL;
if (line[0] == ';') return NULL;
char* token = SplitOnWhiteSpace(line);
while (strlen(token) != 0) {
printf("'%s' ", token);
//if (token[0] == '"') printf("String token: '%s'\n", token);
free(token);
token = SplitOnWhiteSpace(NULL);
}
printf("\n");
//free(currentWord);
free(token);
return NULL;
}
char* SplitOnWhiteSpace(char* line) {
static char* string;
static unsigned long position;
if (line) {
string = line;
position = 0;
}
char* token = calloc(1, strlen(string) + 1);
int parsing_string = 0;
for (int i = 0; position < strlen(string); i++, position++) {
if (parsing_string) {
if (string[position] == '\n') break;
token[i] = string[position];
continue;
}
if (string[position] == ';') break;
if (string[position] == '"') {
parsing_string = 1;
}
if (string[position] == ' ') {
while(string[position] == ' ') {
position++;
}
if (strlen(token) != 0) break;
}
if (string[position] == ',') {
if (strlen(token) == 0) {
token[0] = string[position];
position++;
}
break;
}
if (string[position] != '\n') token[i] = string[position];
}
//token[strlen(token)] = '\0';
return token;
}
TokenType GetOperatorType(char c) {
switch (c){
case '+':
return TK_Add;
case '-':
return TK_Sub;
case '*':
return TK_Mul;
case '/':
return TK_Div;
case '^':
return TK_Power;
case ':':
return TK_Colon;
case '(':
return TK_LParam;
case ')':
return TK_RParam;
case '[':
return TK_LBracket;
case ']':
return TK_RBracket;
};
return TK_Invalid;
}