| 1 | #include <stdlib.h> |
| 2 | #include <stdio.h> |
| 3 | #include <string.h> |
| 4 | #include <stdbool.h> |
| 5 | #include <wchar.h> |
| 6 | |
| 7 | #define TOKEN_MAX 500 |
| 8 | |
| 9 | struct token_s { |
| 10 | const char* type; |
| 11 | wint_t value[50]; |
| 12 | }; |
| 13 | |
| 14 | struct token_s token[TOKEN_MAX] = {NULL, 0}; |
| 15 | |
| 16 | FILE *source = NULL, *target = NULL; |
| 17 | wint_t c; |
| 18 | unsigned int tokenFound = 0; |
| 19 | enum TokenType { |
| 20 | MOTCLE, |
| 21 | SECTION, |
| 22 | SSECTION, |
| 23 | NPARA, |
| 24 | MOT, |
| 25 | FIN |
| 26 | } tokenType; |
| 27 | const char* tokenTypestr[] = { "MOTCLE", "SECTION", "SSECTION", "NPARA", "MOT", "FIN" }; |
| 28 | unsigned int i = 0; |
| 29 | |
| 30 | /* It looks silly to check for each characters but for debugging, it's just the way to go */ |
| 31 | bool istAlpha() { |
| 32 | if (c == L'a' || c == L'b' || c == L'c' || c == L'd' || c == L'e' || c == L'f' || c == L'g' || \ |
| 33 | c == L'h' || c == L'i' || c == L'j' || c == L'k' || c == L'l' || c == L'm' || c == L'n' || \ |
| 34 | c == L'o' || c == L'p' || c == L'q' || c == L'r' || c == L's' || c == L't' || c == L'u' || \ |
| 35 | c == L'v' || c == L'w' || c == L'x' || c == L'y' || c == L'z' || \ |
| 36 | c == L'A' || c == L'B' || c == L'C' || c == L'D' || c == L'E' || c == L'F' || c == L'G' || \ |
| 37 | c == L'H' || c == L'I' || c == L'J' || c == L'K' || c == L'L' || c == L'M' || c == L'N' || \ |
| 38 | c == L'O' || c == L'P' || c == L'Q' || c == L'R' || c == L'S' || c == L'T' || c == L'U' || \ |
| 39 | c == L'V' || c == L'W' || c == L'X' || c == L'Y' || c == L'Z' || \ |
| 40 | c == L'.' || c == L'?' || c == L'!' || c == L',' || c == L';' || c == L':' || c == L'-' || \ |
| 41 | c == L'\''|| c == L'#' || \ |
| 42 | c == L'0' || c == L'1' || c == L'2' || c == L'3' || c == L'4' || c == L'5' || c == L'6' || \ |
| 43 | c == L'7' || c == L'8' || c == L'9' || \ |
| 44 | c == L'à' || c == L'â' || c == L'ç' || c == L'è' || c == L'é' || c == L'î' || c == L'ô' || \ |
| 45 | c == L'ù' || c == L'û' || \ |
| 46 | c == L'À' || c == L'Â' || c == L'Ç' || c == L'È' || c == L'É' || c == L'Î' || c == L'Ô' || \ |
| 47 | c == L'Ù' || c == L'Û') { |
| 48 | return true; |
| 49 | } |
| 50 | return false; |
| 51 | } |
| 52 | |
| 53 | bool isSeparator() { |
| 54 | if (c == L'\t' || c == L' ' || c == L'\n') { |
| 55 | return true; |
| 56 | } |
| 57 | return false; |
| 58 | } |
| 59 | |
| 60 | int scanner() { |
| 61 | const wchar_t* Titre = L"Titre"; |
| 62 | const wchar_t* Auteur = L"Auteur"; |
| 63 | unsigned int j = 0; |
| 64 | |
| 65 | // The main loop get the next character |
| 66 | init: |
| 67 | if (c == L' ' || c == L'\t') { |
| 68 | c = fgetwc(source); |
| 69 | token[tokenFound].value[i] = c; |
| 70 | i++; |
| 71 | goto init; |
| 72 | } |
| 73 | if (c == L'\n') { |
| 74 | c = fgetwc(source); |
| 75 | token[tokenFound].value[i] = c; |
| 76 | i++; |
| 77 | goto initLV1; |
| 78 | } |
| 79 | if (c == L'>') { |
| 80 | c = fgetwc(source); |
| 81 | token[tokenFound].value[i] = c; |
| 82 | i++; |
| 83 | goto MC1; |
| 84 | } |
| 85 | if (c == L'=') { |
| 86 | c = fgetwc(source); |
| 87 | token[tokenFound].value[i] = c; |
| 88 | i++; |
| 89 | goto S1SS1; |
| 90 | } |
| 91 | if (istAlpha()) { |
| 92 | c = fgetwc(source); |
| 93 | token[tokenFound].value[i] = c; |
| 94 | i++; |
| 95 | goto M1; |
| 96 | } |
| 97 | if (c == WEOF) { |
| 98 | goto FIN; |
| 99 | } else { |
| 100 | goto error; |
| 101 | } |
| 102 | |
| 103 | MC1: |
| 104 | // FIXME: Partial match need a rewind in the characters extraction from the file |
| 105 | if (c == (wint_t)Titre[j] && j < wcslen(Titre) - 1) { |
| 106 | c = fgetwc(source); |
| 107 | token[tokenFound].value[i] = c; |
| 108 | i++; |
| 109 | j++; |
| 110 | goto MC1; |
| 111 | } |
| 112 | if (c == (wint_t)Auteur[j] && j < wcslen(Auteur) - 1) { |
| 113 | c = fgetwc(source); |
| 114 | token[tokenFound].value[i] = c; |
| 115 | i++; |
| 116 | j++; |
| 117 | goto MC1; |
| 118 | } else { |
| 119 | c = fgetwc(source); |
| 120 | token[tokenFound].value[i] = c; |
| 121 | i++; |
| 122 | goto MC2; |
| 123 | } |
| 124 | |
| 125 | S1SS1: |
| 126 | if (c == L'=') { |
| 127 | c = fgetwc(source); |
| 128 | token[tokenFound].value[i] = c; |
| 129 | i++; |
| 130 | goto SS2; |
| 131 | } |
| 132 | if (isSeparator() || c == WEOF) { |
| 133 | goto SECTION; |
| 134 | } |
| 135 | |
| 136 | SS2: |
| 137 | if (isSeparator() || c == WEOF) { |
| 138 | goto SSECTION; |
| 139 | } |
| 140 | |
| 141 | SECTION: |
| 142 | tokenType = SECTION; |
| 143 | return 1; |
| 144 | |
| 145 | SSECTION: |
| 146 | tokenType = SSECTION; |
| 147 | return 1; |
| 148 | |
| 149 | M1: |
| 150 | if (istAlpha()) { |
| 151 | c = fgetwc(source); |
| 152 | token[tokenFound].value[i] = c; |
| 153 | i++; |
| 154 | goto M1; |
| 155 | } |
| 156 | if (isSeparator() || c == WEOF) { |
| 157 | goto MOT; |
| 158 | } |
| 159 | |
| 160 | initLV1: |
| 161 | if (c == L' ' || c == L'\t') { |
| 162 | c = fgetwc(source); |
| 163 | token[tokenFound].value[i] = c; |
| 164 | i++; |
| 165 | goto initLV1; |
| 166 | } |
| 167 | if (c == L'\n') { |
| 168 | c = fgetwc(source); |
| 169 | token[tokenFound].value[i] = c; |
| 170 | i++; |
| 171 | goto initLV1LV2; |
| 172 | } |
| 173 | if (istAlpha()) { |
| 174 | c = fgetwc(source); |
| 175 | token[tokenFound].value[i] = c; |
| 176 | i++; |
| 177 | goto M1; |
| 178 | } |
| 179 | if (c == L'=') { |
| 180 | c = fgetwc(source); |
| 181 | token[tokenFound].value[i] = c; |
| 182 | i++; |
| 183 | goto S1SS1; |
| 184 | } |
| 185 | if (c == L'>') { |
| 186 | c = fgetwc(source); |
| 187 | token[tokenFound].value[i] = c; |
| 188 | i++; |
| 189 | goto MC1; |
| 190 | } |
| 191 | if (c == WEOF) { |
| 192 | goto FIN; |
| 193 | } |
| 194 | |
| 195 | initLV1LV2: |
| 196 | if (isSeparator()) { |
| 197 | c = fgetwc(source); |
| 198 | token[tokenFound].value[i] = c; |
| 199 | i++; |
| 200 | goto initLV1LV2; |
| 201 | } |
| 202 | if (istAlpha()) { |
| 203 | goto NPARA; |
| 204 | } |
| 205 | if (c == L'>') { |
| 206 | c = fgetwc(source); |
| 207 | token[tokenFound].value[i] = c; |
| 208 | i++; |
| 209 | goto MC1; |
| 210 | } |
| 211 | if (c == L'=') { |
| 212 | c = fgetwc(source); |
| 213 | token[tokenFound].value[i] = c; |
| 214 | i++; |
| 215 | goto S1SS1; |
| 216 | } |
| 217 | if (c == WEOF) { |
| 218 | goto FIN; |
| 219 | } |
| 220 | |
| 221 | NPARA: |
| 222 | tokenType = NPARA; |
| 223 | return 1; |
| 224 | |
| 225 | MOT: |
| 226 | tokenType = MOT; |
| 227 | return 1; |
| 228 | |
| 229 | MC2: |
| 230 | if (isSeparator() || c == WEOF) { |
| 231 | goto MOTCLE; |
| 232 | } |
| 233 | |
| 234 | MOTCLE: |
| 235 | tokenType = MOTCLE; |
| 236 | return 1; |
| 237 | |
| 238 | FIN: |
| 239 | tokenType = FIN; |
| 240 | return 1; |
| 241 | |
| 242 | error: |
| 243 | tokenType = FIN; |
| 244 | return -1; |
| 245 | } |
| 246 | |
| 247 | int main() { |
| 248 | |
| 249 | // Ouvre le fichier test.txt en lecture seulement (le fichier doit exister) : |
| 250 | source = fopen("test.txt", "r"); |
| 251 | // Cree et ouvre un fichier target.html en lecture/ecriture |
| 252 | // avec suppression du contenu au prealable : |
| 253 | target = fopen("target.html", "w+"); |
| 254 | |
| 255 | if (source == NULL) { |
| 256 | printf("Impossible d'ouvrir le fichier source\n"); |
| 257 | return -1; |
| 258 | } |
| 259 | |
| 260 | if (target == NULL) { |
| 261 | printf("Impossible d'ouvrir le fichier target\n"); |
| 262 | return -1; |
| 263 | } |
| 264 | |
| 265 | do { |
| 266 | c = fgetwc(source); // lecture du caractere suivant du fichier source |
| 267 | token[tokenFound].value[i] = c; |
| 268 | i++; |
| 269 | int scanrt = scanner(); |
| 270 | if (scanrt == -1) { |
| 271 | wprintf(L"Scanner error with token value: %ls\n", token[tokenFound].value); |
| 272 | exit(EXIT_FAILURE); |
| 273 | } |
| 274 | if (c != WEOF) { |
| 275 | wprintf(L"Token type found: %s with value: %ls\n", tokenTypestr[tokenType], token[tokenFound].value); |
| 276 | } else { |
| 277 | wprintf(L"Token type found: %s\n", tokenTypestr[tokenType]); |
| 278 | } |
| 279 | token[tokenFound].type = tokenTypestr[tokenType]; |
| 280 | tokenFound++; |
| 281 | // reinit token.value array counter |
| 282 | i = 0; |
| 283 | //} while (c != WEOF); // tant que la fin du fichier n'est pas atteinte |
| 284 | } while (!feof(source)); // tant que la fin du fichier n'est pas atteinte |
| 285 | |
| 286 | if (source != NULL) fclose(source); // fermeture du fichier source |
| 287 | if (target != NULL) fclose(target); // fermeture du fichier target |
| 288 | |
| 289 | return 0; |
| 290 | } |