Increment the number of tokens found after the array storage.

[TP_AL_C.git] / lexer / main.c

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

#define TOKEN_MAX_LENGTH 50
#define TOKEN_LIST_MAX 500

FILE *source = NULL, *target = NULL;
char c;
unsigned int i = 0;
char tokenValue[TOKEN_MAX_LENGTH];
enum TokenType {
    MOTCLE,
    SECTION,
    SSECTION,
    NPARA,
    MOT,
    FIN
} tokenType;
const char* tokenTypestr[] = { "MOTCLE", "SECTION", "SSECTION", "NPARA", "MOT", "FIN" };
const char* tokenList[TOKEN_LIST_MAX];

/* It looks silly to check for each characters but for debugging, it's just the way to go */
bool istAlpha() {
    if (c == 'a' || c == 'b' || c == 'c' || c == 'd' || c == 'e' || c == 'f' || c == 'g' || \
        c == 'h' || c == 'i' || c == 'j' || c == 'k' || c == 'l' || c == 'm' || c == 'n' || \
        c == 'o' || c == 'p' || c == 'q' || c == 'r' || c == 's' || c == 't' || c == 'u' || \
        c == 'v' || c == 'w' || c == 'x' || c == 'y' || c == 'z' || \
        c == 'A' || c == 'B' || c == 'C' || c == 'D' || c == 'E' || c == 'F' || c == 'G' || \
        c == 'H' || c == 'I' || c == 'J' || c == 'K' || c == 'L' || c == 'M' || c == 'N' || \
        c == 'O' || c == 'P' || c == 'Q' || c == 'R' || c == 'S' || c == 'T' || c == 'U' || \
        c == 'V' || c == 'W' || c == 'X' || c == 'Y' || c == 'Z' || \
        c == '.' || c == '?' || c == '!' || c == ',' || c == ';' || c == ':' || c == '-' || \
        c == '\''|| c == '#' || \
        c == '0' || c == '1' || c == '2' || c == '3' || c == '4' || c == '5' || c == '6' || \
        c == '7' || c == '8' || c == '9') {
            return true;
        }
        return false;
}

bool isSeparator() {
    if (c == '\t' || c == ' ' || c == '\n') {
        return true;
    }
    return false;
}

int scanner() {
    const char* Titre = "Titre";
    const char* Auteur = "Auteur";
    unsigned int j = 0;

// The main loop get the next character
init:
    if (c == ' ' || c == '\t') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto init;
    }
    if (c == '\n') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto initLV1;
    }
    if (c == '>') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto MC1;
    }
    if (c == '=') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto S1SS1;
    }
    if (istAlpha()) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto M1;
    }
    if (c == EOF) {
        goto FIN;
    } else {
        goto error;
    }

MC1:
    // FIXME: Partial match need a rewind in the characters extraction from the file
    if (c == Titre[j] && j < strlen(Titre) - 1) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        j++;
        goto MC1;
    }
    if (c == Auteur[j] && j < strlen(Auteur) - 1) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        j++;
        goto MC1;
    } else {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto MC2;
    }

S1SS1:
    if (c == '=') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto SS2;
    }
    if (isSeparator() || c == EOF) {
        goto SECTION;
    }

SS2:
    if (isSeparator() || c == EOF) {
        goto SSECTION;
    }

SECTION:
    tokenType = SECTION;
    return 1;

SSECTION:
    tokenType = SSECTION;
    return 1;

M1:
    if (istAlpha()) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto M1;
    }
    if (isSeparator() || c == EOF) {
        goto MOT;
    }

initLV1:
    if (c == ' ' || c == '\t') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto initLV1;
    }
    if (c == '\n') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto initLV1LV2;
    }
    if (istAlpha()) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto M1;
    }
    if (c == '=') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto S1SS1;
    }
    if (c == '>') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto MC1;
    }
    if (c == EOF) {
        goto FIN;
    }

initLV1LV2:
    if (isSeparator()) {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto initLV1LV2;
    }
    if (istAlpha()) {
        goto NPARA;
    }
    if (c == '>') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto MC1;
    }
    if (c == '=') {
        c = fgetc(source);
        tokenValue[i] = c;
        i++;
        goto S1SS1;
    }
    if (c == EOF) {
        goto FIN;
    }

NPARA:
    tokenType = NPARA;
    return 1;

MOT:
    tokenType = MOT;
    return 1;

MC2:
    if (isSeparator() || c == EOF) {
        goto MOTCLE;
    }

MOTCLE:
    tokenType = MOTCLE;
    return 1;

FIN:
    tokenType = FIN;
    return 1;

error:
    tokenType = FIN;
    return -1;
}

int main (int argc, char const *argv[]) {

    // Ouvre le fichier test.txt en lecture seulement (le fichier doit exister) :
    source = fopen("test.txt", "r");
    // Cree et ouvre un fichier target.html en lecture/ecriture
    // avec suppression du contenu au prealable :
    target = fopen("target.html", "w+");

    if (source == NULL) {
        printf("Impossible d'ouvrir le fichier source\n");
        return -1;
    }

    if (target == NULL) {
        printf("Impossible d'ouvrir le fichier target\n");
        return -1;
    }

    int tokenFound = 0;

    do {
        c = fgetc(source); // lecture du caractere suivant du fichier source
        tokenValue[i] = c;
        i++;
        int scanrt = scanner();
        if (scanrt == -1) {
            printf ("Scanner error with token value: %s\n", tokenValue);
            exit(EXIT_FAILURE);
        }
        if (c != EOF) {
            printf ("Token type found: %s with value: %s\n", tokenTypestr[tokenType], tokenValue);
        } else {
            printf ("Token type found: %s\n", tokenTypestr[tokenType]);
        }
        tokenList[tokenFound] = tokenTypestr[tokenType];
        tokenFound++;
        // reinit tokenValue
        i = 0;
        memset(tokenValue, 0, sizeof(tokenValue));
    } while (c != EOF); // tant que la fin du fichier n'est pas atteinte

    if (source != NULL) fclose(source); // fermeture du fichier source
    if (target != NULL) fclose(target); // fermeture du fichier target

    return 0;
}