-
Notifications
You must be signed in to change notification settings - Fork 0
/
parser.c
399 lines (344 loc) · 11.5 KB
/
parser.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
//Jlonge421
#define charLimit 1500
#define NUMSYM 12
#define NORW 14
#define CMAX 12
#define DMAX 5
#define MAXCLENGTH 500
#define MSYMSIZE 100
#include <stdio.h>
#include <string.h>
#include <ctype.h>
#include <limits.h>
#include <stdlib.h>
//#include <malloc.h>
typedef enum {
skipsym = 1, identsym, numbersym, plussym, minussym, multsym, slashsym, oddsym, eqsym, neqsym, lessym, leqsym, gtrsym, geqsym, lparentsym, rparentsym, commasym, semicolonsym, periodsym, becomessym, beginsym, endsym, ifsym, thensym, whilesym, dosym, callsym, constsym, varsym, procsym, writesym, readsym , elsesym } token_type;
typedef struct specialSymbols{
char symbol;
int token;
} specialSymbols;
typedef struct reservedWords{
char word[25];
int token;
} reservedWords;
typedef struct lexemeTable{
char lexeme[CMAX];
int numLex;
int tokenType;
} lexemeTable;
// Global Variables
char lexTemp[charLimit] = "";
char lexOutput[charLimit*3] = "";
void errorMessage(FILE *inFile, FILE *outFile, int errorCode);
int isComment(char src[], int idx, int inx);
void displayLexeme(lexemeTable lexemes[], int lexemeCount, FILE *outFile);
int main(int argc, char *argv[]) {
printf("\n");
specialSymbols ssym[NUMSYM] = {
{'+', plussym},
{'-', minussym},
{'*', multsym},
{'/', slashsym},
{'(', lparentsym},
{')', rparentsym},
{'=', eqsym},
{',', commasym},
{'.', periodsym},
{'<', lessym},
{'>', gtrsym},
{';', semicolonsym},
};
reservedWords rwords[NORW] = {
{"const", constsym},
{"var", varsym},
{"procedure", procsym},
{"call", callsym},
{"if", ifsym},
{"then", thensym},
{"else", elsesym},
{"while", whilesym},
{"do", dosym},
{"read", readsym},
{"write", writesym},
{"odd", oddsym},
{"begin", beginsym},
{"end", endsym}
};
lexemeTable lexemes[MAXCLENGTH];
// DEV MODE
int devMode = 0;
if (argc == 3){
if (!strcmp(argv[2], "-dev")){
devMode = 1;
printf("~~~~~DEV MODE ENABLED~~~~~\n");
}}
//open input file
FILE* inFile;
inFile = fopen(argv[1], "r");
if (inFile == NULL) {
printf("file not found.");
return 0;
}
//open output file
FILE* outFile;
outFile = fopen("outParse.txt", "w");
token_type token_type;
//~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
char src[charLimit];
char temp;
int inx = 0;
printf("\n");
printf("Source Program:\n");
printf("\n");
// Source Program input for loop
for(int i=0; i < charLimit; i++){
src[i] = fgetc(inFile);
inx++;
if ( feof(inFile))
break;
// Print out Source Program
printf("%c", src[i]);
}
// Ending array where it should end
inx--;
src[inx]='\0';
printf("contained in file outParse.txt\n");
printf("\n");
printf("Lexeme Table:\n");
printf("lexeme\ttokentype\n");
printf("\n");
/*
if (devMode == 1){
printf("**Entering src** Press K for next\n");
printf("inx = %d\n", inx);
for (int i=0; i<inx; i++) {
printf("%c", src[i]);
}
}
For later me:
ok, so basically, we can seperate everything by delimeters (including whitespaces)
dont forget about enumators and all that shit
and dont forget about the trauma you endured on mar 7.
*/
// ~~~~~Lexical Analysis~~~~~
int idx = 0;
int commentIdx = 0;
char inString[charLimit] = "";
int valSym = 0;
int symbolFound = 0;
int lexemeCount = 0;
char digitTemp[charLimit] = "";
char currentWord[charLimit] = "";
do {
if( isspace(src[idx]) ){
idx++;
if (devMode == 1)
printf("WS detected at idx %d;\n", idx-1);
} else if ( ispunct(src[idx]) ){
commentIdx = isComment(src, idx, inx);
if (devMode == 1 && commentIdx > 0)
printf("Comment detected at idx %d;\n", idx);
if (commentIdx != -1){
idx = commentIdx+1;
}
for(int i=0; i < NUMSYM; i++){
if (src[idx] == ssym[i].symbol || src[idx] == ':' || src[idx] == '!'){
symbolFound = 1;
lexemes[lexemeCount].lexeme[0] = src[idx];
if ((idx + 1) < inx && ispunct(src[idx+1])){
switch(src[idx]){
case '<':
if(src[idx+1]== '>'){
lexemes[lexemeCount].tokenType = neqsym;
lexemes[lexemeCount].lexeme[1] = src[idx++];
} else if (src[idx+1] == '='){
lexemes[lexemeCount].tokenType = leqsym;
lexemes[lexemeCount].lexeme[1] = src[idx++];
} else
lexemes[lexemeCount].tokenType = ssym[i].token;
break;
case '>': // looking for >=
if(src[idx+1] == '='){
lexemes[lexemeCount].tokenType = becomessym;
lexemes[lexemeCount].lexeme[1] = src[idx++];
} else
lexemes[lexemeCount].tokenType = ssym[i].token;
break;
case ':': //looking for :=
if(src[idx+1]== '='){
lexemes[lexemeCount].tokenType = becomessym;
lexemes[lexemeCount].lexeme[1] = src[idx++];
} else
errorMessage(inFile, outFile, 1);
break;
default:
lexemes[lexemeCount].tokenType = ssym[i].token;
break;
}
}
else{
if(src[idx] == ':' || src[idx] == '!')
errorMessage(inFile, outFile, 1);
lexemes[lexemeCount].tokenType = ssym[i].token;
}
idx++;
lexemeCount++;
break;
}
}
if(!symbolFound)
errorMessage( inFile, outFile, 1);
}
else if (isalpha(src[idx])){
int letterCount = 0;
while (isalnum(src[idx])){
currentWord[letterCount] = src[idx];
idx++;
letterCount++;
}
currentWord[letterCount++] = '\0';
if(letterCount > CMAX)
errorMessage(inFile, outFile, 2);
else{
strcpy(lexemes[lexemeCount].lexeme, currentWord);
for(int i = 0; i < NORW; i++) //checking for keyword
{
if(strcmp(rwords[i].word, currentWord) == 0){
lexemes[lexemeCount].tokenType = rwords[i].token;
break;
} else
lexemes[lexemeCount].tokenType = identsym;
}
lexemeCount++;
}
} else if (isdigit(src[idx])){
int digitCount = 0;
while(isdigit(src[idx])){
digitTemp[digitCount] = src[idx];
idx++;
digitCount++;
}
digitTemp[digitCount++] = '\0';
if (isalpha(src[idx]))
errorMessage(inFile, outFile, 3);
else if(digitCount <= DMAX)
{
strcpy(lexemes[lexemeCount].lexeme, digitTemp);
lexemes[lexemeCount].numLex = atoi(digitTemp);
lexemes[lexemeCount].tokenType = numbersym;
lexemeCount++;
}
else
errorMessage(inFile, outFile, 4);
}
if(lexemes[lexemeCount-1].tokenType == numbersym){
sprintf(lexTemp, "%d", lexemes[lexemeCount - 1].numLex);
strcat(lexOutput, lexTemp);
fprintf(outFile, "%d", lexemes[lexemeCount - 1].numLex);
printf("%d", lexemes[lexemeCount - 1].numLex);
} else {
sprintf(lexTemp, "%s", lexemes[lexemeCount - 1].lexeme);
strcat(lexOutput, lexTemp);
fprintf(outFile, "%s", lexemes[lexemeCount - 1].lexeme);
printf("%s", lexemes[lexemeCount - 1].lexeme);
}
sprintf(lexTemp, "\t\t%d\n", lexemes[lexemeCount - 1].tokenType);
strcat(lexOutput, lexTemp);
fprintf(outFile, "\t\t%d\n", lexemes[lexemeCount - 1].tokenType);
printf("\t\t%d\n", lexemes[lexemeCount - 1].tokenType);
} while (idx < inx);
displayLexeme(lexemes, lexemeCount, outFile);
fclose(inFile);
fclose(outFile);
printf("\n");
return 0;
}
int isComment(char src[], int idx, int inx){
int isComment = 0;
if (src[idx]!='/' || idx++ == inx)
return -1;
if (src[idx] == '/' && src[idx++]== '*'){
//comment in action; find end and return it;
for (idx=idx+2; idx < inx; idx++){
if (src[idx]=='*' && idx++<inx)
if (src[idx++]=='/')
return idx;
}
}
return isComment;
}
void errorMessage(FILE *inFile, FILE *outFile, int errorCode)
{
char *message = "";
switch(errorCode){
case 1:
message = "Symbol does not exist";
case 2:
message = "Identifier is over 11 characters long";
break;
case 3:
message = "Identifiers cannot start with a number";
break;
case 4:
message = "Number is over 5 digits long";
break;
default:
break;
}
sprintf(lexTemp, "ERROR: %s\n", message);
strcat(lexOutput, lexTemp);
fprintf(outFile, "ERROR: %s\n", message);
printf("ERROR: %s\n", message);
fclose(inFile);
fclose(outFile);
exit(0);
}
void displayLexeme(lexemeTable lexemes[], int lexemeCount, FILE *outFile)
{
FILE *out = fopen("tokens.txt", "w");
if (out == NULL)
{
sprintf(lexTemp, "Unable to write tokens to file.");
strcat(lexOutput, lexTemp);
}
sprintf(lexTemp, "Lexeme List:\n");
strcat(lexOutput, lexTemp);
fprintf(outFile, "Lexeme List:\n");
printf("Lexeme List:\n");
for (int i = 0; i < lexemeCount; i++)
{
int alrPrint = 0;
sprintf(lexTemp, "%d ", lexemes[i].tokenType);
strcat(lexOutput, lexTemp);
fprintf(outFile, "%d ", lexemes[i].tokenType);
printf("%d ", lexemes[i].tokenType);
alrPrint = 1;
fprintf(out, "%d ", lexemes[i].tokenType);
//printf("%d ", lexemes[i].tokenType);
if (lexemes[i].tokenType == identsym)
{
sprintf(lexTemp, "%s ", lexemes[i].lexeme);
strcat(lexOutput, lexTemp);
fprintf(outFile, "%s ", lexemes[i].lexeme);
printf("%s ", lexemes[i].lexeme);
fprintf(out, "%s ", lexemes[i].lexeme);
//printf("%s ", lexemes[i].lexeme);
}
if (lexemes[i].tokenType == numbersym)
{
sprintf(lexTemp, "%d ", lexemes[i].numLex);
strcat(lexOutput, lexTemp);
fprintf(outFile, "%d ", lexemes[i].numLex);
printf("%d ", lexemes[i].numLex);
fprintf(out, "%d ", lexemes[i].numLex);
//printf("%d ", lexemes[i].numLex);
}
}
sprintf(lexTemp, "\n");
strcat(lexOutput, lexTemp);
fprintf(outFile, "\n");
printf("\n");
fprintf(out, "\n");
fclose(out);
}