Introduction of wchar.h to support more characters.

[TP_AL_C.git] / lexer / main.c

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

#define TOKEN_MAX 500

struct token_s {
    const char* type;
    wint_t value[50];
};

struct token_s token[TOKEN_MAX] = {NULL, 0};

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

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

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

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

// The main loop get the next character
init:
    if (c == L' ' || c == L'\t') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto init;
    }
    if (c == L'\n') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto initLV1;
    }
    if (c == L'>') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto MC1;
    }
    if (c == L'=') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto S1SS1;
    }
    if (istAlpha()) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto M1;
    }
    if (c == WEOF) {
        goto FIN;
    } else {
        goto error;
    }

MC1:
    // FIXME: Partial match need a rewind in the characters extraction from the file
    if (c == (wint_t)Titre[j] && j < wcslen(Titre) - 1) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        j++;
        goto MC1;
    }
    if (c == (wint_t)Auteur[j] && j < wcslen(Auteur) - 1) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        j++;
        goto MC1;
    } else {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto MC2;
    }

S1SS1:
    if (c == L'=') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto SS2;
    }
    if (isSeparator() || c == WEOF) {
        goto SECTION;
    }

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

SECTION:
    tokenType = SECTION;
    return 1;

SSECTION:
    tokenType = SSECTION;
    return 1;

M1:
    if (istAlpha()) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto M1;
    }
    if (isSeparator() || c == WEOF) {
        goto MOT;
    }

initLV1:
    if (c == L' ' || c == L'\t') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto initLV1;
    }
    if (c == L'\n') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto initLV1LV2;
    }
    if (istAlpha()) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto M1;
    }
    if (c == L'=') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto S1SS1;
    }
    if (c == L'>') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto MC1;
    }
    if (c == WEOF) {
        goto FIN;
    }

initLV1LV2:
    if (isSeparator()) {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto initLV1LV2;
    }
    if (istAlpha()) {
        goto NPARA;
    }
    if (c == L'>') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto MC1;
    }
    if (c == L'=') {
        c = fgetwc(source);
        token[tokenFound].value[i] = c;
        i++;
        goto S1SS1;
    }
    if (c == WEOF) {
        goto FIN;
    }

NPARA:
    tokenType = NPARA;
    return 1;

MOT:
    tokenType = MOT;
    return 1;

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

MOTCLE:
    tokenType = MOTCLE;
    return 1;

FIN:
    tokenType = FIN;
    return 1;

error:
    tokenType = FIN;
    return -1;
}

int main() {

    // 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;
    }

    do {
        c = fgetwc(source); // lecture du caractere suivant du fichier source
        token[tokenFound].value[i] = c;
        i++;
        int scanrt = scanner();
        if (scanrt == -1) {
            wprintf(L"Scanner error with token value: %ls\n", token[tokenFound].value);
            exit(EXIT_FAILURE);
        }
        if (c != WEOF) {
            wprintf(L"Token type found: %s with value: %ls\n", tokenTypestr[tokenType], token[tokenFound].value);
        } else {
            wprintf(L"Token type found: %s\n", tokenTypestr[tokenType]);
        }
        token[tokenFound].type = tokenTypestr[tokenType];
        tokenFound++;
        // reinit token.value array counter
        i = 0;
    //} while (c != WEOF); // tant que la fin du fichier n'est pas atteinte
    } while (!feof(source)); // 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;
}