summaryrefslogtreecommitdiff
path: root/BJC-Utils2/src/main/java/bjc/utils/gen/WeightedGrammar.java
blob: 623c212eb8ce26ccb94b2804bc8194ade8511109 (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
package bjc.utils.gen;

import java.util.Hashtable;
import java.util.Map;
import java.util.Random;
import java.util.Set;
import java.util.function.Function;

import bjc.utils.data.Pair;
import bjc.utils.funcdata.FunctionalList;

/**
 * A random grammar, where certain rules will come up more often than
 * others.
 * 
 * @author ben
 *
 * @param <E>
 *            The values that make up sentances of this grammar.
 */
public class WeightedGrammar<E> {
	/**
	 * The initial rule of the grammar
	 */
	protected String									initRule;

	/**
	 * The rules currently in this grammar
	 */
	protected Map<E, WeightedRandom<FunctionalList<E>>>	rules;

	/**
	 * The random number generator used for random numbers
	 */
	private Random										sr;

	/**
	 * All of the subgrammars of this grammar
	 */
	protected Map<E, WeightedGrammar<E>>				subgrammars;

	/**
	 * Create a new weighted grammar.
	 */
	public WeightedGrammar() {
		rules = new Hashtable<>();
		subgrammars = new Hashtable<>();
	}

	/**
	 * Create a new weighted grammar that uses the specified source of
	 * randomness.
	 */
	public WeightedGrammar(Random src) {
		this();

		sr = src;
	}

	/**
	 * Add a case to an already existing rule.
	 * 
	 * @param rule
	 *            The rule to add a case to.
	 * @param prob
	 *            The probability for this rule to be chosen.
	 * @param cse
	 *            The case being added.
	 */
	public void addCase(E rule, int prob, FunctionalList<E> cse) {
		rules.get(rule).addProb(prob, cse);
	}

	/**
	 * Add a alias for an existing subgrammar
	 * 
	 * @param name
	 *            The name of the subgrammar to alias
	 * @param alias
	 *            The alias of the subgrammar
	 * @return Whether the alias was succesfully created
	 */
	public boolean addGrammarAlias(E name, E alias) {
		if (subgrammars.containsKey(alias)) {
			return false;
		} else {
			if (subgrammars.containsKey(name)) {
				subgrammars.put(alias, subgrammars.get(name));
				return true;
			} else {
				return false;
			}
		}
	}

	/**
	 * Add a new rule with no cases.
	 * 
	 * @param name
	 *            The name of the rule to add.
	 * @return Whether or not the rule was succesfully added.
	 */
	public boolean addRule(E name) {
		if (sr == null) {
			sr = new Random();
		}
		return addRule(name, new WeightedRandom<>(sr));
	}

	/**
	 * Add a new rule with a set of cases.
	 * 
	 * @param name
	 *            The name of the rule to add.
	 * @param rnd
	 *            The set of cases for the rule.
	 * @return Whether or not the rule was succesfully added.
	 */
	public boolean addRule(E name, WeightedRandom<FunctionalList<E>> rnd) {
		if (rules.containsKey(name)) {
			return false;
		} else {
			rules.put(name, rnd);
			return true;
		}
	}

	/**
	 * Add a subgrammar.
	 * 
	 * @param name
	 *            The name of the subgrammar.
	 * @param subG
	 *            The subgrammar to add.
	 * @return Whether or not the subgrammar was succesfully added.
	 */
	public boolean addSubGrammar(E name, WeightedGrammar<E> subG) {
		if (subgrammars.containsKey(name)) {
			return false;
		} else {
			subgrammars.put(name, subG);
			return true;
		}
	}

	/**
	 * Generate a set of debug sentences for the specified rule. Only
	 * generates sentances one layer deep.
	 * 
	 * @param rl
	 *            The rule to test.
	 * @return A set of sentances generated by the specified rule.
	 */
	public FunctionalList<FunctionalList<E>> debugVals(E rl) {
		FunctionalList<FunctionalList<E>> fl = new FunctionalList<>();

		WeightedRandom<FunctionalList<E>> random = rules.get(rl);

		for (int i = 0; i < 10; i++) {
			fl.add(random.genVal());
		}

		return fl;
	}

	/**
	 * Generate a generic sentance from a initial rule.
	 * 
	 * @param initRule
	 *            The initial rule to start with.
	 * @param f
	 *            The function to transform grammar output into something.
	 * @param spacer
	 *            The spacer element to add in between output tokens.
	 * @return A randomly generated sentance from the specified initial
	 *         rule.
	 */
	public <T> FunctionalList<T> genGeneric(E initRule, Function<E, T> f,
			T spacer) {
		FunctionalList<T> r = new FunctionalList<>();

		if (subgrammars.containsKey(initRule)) {
			subgrammars.get(initRule).genGeneric(initRule, f, spacer)
					.forEach(rp -> {
						r.add(rp);
						r.add(spacer);
					});
		} else if (rules.containsKey(initRule)) {
			rules.get(initRule).genVal().forEach(
					rp -> genGeneric(rp, f, spacer).forEach(rp2 -> {
						r.add(rp2);
						r.add(spacer);
					}));
		} else {
			r.add(f.apply(initRule));
			r.add(spacer);
		}

		return r;
	}

	/**
	 * Generate a random list of grammar elements from a given initial
	 * rule.
	 * 
	 * @param initRule
	 *            The initial rule to start with.
	 * @param spacer
	 *            The item to use to space the list.
	 * @return A list of random grammar elements generated by the specified
	 *         rule.
	 */
	public FunctionalList<E> genList(E initRule, E spacer) {
		return genGeneric(initRule, s -> s, spacer);
	}

	public String getInitRule() {
		return initRule;
	}

	/**
	 * Get the subgrammar with the specified name.
	 * 
	 * @param name
	 *            The name of the subgrammar to get.
	 * @return The subgrammar with the specified name.
	 */
	public WeightedGrammar<E> getSubGrammar(E name) {
		return subgrammars.get(name);
	}

	/**
	 * Check if this grammar has an initial rule
	 * 
	 * @return Whether or not this grammar has an initial rule
	 */
	public boolean hasInitRule() {
		return initRule != null && !initRule.equalsIgnoreCase("");
	}

	/**
	 * Prefix a given rule with a token multiple times
	 * 
	 * @param rName
	 *            The name of the rule to prefix
	 * @param prefixToken
	 *            The token to prefix to the rules
	 * @param addProb
	 *            The additional probability of the tokens
	 * @param nTimes
	 *            The number of times to prefix the token
	 */
	public void multiPrefixRule(E rName, E prefixToken, int addProb,
			int nTimes) {
		WeightedRandom<FunctionalList<E>> rule = rules.get(rName);

		FunctionalList<Pair<Integer, FunctionalList<E>>> newResults = new FunctionalList<>();

		rule.getValues().forEach((par) -> {
			FunctionalList<FunctionalList<E>> nls = new FunctionalList<>();

			// TODO bugtest this. if it works, write multiSuffixWith
			for (int i = 1; i <= nTimes; i++) {
				FunctionalList<E> nl = par
						.merge((left, right) -> right.clone());

				for (int j = 1; j <= i; j++) {
					nl.prepend(prefixToken);
				}

				nls.add(nl);
			}

			nls.forEach((ls) -> newResults.add(new Pair<>(
					par.merge((left, right) -> left) + addProb, ls)));
		});

		newResults.forEach((par) -> par
				.doWith((left, right) -> addCase(rName, left, right)));
	}

	/**
	 * Create a series of alternatives for a rule by prefixing them with a
	 * given token
	 * 
	 * @param addProb
	 *            The amount to adjust the probability by
	 * @param rName
	 *            The name of the rule to prefix
	 * @param prefixToken
	 *            The token to prefix to the rule
	 */
	public void prefixRule(E rName, E prefixToken, int addProb) {
		WeightedRandom<FunctionalList<E>> rule = rules.get(rName);

		FunctionalList<Pair<Integer, FunctionalList<E>>> newResults = new FunctionalList<>();

		rule.getValues().forEach((par) -> {
			FunctionalList<E> nl = par
					.merge((left, right) -> right.clone());
			nl.prepend(prefixToken);

			newResults.add(new Pair<>(
					par.merge((left, right) -> left) + addProb, nl));
		});

		newResults.forEach((par) -> par
				.doWith((left, right) -> addCase(rName, left, right)));
	}

	/**
	 * Remove a rule with the specified name.
	 * 
	 * @param name
	 *            The name of the rule to remove.
	 */
	public void removeRule(E name) {
		rules.remove(name);
	}

	/**
	 * Remove a subgrammar with the specified name.
	 * 
	 * @param name
	 *            The name of the subgrammar to remove.
	 */
	public void removeSubgrammar(E name) {
		subgrammars.remove(name);
	}

	/**
	 * Returns the number of rules in this grammar
	 * 
	 * @return The number of rules in this grammar
	 */
	public int ruleCount() {
		return rules.size();
	}

	/**
	 * Returns a set containing all of the rules in this grammar
	 * 
	 * @return The set of all rule names in this grammar
	 */
	public Set<E> ruleNames() {
		return rules.keySet();
	}

	/**
	 * Set the initial rule of the graphic
	 * 
	 * @param initRule
	 */
	public void setInitRule(String initRule) {
		this.initRule = initRule;
	}

	/**
	 * Suffix a token to a rule
	 * 
	 * @param rName
	 *            The rule to suffix
	 * @param prefixToken
	 *            The token to prefix to the rule
	 * @param addProb
	 *            Additional probability of the prefixed rule
	 */
	public void suffixRule(E rName, E prefixToken, int addProb) {
		WeightedRandom<FunctionalList<E>> rule = rules.get(rName);

		FunctionalList<Pair<Integer, FunctionalList<E>>> newResults = new FunctionalList<>();

		rule.getValues().forEach((par) -> {
			FunctionalList<E> nl = par
					.merge((left, right) -> right.clone());
			nl.add(prefixToken);

			newResults.add(new Pair<>(
					par.merge((left, right) -> left) + addProb, nl));
		});

		newResults.forEach((par) -> par
				.doWith((left, right) -> addCase(rName, left, right)));
	}
}