How to read two consecutive characters from a file in C?

Question

I have the following code, where I want to create a simply scanner for a simple calculator language. I am using fgetc to get the character from the file. Though, at some places I also need to check the next character that is followed. For this reason I have been using the ++ operator, but it seems like it is not working properly. Can someone help me fix my problem.

For example, when I have := in my text file, it prints colon, and then shows an error message saying: "; cannot follow : (colon).", whereas it should print "assign".

Here is my full code:

#include <regex.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>

int main(int argc, char** argv)
{
    FILE *fp;
    int c, check, reti_d, reti_l;

    regex_t digit, letter;
    reti_d = regcomp(&digit, "[0-9]", 0);
    reti_l = regcomp(&letter, "[a-zA-Z]", 0);

    if (reti_d || reti_l)
    {
        fprintf(stderr, "Couldn't compile the regular expression(s).\n");
        exit(1);
    }

    if (argc != 2)
    {
        fprintf(stderr, "Usage: %s filename.txt\n", argv[0]);
        exit(1);
    }

    if (!(fp = fopen(argv[1], "r")))
    {
        perror("Error opening file!\n");
        exit(1);
    }

    while ((c = fgetc(fp)) != EOF)
    {
        char regdtest[1];
        char regltest[1];
        regdtest[0] = (char)c;
        reti_d = regexec(&digit, regdtest, 0, NULL, 0);
        reti_l = regexec(&letter, regltest, 0, NULL, 0);

        switch (c)
        {
            case '(': printf("lperen "); break;
            case ')': printf("rparen "); break;
            case '+': printf("plus "); break;
            case '-': printf("minus "); break;
            case '*': printf("times "); break;
        }

        if (c == ':')
        {
            if (c++ == '=')
                printf("assign ");
            else printf("\n%c cannot follow : (colon).\n", (char)c);
        }

        if (c == '/')
        {
            if (++c == '/' || ++c == '*')
            {
                while (c != '\n' || (c == '*' && ++c == '/'))
                    c++;
            }
            else printf("div ");
        }

        if (c == '.')
        {
            regdtest[0] = (char)++c;
            reti_d = regexec(&digit, regdtest, 0, NULL, 0);

            if (!reti_d)
            {
                printf("number ");
            }
            else printf("\n. (dot) should be followed by digits.\n");
        }

        if (!reti_d)
        {
            while (!reti_d)
            {
                regdtest[0] = (char)c;
                reti_d = regexec(&digit, regdtest, 0, NULL, 0);
            }

            printf("number ");
        }

        if (!reti_l)
        {
            int i, j = 0;
            char read[5], write[6];
            read[i] = write[j] = (char)c;

            while(!reti_d || !reti_l)
            {
                c++;
                i++;
                j++;

                if (i >= 5)
                    i = 0;
                if (j >= 6)
                    j = 0;

                read[i] = write[j] = (char)c;
                if (strcmp(read, "read") == 0)
                    printf("read ");
                else printf("id ");

                if (strcmp(write, "write") == 0)
                    printf("write ");
                else printf("id ");

                regdtest[0] = (char)c;
                regltest[0] = (char)c;
                reti_d = regexec(&digit, regdtest, 0, NULL, 0);
                reti_l = regexec(&letter, regltest, 0, NULL, 0);
            }

            printf("letter ");
        }

    }

    fclose(fp);
    return 0;
}

Answer 1

您需要再次调用fgetc()来获取第二个字符。

Answer 2

As @pmg suggested, replace ++c with fgetc() .

Below is a reworked if (c == '/') section. The various syntax errors path were not completely coded and the below may need additional cod to deal with unexpected paths. Remember than any fgetc() may result in the EOF condition. Also up to 1 ungetc() may be executed between fgetc() calls to undo.

if (c == '/') {
  c = fgetc(fp);
  if (c == '/') {
    c = fgetc(fp);
    if (c == '*') {
      while (c = fgetc(fp) != '\n' && c != EOF) {
        if (c == '*') {
          c = fgetc(fp);
          if (c == '/') break;
          ungetc(c, fp);
        }
      }
      printf("div ");
    }
    else TBD();
  } else ...