-
Notifications
You must be signed in to change notification settings - Fork 6
Expand file tree
/
Copy pathCGTFile.cpp
More file actions
384 lines (294 loc) · 8.76 KB
/
Copy pathCGTFile.cpp
File metadata and controls
384 lines (294 loc) · 8.76 KB
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
/***************************************************************************
CGTFile.cpp -
Encapsulates the Compiled Grammar Table File
read operations and structures.
-------------------
begin : Fri May 31 00:53:11 CEST 2002
copyright : (C) 2002 by Manuel Astudillo
***************************************************************************/
/***************************************************************************
* *
* This program is free software; you can redistribute it and/or modify *
* it under the terms of the GNU Lesser General Public License as *
* published by the Free Software Foundation; either version 2 of the *
* License, or (at your option) any later version. *
* *
***************************************************************************/
#include "CGTFile.h"
#include "GrammarInfo.h"
CGTFile::CGTFile () {
gInfo = NULL;
errorString = NULL;
ruleTable = NULL;
symbolTable = NULL;
stateTable = NULL;
LALRTable = NULL;
characterSetTable = NULL;
theDFA = NULL;
theLALR = NULL;
}
CGTFile::~CGTFile () {
delete gInfo;
delete [] errorString;
// Delete tables
delete symbolTable;
delete stateTable;
delete LALRTable;
delete ruleTable;
delete characterSetTable;
delete theDFA;
delete theLALR;
}
bool CGTFile::load (char *filename) {
ifstream cgtStream;
cgtStream.open (filename, ifstream::in | ifstream::binary);
if (((void*) cgtStream) == NULL) {
return false;
}
bool result = load (&cgtStream);
cgtStream.close();
return result;
}
bool CGTFile::load (ifstream *myStream) {
int i;
EntryStruct entry;
theStream = myStream;
// Read Header
//////////////
header = readUnicodeString();
// Read Records
////////////////
unsigned char recordType;
integer nbrEntries;
integer index;
while (!theStream->eof()) {
// Read record type & number of entries
theStream->read ((char*)&recordType, 1);
if (theStream->fail()) {
if (theStream->eof()) {
break;
} else {
return false;
}
}
theStream->read ((char*) &nbrEntries, 2);
//Convert to little endian if needed.
nbrEntries = EndianConversion(nbrEntries);
//wprintf (L"Record Type: %i\n", recordType);
//wprintf (L"Entries: %i\n", nbrEntries);
if (recordType != 77) {
errorString = "Record type is not supported\n";
return false;
}
// Read the type of content
byte contentType;
readEntry (&entry);
contentType = entry.vByte;
//wprintf (L"Content Type: %d\n", contentType);
switch (contentType) {
// Parameters Record
case 'P':
delete gInfo;
gInfo = new GrammarInfo ();
// read name
readEntry (&entry);
gInfo->name = entry.vString;
// read version
readEntry (&entry);
gInfo->version = entry.vString;
// read Author
readEntry (&entry);
gInfo->author = entry.vString;
// read About
readEntry (&entry);
gInfo->about = entry.vString;
// Case
readEntry (&entry);
caseSensitive = entry.vBool;
// start symbol
readEntry (&entry);
startSymbol = entry.vInteger;
break;
// Table Counts
case 'T' :
readEntry (&entry);
nbrSymbolTable = entry.vInteger;
// Delete & Create a Symbol Table
delete symbolTable;
symbolTable = new SymbolTable (nbrSymbolTable);
readEntry (&entry);
nbrCharacterSets = entry.vInteger;
// Delete & Create a Character Sets Table
delete characterSetTable;
characterSetTable = new CharacterSetTable (nbrCharacterSets);
// Delete & Create a Rule Table
readEntry (&entry);
nbrRuleTable = entry.vInteger;
delete ruleTable;
ruleTable = new RuleTable (nbrRuleTable);
// Delete & Create a DFAStateTable
readEntry (&entry);
nbrDFATable = entry.vInteger;
delete stateTable;
stateTable = new DFAStateTable (nbrDFATable);
// Delete & Create a LALR Table
readEntry (&entry);
nbrLALRTable = entry.vInteger;
delete LALRTable;
LALRTable = new LALRStateTable (nbrLALRTable);
break;
// Character Set Table Entry
case 'C' :
readEntry (&entry);
index = entry.vInteger;
readEntry (&entry);
characterSetTable->characters[index] = entry.vString;
break;
// Symbol Table Entry
case 'S' :
readEntry (&entry);
index = entry.vInteger;
readEntry (&entry);
symbolTable->symbols[index].name = entry.vString;
readEntry (&entry);
symbolTable->symbols[index].kind = (SymbolType) entry.vInteger;
break;
// Rule
case 'R' :
readEntry (&entry);
index = entry.vInteger;
ruleTable->rules[index].ruleIndex = index;
readEntry (&entry);
ruleTable->rules[index].symbolIndex = entry.vInteger;
// Read empty field
readEntry (&entry);
// Read symbols for this rule (nonTerminal -> symbol0 symbol1 ... symboln)
for (i=0; i < nbrEntries-4; i++) {
readEntry (&entry);
// ruleTable->rules[index].symbols.push_back (entry.vInteger);
RuleStruct *rst = &ruleTable->rules[index];
vector <integer> *s = &rst->symbols;
s->push_back (entry.vInteger);
}
break;
// Initial States
case 'I' :
readEntry(&entry);
DFAInit = entry.vInteger;
readEntry (&entry);
LALRInit = entry.vInteger;
break;
// DFA State Entry
case 'D':
readEntry (&entry);
index = entry.vInteger;
// create a new State an insert it in the table
readEntry (&entry);
stateTable->states[index].accept = entry.vBool;
readEntry(&entry);
stateTable->states[index].acceptIndex = entry.vInteger;
readEntry(&entry);
Edge edge;
for (i=0; i < nbrEntries-5; i+=3) {
readEntry(&entry);
edge.characterSetIndex = entry.vInteger;
readEntry(&entry);
edge.targetIndex = entry.vInteger;
readEntry(&entry);
stateTable->states[index].edges.push_back(edge);
}
break;
// LALR State entry
case 'L':
readEntry(&entry);
index = entry.vInteger;
readEntry(&entry);
Action action;
for (i=0; i < nbrEntries-3; i+=4) {
readEntry(&entry);
action.symbolIndex = entry.vInteger;
readEntry(&entry);
action.action = entry.vInteger;
readEntry(&entry);
action.target = entry.vInteger;
readEntry(&entry);
LALRTable->states[index].actions.push_back(action);
}
break;
}
}
return true;
}
/*
Reads an entry in a record
*/
void CGTFile::readEntry (EntryStruct *entry) {
char tmpChar;
char dataType;
theStream->get (dataType);
if (theStream->fail()) {
wprintf (L"Error reading entry\n");
} else {
switch (dataType) {
case 'E': break;
case 'B':
theStream->get (tmpChar);
if (tmpChar) {
entry->vBool = true;
} else {
entry->vBool = false;
}
break;
case 'b':
theStream->read ((char*) &entry->vByte, 1);
break;
case 'I':
theStream->read ((char*) &entry->vInteger, 2);
entry->vInteger = EndianConversion(entry->vInteger);
break;
case 'S':
entry->vString = readUnicodeString();
break;
}
}
}
/*
Reads a Unicode String
*/
wstring CGTFile::readUnicodeString () {
char readChar[2];
wstring str;
theStream->read ((char*) &readChar, 2);
while ((readChar[0] != 0) && (!theStream->eof())){
str.append (1, (wchar_t) ((readChar[1] << 8) | readChar[0]));
theStream->read ((char*) &readChar, 2);
}
return str;
}
GrammarInfo *CGTFile::getInfo () {
return gInfo;
}
DFA *CGTFile::getScanner () {
delete theDFA;
theDFA = new DFA (stateTable, symbolTable,
characterSetTable, DFAInit, caseSensitive);
return theDFA;
}
LALR *CGTFile::getParser () {
delete theLALR;
theLALR = new LALR (LALRTable, symbolTable, ruleTable, LALRInit);
return theLALR;
}
void CGTFile::printInfo () {
// Prints the info of this grammar
wprintf (L"Grammar Information\n");
wprintf (L"Name: ");
wprintf (gInfo->name.c_str());
wprintf (L"\nVersion: ");
wprintf (gInfo->version.c_str());
wprintf (L"\nAuthor: ");
wprintf (gInfo->author.c_str());
wprintf (L"\nAbout: ");
wprintf (gInfo->about.c_str());
wprintf (L"\n");
}