#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <stdbool.h>

typedef struct {
    const char* text;
    unsigned    text_len;
    unsigned    text_pos;

    const char* token;
    unsigned    token_len;
} lexer_t;

bool lexer_next_token(lexer_t* self)
{
    unsigned i;
    unsigned len;
    char     ch;

    for(i = self->text_pos, len = 0;
        i != self->text_len;
        i++, len++) {
        start:

        ch = self->text[i];

        if((ch < 'A' || ch > 'Z') &&
           (ch < 'a' || ch > 'z')) {

            if(len == 0) {
                if(ch != ' ') {
                    self->token = &self->text[i];
                    self->token_len = 1;
                    self->text_pos = i + 1;
                    return true;
                } else {
                    len = 0;
                    i++;
                    goto start;
                }
            }

            self->token = &self->text[i-len];
            self->token_len = len;
            self->text_pos = i;
            return true;

        }
    }

    if(len) {
        self->token = &self->text[i-len];
        self->token_len = len;
        self->text_pos = i;
        return true;
    }

    return false;
}

int main(int argc, char* argv[])
{
    FILE*   file;
    size_t  file_size;
    char*   file_data;
    int     cnt_word = 0, cnt_point = 0;
    lexer_t lexer = {0};



    file = fopen("data","r");
    fseek(file,0,SEEK_END);
    file_size = ftell(file);
    fseek(file,0,SEEK_SET);

    file_data = malloc(file_size);
    fread(file_data,file_size,1,file);
    fclose(file);

    lexer.text_pos = 0;
    lexer.text = file_data;
    lexer.text_len = file_size-1;

    while(lexer_next_token(&lexer)) {
        if(lexer.token_len == 1 && lexer.token[0] == ',')
            cnt_point++;
        else
            cnt_word++;
    }

    printf("Итого: %d слов и %d запятых\n",cnt_word,cnt_point);
}