lexer/main.c

   1 #include <stdlib.h>
   2 #include <stdio.h>
   3 #include <string.h>
   4 #include <stdbool.h>
   5
   6 FILE *source, *target = NULL;
   7 char c;
   8 unsigned int i = 0;
   9 char tokenValue[50];
  10 enum TokenType {
  11     MOTCLE,
  12     SECTION,
  13     SSECTION,
  14     NPARA,
  15     MOT,
  16     FIN
  17 } tokenType;
  18 const char* tokenTypestr[] = { "MOTCLE", "SECTION", "SSECTION", "NPARA", "MOT", "FIN" };
  19
  20 /* It looks silly to check for each characters but for debugging, it's just the way to go */
  21 bool istAlpha() {
  22     if (c == 'a' || c == 'b' || c == 'c' || c == 'd' || c == 'e' || c == 'f' || c == 'g' || \
  23         c == 'h' || c == 'i' || c == 'j' || c == 'k' || c == 'l' || c == 'm' || c == 'n' || \
  24         c == 'o' || c == 'p' || c == 'q' || c == 'r' || c == 's' || c == 't' || c == 'u' || \
  25         c == 'v' || c == 'w' || c == 'x' || c == 'y' || c == 'z' || \
  26         c == 'A' || c == 'B' || c == 'C' || c == 'D' || c == 'E' || c == 'F' || c == 'G' || \
  27         c == 'H' || c == 'I' || c == 'J' || c == 'K' || c == 'L' || c == 'M' || c == 'N' || \
  28         c == 'O' || c == 'P' || c == 'Q' || c == 'R' || c == 'S' || c == 'T' || c == 'U' || \
  29         c == 'V' || c == 'W' || c == 'X' || c == 'Y' || c == 'Z' || \
  30         c == '.' || c == '?' || c == '!' || c == ',' || c == ';' || c == ':' || c == '-' || \
  31         c == '\''|| c == '#' || \
  32         c == '0' || c == '1' || c == '2' || c == '3' || c == '4' || c == '5' || c == '6' || \
  33         c == '7' || c == '8' || c == '9') {
  34             return true;
  35         }
  36         return false;
  37 }
  38
  39 bool isSeparator() {
  40     if (c == '\t' || c == ' ' || c == '\n') {
  41         return true;
  42     }
  43     return false;
  44 }
  45
  46 int scanner() {
  47     const char* Titre = "Titre";
  48     const char* Auteur = "Auteur";
  49     unsigned int j = 0;
  50
  51 // The main loop get the next character
  52 init:
  53     if (c == ' ' || c == '\t') {
  54         c = fgetc(source);
  55         tokenValue[i] = c;
  56         i++;
  57         goto init;
  58     }
  59     if (c == '\n') {
  60         c = fgetc(source);
  61         tokenValue[i] = c;
  62         i++;
  63         goto initLV1;
  64     }
  65     if (c == '>') {
  66         c = fgetc(source);
  67         tokenValue[i] = c;
  68         i++;
  69         goto MC1;
  70     }
  71     if (c == '=') {
  72         c = fgetc(source);
  73         tokenValue[i] = c;
  74         i++;
  75         goto S1SS1;
  76     }
  77     if (istAlpha()) {
  78         c = fgetc(source);
  79         tokenValue[i] = c;
  80         i++;
  81         goto M1;
  82     }
  83     if (c == EOF) {
  84         goto FIN;
  85     } else {
  86         goto error;
  87     }
  88
  89 MC1:
  90     // FIXME: Partial match need a rewind in the characters extraction from the file
  91     if (c == Titre[j] && j < strlen(Titre) - 1) {
  92         c = fgetc(source);
  93         tokenValue[i] = c;
  94         i++;
  95         j++;
  96         goto MC1;
  97     }
  98     if (c == Auteur[j] && j < strlen(Auteur) - 1) {
  99         c = fgetc(source);
 100         tokenValue[i] = c;
 101         i++;
 102         j++;
 103         goto MC1;
 104     } else {
 105         c = fgetc(source);
 106         tokenValue[i] = c;
 107         i++;
 108         goto MC2;
 109     }
 110
 111 S1SS1:
 112     if (c == '=') {
 113         c = fgetc(source);
 114         tokenValue[i] = c;
 115         i++;
 116         goto SS2;
 117     }
 118     if (isSeparator() || c == EOF) {
 119         goto SECTION;
 120     }
 121
 122 SS2:
 123     if (isSeparator() || c == EOF) {
 124         goto SSECTION;
 125     }
 126
 127 SECTION:
 128     tokenType = SECTION;
 129     return 1;
 130
 131 SSECTION:
 132     tokenType = SSECTION;
 133     return 1;
 134
 135 M1:
 136     if (istAlpha()) {
 137         c = fgetc(source);
 138         tokenValue[i] = c;
 139         i++;
 140         goto M1;
 141     }
 142     if (isSeparator() || c == EOF) {
 143         goto MOT;
 144     }
 145
 146 initLV1:
 147     if (c == ' ' || c == '\t') {
 148         c = fgetc(source);
 149         tokenValue[i] = c;
 150         i++;
 151         goto initLV1;
 152     }
 153     if (c == '\n') {
 154         c = fgetc(source);
 155         tokenValue[i] = c;
 156         i++;
 157         goto initLV1LV2;
 158     }
 159     if (istAlpha()) {
 160         c = fgetc(source);
 161         tokenValue[i] = c;
 162         i++;
 163         goto M1;
 164     }
 165     if (c == '=') {
 166         c = fgetc(source);
 167         tokenValue[i] = c;
 168         i++;
 169         goto S1SS1;
 170     }
 171     if (c == '>') {
 172         c = fgetc(source);
 173         tokenValue[i] = c;
 174         i++;
 175         goto MC1;
 176     }
 177     if (c == EOF) {
 178         goto FIN;
 179     }
 180
 181 initLV1LV2:
 182     if (isSeparator()) {
 183         c = fgetc(source);
 184         tokenValue[i] = c;
 185         i++;
 186         goto initLV1LV2;
 187     }
 188     if (istAlpha()) {
 189         goto NPARA;
 190     }
 191     if (c == '>') {
 192         c = fgetc(source);
 193         tokenValue[i] = c;
 194         i++;
 195         goto MC1;
 196     }
 197     if (c == '=') {
 198         c = fgetc(source);
 199         tokenValue[i] = c;
 200         i++;
 201         goto S1SS1;
 202     }
 203     if (c == EOF) {
 204         goto FIN;
 205     }
 206
 207 NPARA:
 208     tokenType = NPARA;
 209     return 1;
 210
 211 MOT:
 212     tokenType = MOT;
 213     return 1;
 214
 215 MC2:
 216     if (isSeparator() || c == EOF) {
 217         goto MOTCLE;
 218     }
 219
 220 MOTCLE:
 221     tokenType = MOTCLE;
 222     return 1;
 223
 224 FIN:
 225     tokenType = FIN;
 226     return 1;
 227
 228 error:
 229     tokenType = FIN;
 230     return -1;
 231 }
 232
 233 int main (int argc, char const *argv[]) {
 234
 235     // Ouvre le fichier test.txt en lecture seulement (le fichier doit exister) :
 236     source = fopen("test.txt", "r");
 237     // Cree et ouvre un fichier target.html en lecture/ecriture
 238     // avec suppression du contenu au prealable :
 239     target = fopen("target.html", "w+");
 240
 241     if (source == NULL) {
 242         printf("Impossible d'ouvrir le fichier source\n");
 243         return -1;
 244     }
 245
 246     if (target == NULL) {
 247         printf("Impossible d'ouvrir le fichier target\n");
 248         return -1;
 249     }
 250
 251     do {
 252         c = fgetc(source); // lecture du caractere suivant du fichier source
 253         tokenValue[i] = c;
 254         i++;
 255         int scanrt = scanner();
 256         if (scanrt == -1) {
 257             printf ("Scanner error with token value: %s\n", tokenValue);
 258             exit(EXIT_FAILURE);
 259         }
 260         if (c != EOF) {
 261             printf ("Token type found: %s with value: %s\n", tokenTypestr[tokenType], tokenValue);
 262         } else {
 263             printf ("Token type found: %s\n", tokenTypestr[tokenType]);
 264         }
 265         // reinit tokenValue
 266         i = 0;
 267         memset(tokenValue, 0, sizeof(tokenValue));
 268     } while (c != EOF); // tant que la fin du fichier n'est pas atteinte
 269
 270     if (source != NULL) fclose(source); // fermeture du fichier source
 271     if (target != NULL) fclose(target); // fermeture du fichier target
 272
 273     return 0;
 274 }