aboutsummaryrefslogtreecommitdiff
path: root/engines/sci/scicore/vocabulary.cpp
blob: af63a9803a360ef40da0117e314dc54da4786b07 (plain)
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
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
/* ScummVM - Graphic Adventure Engine
 *
 * ScummVM is the legal property of its developers, whose names
 * are too numerous to list here. Please refer to the COPYRIGHT
 * file distributed with this source distribution.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.

 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.

 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 *
 * $URL$
 * $Id$
 *
 */

// Main vocabulary support functions and word lookup

#include "sci/scicore/vocabulary.h"
#include "sci/scicore/resource.h"
#include "sci/engine/state.h"
#include "sci/engine/kernel.h"

namespace Sci {

int vocab_version;

#define VOCAB_RESOURCE_PARSE_TREE_BRANCHES vocab_version == 1 ? \
					   VOCAB_RESOURCE_SCI1_PARSE_TREE_BRANCHES : \
					   VOCAB_RESOURCE_SCI0_PARSE_TREE_BRANCHES

#define VOCAB_RESOURCE_SUFFIX_VOCAB vocab_version==1 ? \
				    VOCAB_RESOURCE_SCI1_SUFFIX_VOCAB : \
				    VOCAB_RESOURCE_SCI0_SUFFIX_VOCAB


/*
// These strange names were taken from an SCI01 interpreter
const char *class_names[] = {"",
                             "",
                             "conj",   // conjunction
                             "ass",    // ?
                             "pos",    // preposition ?
                             "art",    // article
                             "adj",    // adjective
                             "pron",   // pronoun
                             "noun",   // noun
                             "auxv",   // auxillary verb
                             "adv",    // adverb
                             "verb",   // verb
                             "",
                             "",
                             "",
                             ""
                            };
*/

bool vocab_get_words(ResourceManager *resmgr, WordMap &words) {

	char currentword[256] = ""; // They're not going to use words longer than 255 ;-)
	int currentwordpos = 0;

	Resource *resource;

	// First try to load the SCI0 vocab resource.
	resource = resmgr->findResource(kResourceTypeVocab, VOCAB_RESOURCE_SCI0_MAIN_VOCAB, 0);
	vocab_version = 0;

	if (!resource) {
		warning("SCI0: Could not find a main vocabulary, trying SCI01");
		resource = resmgr->findResource(kResourceTypeVocab, VOCAB_RESOURCE_SCI1_MAIN_VOCAB, 0);
		vocab_version = 1;
	}

	if (!resource) {
		warning("SCI1: Could not find a main vocabulary");
		return false; // NOT critical: SCI1 games and some demos don't have one!
	}

	unsigned int seeker;
	if (vocab_version == 1)
		seeker = 255 * 2; // vocab.900 starts with 255 16-bit pointers which we don't use
	else
		seeker = 26 * 2; // vocab.000 starts with 26 16-bit pointers which we don't use

	if (resource->size < seeker) {
		fprintf(stderr, "Invalid main vocabulary encountered: Too small\n");
		return false;
		// Now this ought to be critical, but it'll just cause parse() and said() not to work
	}

	words.clear();

	while (seeker < resource->size) {
		byte c;

		currentwordpos = resource->data[seeker++]; // Parts of previous words may be re-used

		if (vocab_version == 1) {
			c = 1;
			while (seeker < resource->size && currentwordpos < 255 && c) {
				c = resource->data[seeker++];
				currentword[currentwordpos++] = c;
			}
			if (seeker == resource->size) {
				warning("SCI1: Vocabulary not usable, disabling");
				words.clear();
				return false;
			}
		} else {
			do {
				c = resource->data[seeker++];
				currentword[currentwordpos++] = c & 0x7f; // 0x80 is used to terminate the string
			} while (c < 0x80);
		}

		currentword[currentwordpos] = 0;

		// Now decode class and group:
		c = resource->data[seeker + 1];
		ResultWord newWord;
		newWord._class = ((resource->data[seeker]) << 4) | ((c & 0xf0) >> 4);
		newWord._group = (resource->data[seeker + 2]) | ((c & 0x0f) << 8);

		// Add the word to the list
		words[currentword] = newWord;

		seeker += 3;
	}

	return true;
}

const char *vocab_get_any_group_word(int group, const WordMap &words) {
	if (group == VOCAB_MAGIC_NUMBER_GROUP)
		return "{number}";

	for (WordMap::const_iterator i = words.begin(); i != words.end(); ++i)
		if (i->_value._group == group)
			return i->_key.c_str();

	return "{invalid}";
}

bool vocab_get_suffixes(ResourceManager *resmgr, SuffixList &suffixes) {
	Resource *resource = resmgr->findResource(kResourceTypeVocab, VOCAB_RESOURCE_SUFFIX_VOCAB, 1);
	unsigned int seeker = 1;

	if (!resource) {
		warning("Could not find suffix vocabulary");
		return false; // Not critical
	}

	while ((seeker < resource->size - 1) && (resource->data[seeker + 1] != 0xff)) {
		suffix_t suffix;

		suffix.alt_suffix = (const char *)resource->data + seeker;
		suffix.alt_suffix_length = strlen(suffix.alt_suffix);
		seeker += suffix.alt_suffix_length + 1; // Hit end of string

		suffix.class_mask = (int16)READ_BE_UINT16(resource->data + seeker);
		seeker += 2;

		// Beginning of next string - skip leading '*'
		seeker++;

		suffix.word_suffix = (const char *)resource->data + seeker;
		suffix.word_suffix_length = strlen(suffix.word_suffix);
		seeker += suffix.word_suffix_length + 1;

		suffix.result_class = (int16)READ_BE_UINT16(resource->data + seeker);
		seeker += 3; // Next entry

		suffixes.push_back(suffix);
	}

	return true;
}

void vocab_free_suffixes(ResourceManager *resmgr, SuffixList &suffixes) {
	resmgr->unlockResource(resmgr->findResource(kResourceTypeVocab, VOCAB_RESOURCE_SUFFIX_VOCAB, 0),
	                     VOCAB_RESOURCE_SUFFIX_VOCAB, kResourceTypeVocab);

	suffixes.clear();
}

bool vocab_get_branches(ResourceManager * resmgr, Common::Array<parse_tree_branch_t> &branches) {
	Resource *resource = resmgr->findResource(kResourceTypeVocab, VOCAB_RESOURCE_PARSE_TREE_BRANCHES, 0);

	branches.clear();

	if (!resource) {
		fprintf(stderr, "No parser tree data found!\n");
		return false;
	}

	int branches_nr = resource->size / 20;

	if (branches_nr == 0) {
		fprintf(stderr, "Parser tree data is empty!\n");
		return false;
	}

	branches.resize(branches_nr);

	for (int i = 0; i < branches_nr; i++) {
		byte *base = resource->data + i * 20;

		branches[i].id = (int16)READ_LE_UINT16(base);

		for (int k = 0; k < 9; k++)
			branches[i].data[k] = READ_LE_UINT16(base + 2 + 2 * k);

		branches[i].data[9] = 0; // Always terminate
	}

	if (!branches[branches_nr - 1].id) // branch lists may be terminated by empty rules
		branches.remove_at(branches_nr - 1);

	return true;
}


ResultWord vocab_lookup_word(const char *word, int word_len, const WordMap &words, const SuffixList &suffixes) {
	Common::String tempword(word, word_len);

	// Remove all dashes from tempword
	for (uint i = 0; i < tempword.size(); ) {
		if (tempword[i] == '-')
			tempword.deleteChar(i);
		else
			++i;
	}

	// Look it up:
	WordMap::iterator dict_word = words.find(tempword);

	// Match found? Return it!
	if (dict_word != words.end()) {
		return dict_word->_value;
	}

	// Now try all suffixes
	for (SuffixList::const_iterator suffix = suffixes.begin(); suffix != suffixes.end(); ++suffix)
		if (suffix->alt_suffix_length <= word_len) {

			int suff_index = word_len - suffix->alt_suffix_length;
			// Offset of the start of the suffix

			if (scumm_strnicmp(suffix->alt_suffix, word + suff_index, suffix->alt_suffix_length) == 0) { // Suffix matched!
				// Terminate word at suffix start position...:
				Common::String tempword2(word, MIN(word_len, suff_index));

				// ...and append "correct" suffix
				tempword2 += Common::String(suffix->word_suffix, suffix->word_suffix_length);

				dict_word = words.find(tempword2);

				if ((dict_word != words.end()) && (dict_word->_value._class & suffix->class_mask)) { // Found it?
					// Use suffix class
					ResultWord tmp = dict_word->_value;
					tmp._class = suffix->result_class;
					return tmp;
				}
			}
		}

	// No match so far? Check if it's a number.

	ResultWord retval = { -1, -1 };
	char *tester;
	if ((strtol(tempword.c_str(), &tester, 10) >= 0) && (*tester == '\0')) { // Do we have a complete number here?
		ResultWord tmp = { VOCAB_CLASS_NUMBER, VOCAB_MAGIC_NUMBER_GROUP };
		retval = tmp;
	}

	return retval;
}

void vocab_decypher_said_block(EngineState *s, byte *addr) {
	int nextitem;

	do {
		nextitem = *addr++;

		if (nextitem < 0xf0) {
			nextitem = nextitem << 8 | *addr++;
			sciprintf(" %s[%03x]", vocab_get_any_group_word(nextitem, s->_parserWords), nextitem);

			nextitem = 42; // Make sure that group 0xff doesn't abort
		} else switch (nextitem) {
			case 0xf0:
				sciprintf(" ,");
				break;
			case 0xf1:
				sciprintf(" &");
				break;
			case 0xf2:
				sciprintf(" /");
				break;
			case 0xf3:
				sciprintf(" (");
				break;
			case 0xf4:
				sciprintf(" )");
				break;
			case 0xf5:
				sciprintf(" [");
				break;
			case 0xf6:
				sciprintf(" ]");
				break;
			case 0xf7:
				sciprintf(" #");
				break;
			case 0xf8:
				sciprintf(" <");
				break;
			case 0xf9:
				sciprintf(" >");
				break;
			case 0xff:
				break;
			}
	} while (nextitem != 0xff);

	sciprintf("\n");
}


#ifdef SCI_SIMPLE_SAID_CODE

static const short _related_words[][2] = { // 0 is backwards, 1 is forward
	{0x800, 0x180}, // preposition
	{0x000, 0x180}, // article
	{0x000, 0x180}, // adjective
	{0x800, 0x000}, // pronoun
	{0x800, 0x180}, // noun
	{0x000, 0x800}, // auxiliary verb
	{0x800, 0x800}, // adverb
	{0x000, 0x180}, // verb
	{0x000, 0x180} // number
};

int vocab_build_simple_parse_tree(parse_tree_node_t *nodes, WordMap &words) {
	int i, length, pos = 0;

	for (i = 0; i < words.size(); ++i) {
		if (words[i]._class != VOCAB_CLASS_ANYWORD) {
			nodes[pos].type = words[i]._class;
			nodes[pos].content.value = words[i]._group;
			pos += 2; // Link information is filled in below
		}
	}
	nodes[pos].type = -1; // terminate
	length = pos >> 1;

	// now find all referenced words
#ifdef SCI_SIMPLE_SAID_DEBUG
	sciprintf("Semantic references:\n");
#endif

	for (i = 0; i < length; i++) {
		int j;
		int searchmask;
		int type;

		pos = (i << 1);
		type = sci_ffs(nodes[pos].type);

		if (type) {
			int found = -1;

			type -= 5; // 1 because ffs starts counting at 1, 4 because nodes[pos].type is a nibble off
			if (type < 0)
				type = 0;
#ifdef SCI_SIMPLE_SAID_DEBUG
			sciprintf("#%d: Word %04x: type %04x\n", i, nodes[pos].content.value, type);
#endif

			// search backwards
			searchmask = _related_words[type][0];
			if (searchmask) {
				for (j = i - 1; j >= 0; j--)
					if (nodes[j << 1].type & searchmask) {
						found = j << 1;
						break;
					}
			}
			nodes[pos+1].content.branches[0] = found;
#ifdef SCI_SIMPLE_SAID_DEBUG
			if (found > -1)
				sciprintf("  %d <\n", found >> 1);
#endif

			// search forward
			found = -1;
			searchmask = _related_words[type][1];
			if (searchmask) {
				for (j = i + 1; j < length; j++)
					if (nodes[j << 1].type & searchmask) {
						found = j << 1;
						break;
					}
			}
#ifdef SCI_SIMPLE_SAID_DEBUG
			if (found > -1)
				sciprintf("  > %d\n", found >> 1);
#endif
		} else {
#ifdef SCI_SIMPLE_SAID_DEBUG
			sciprintf("#%d: Untypified word\n", i); /* Weird, but not fatal */
#endif
			nodes[pos + 1].content.branches[0] = -1;
			nodes[pos + 1].content.branches[1] = -1;
		}
	}
#ifdef SCI_SIMPLE_SAID_DEBUG
	sciprintf("/Semantic references.\n");
#endif

	return 0;
}
#endif

bool vocab_tokenize_string(ResultWordList &retval, const char *sentence, const WordMap &words,
	const SuffixList &suffixes, char **error) {
	const char *lastword = sentence;
	int pos_in_sentence = 0;
	char c;
	int wordlen = 0;

	*error = NULL;

	do {

		c = sentence[pos_in_sentence++];

		if (isalnum(c) || (c == '-' && wordlen))
			++wordlen;
		// Continue on this word */
		// Words may contain a '-', but may not
		// start with one.
		else {
			if (wordlen) { // Finished a word?

				ResultWord lookup_result =
				    vocab_lookup_word(lastword, wordlen, words, suffixes);
				// Look it up

				if (lookup_result._class == -1) { // Not found?
					*error = (char *)calloc(wordlen + 1, 1);
					strncpy(*error, lastword, wordlen); // Set the offending word
					retval.clear();
					return false; // And return with error
				}

				// Copy into list
				retval.push_back(lookup_result);
			}

			lastword = sentence + pos_in_sentence;
			wordlen = 0;
		}

	} while (c); // Until terminator is hit

	return true;
}

void _vocab_recursive_ptree_dump_treelike(parse_tree_node_t *nodes, int nr, int prevnr) {
	if ((nr > VOCAB_TREE_NODES)/* || (nr < prevnr)*/) {
		sciprintf("Error(%04x)", nr);
		return;
	}

	if (nodes[nr].type == PARSE_TREE_NODE_LEAF)
		//sciprintf("[%03x]%04x", nr, nodes[nr].content.value);
		sciprintf("%x", nodes[nr].content.value);
	else {
		int lbranch = nodes[nr].content.branches[0];
		int rbranch = nodes[nr].content.branches[1];
		//sciprintf("<[%03x]", nr);
		sciprintf("<");

		if (lbranch)
			_vocab_recursive_ptree_dump_treelike(nodes, lbranch, nr);
		else
			sciprintf("NULL");

		sciprintf(",");

		if (rbranch)
			_vocab_recursive_ptree_dump_treelike(nodes, rbranch, nr);
		else
			sciprintf("NULL");

		sciprintf(">");
	}
}

void _vocab_recursive_ptree_dump(parse_tree_node_t *nodes, int nr, int prevnr, int blanks) {
	int lbranch = nodes[nr].content.branches[0];
	int rbranch = nodes[nr].content.branches[1];
	int i;

	if (nodes[nr].type == PARSE_TREE_NODE_LEAF) {
		sciprintf("vocab_dump_parse_tree: Error: consp is nil for element %03x\n", nr);
		return;
	}

	if ((nr > VOCAB_TREE_NODES)/* || (nr < prevnr)*/) {
		sciprintf("Error(%04x))", nr);
		return;
	}

	if (lbranch) {
		if (nodes[lbranch].type == PARSE_TREE_NODE_BRANCH) {
			sciprintf("\n");
			for (i = 0; i < blanks; i++)
				sciprintf("    ");
			sciprintf("(");
			_vocab_recursive_ptree_dump(nodes, lbranch, nr, blanks + 1);
			sciprintf(")\n");
			for (i = 0; i < blanks; i++)
				sciprintf("    ");
		} else
			sciprintf("%x", nodes[lbranch].content.value);
		sciprintf(" ");
	}/* else sciprintf ("nil");*/

	if (rbranch) {
		if (nodes[rbranch].type == PARSE_TREE_NODE_BRANCH)
			_vocab_recursive_ptree_dump(nodes, rbranch, nr, blanks);
		else
			sciprintf("%x", nodes[rbranch].content.value);
	}/* else sciprintf("nil");*/
}

void vocab_dump_parse_tree(const char *tree_name, parse_tree_node_t *nodes) {
	//_vocab_recursive_ptree_dump_treelike(nodes, 0, 0);
	sciprintf("(setq %s \n'(", tree_name);
	_vocab_recursive_ptree_dump(nodes, 0, 0, 1);
	sciprintf("))\n");
}

void vocab_synonymize_tokens(ResultWordList &words, const SynonymList &synonyms) {
	if (synonyms.empty())
		return; // No synonyms: Nothing to check

	for (ResultWordList::iterator i = words.begin(); i != words.end(); ++i)
		for (SynonymList::const_iterator sync = synonyms.begin(); sync != synonyms.end(); ++sync)
			if (i->_group == sync->replaceant)
				i->_group = sync->replacement;
}

} // End of namespace Sci