001 /*
002 * Java Genetic Algorithm Library (jenetics-3.0.0).
003 * Copyright (c) 2007-2014 Franz Wilhelmstötter
004 *
005 * Licensed under the Apache License, Version 2.0 (the "License");
006 * you may not use this file except in compliance with the License.
007 * You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 *
017 * Author:
018 * Franz Wilhelmstötter (franz.wilhelmstoetter@gmx.at)
019 */
020 package org.jenetics.util;
021
022 import static java.util.Objects.requireNonNull;
023 import static org.jenetics.internal.util.Equality.eq;
024
025 import java.io.Serializable;
026 import java.util.Arrays;
027 import java.util.regex.PatternSyntaxException;
028
029 import org.jenetics.internal.collection.ArrayProxyISeq;
030 import org.jenetics.internal.collection.CharArrayProxy;
031 import org.jenetics.internal.util.Equality;
032 import org.jenetics.internal.util.Hash;
033
034 /**
035 * This class is used for holding the valid characters of an
036 * {@link org.jenetics.CharacterGene}. It is not a character sequence in the
037 * classical sense. The characters of this sequence are sorted and doesn't
038 * contain duplicate values, like a set.
039 *
040 * [code]
041 * final CharSeq cs1 = new CharSeq("abcdeaafg");
042 * final CharSeq cs2 = new CharSeq("gfedcbabb");
043 * assert(cs1.equals(cs2));
044 * [/code]
045 *
046 * @author <a href="mailto:franz.wilhelmstoetter@gmx.at">Franz Wilhelmstötter</a>
047 * @since 1.0
048 * @version 2.0 — <em>$Date: 2014-12-28 $</em>
049 */
050 public final class CharSeq
051 extends CharSeqBase
052 implements
053 CharSequence,
054 ISeq<Character>,
055 Comparable<CharSeq>,
056 Serializable
057 {
058 private static final long serialVersionUID = 2L;
059
060 /**
061 * Create a new (distinct) CharSeq from the given {@code characters}. The
062 * given {@link CharSequence} is sorted and duplicate values are removed
063 *
064 * @see #CharSeq(CharSequence)
065 *
066 * @param characters the characters.
067 * @throws NullPointerException if the {@code characters} are {@code null}.
068 */
069 public CharSeq(final char[] characters) {
070 super(distinct(characters.clone()));
071 }
072
073 /**
074 * Create a new (distinct) CharSeq from the given {@code characters}. The
075 * given {@link CharSequence} is sorted and duplicate values are removed.
076 *
077 * @param characters the characters.
078 * @throws NullPointerException if the {@code characters} are {@code null}.
079 */
080 public CharSeq(final CharSequence characters) {
081 this(toCharArray(characters));
082 }
083
084 private static char[] toCharArray(final CharSequence characters) {
085 requireNonNull(characters, "Characters");
086
087 final char[] chars = new char[characters.length()];
088 for (int i = chars.length; --i >= 0;) {
089 chars[i] = characters.charAt(i);
090 }
091
092 return chars;
093 }
094
095 private static char[] distinct(final char[] chars) {
096 Arrays.sort(chars);
097
098 int size = 0;
099 for (int i = 0, j = 0, n = chars.length; i < n && j < n; ++i) {
100 chars[i] = chars[j];
101 ++size;
102
103 while (j < n && chars[j] == chars[i]) ++j;
104 }
105
106 final char[] array = new char[size];
107 System.arraycopy(chars, 0, array, 0, size);
108 return array;
109 }
110
111 @Override
112 public boolean contains(final Object object) {
113 return object instanceof Character && contains((Character)object);
114 }
115
116 /**
117 * Test whether this character set contains the given character {@code c}.
118 *
119 * @param c the character to test.
120 * @return {@code true} if this character set contains the given character,
121 * {@code false} otherwise.
122 * @throws NullPointerException if the given character {@code c} is
123 * {@code null}.
124 */
125 public boolean contains(final Character c) {
126 return contains(c.charValue());
127 }
128
129 /**
130 * Test whether this character set contains the given character {@code c}.
131 *
132 * @param c the character to test.
133 * @return {@code true} if this character set contains the given character,
134 * {@code false} otherwise.
135 */
136 public boolean contains(final char c) {
137 return Arrays.binarySearch(proxy.array, c) >= 0;
138 }
139
140 @Override
141 public char charAt(int index) {
142 return proxy.array[index];
143 }
144
145 @Override
146 public int length() {
147 return proxy.array.length;
148 }
149
150 @Override
151 public CharSeq subSequence(int start, int end) {
152 return new CharSeq(new String(proxy.array, start, end - start));
153 }
154
155 /**
156 * Test whether this character set is empty.
157 *
158 * @return {@code true} if this character set is empty, {@code false}
159 * otherwise.
160 */
161 public boolean isEmpty() {
162 return proxy.array.length == 0;
163 }
164
165 @Override
166 public int hashCode() {
167 return Hash.of(getClass()).and(proxy.array).value();
168 }
169
170 @Override
171 public boolean equals(final Object obj) {
172 return Equality.of(this, obj).test(ch -> eq(proxy.array, ch.proxy.array));
173 }
174
175 @Override
176 public int compareTo(final CharSeq set) {
177 int result = 0;
178
179 final int n = Math.min(proxy.array.length, set.proxy.array.length);
180 for (int i = 0; i < n && result == 0; ++i) {
181 result = proxy.array[i] - set.proxy.array[i];
182 }
183 if (result == 0) {
184 result = proxy.array.length - set.proxy.array.length;
185 }
186
187 return result;
188 }
189
190 @Override
191 public String toString() {
192 return new String(proxy.array);
193 }
194
195 /**
196 * Expands the character range for the given {@code pattern}. E.g
197 * {@code a-zA-Z0-1} will return a string containing all upper and lower
198 * case characters (from a to z) and all digits form 0 to 9.
199 *
200 * @param pattern the {@code pattern} to expand.
201 * @return the expanded pattern.
202 * @throws PatternSyntaxException if the pattern could not be expanded.
203 * @throws NullPointerException if the pattern is {@code null}.
204 */
205 public static String expand(final CharSequence pattern) {
206 requireNonNull(pattern, "Pattern");
207 final StringBuilder out = new StringBuilder();
208
209 for (int i = 0, n = pattern.length(); i < n; ++i) {
210 if (pattern.charAt(i) == '\\') {
211 ++i;
212 if (i < pattern.length()) {
213 out.append(pattern.charAt(i));
214 }
215 } else if (pattern.charAt(i) == '-') {
216 if (i <= 0 || i >= (pattern.length() - 1)) {
217 throw new PatternSyntaxException(
218 "Dangling range operator '-'", pattern.toString(),
219 pattern.length() - 1
220 );
221 }
222
223 final String range = expand(
224 pattern.charAt(i - 1),
225 pattern.charAt(i + 1)
226 );
227 out.append(range);
228
229 ++i;
230 } else if (i + 1 == n || pattern.charAt(i + 1) != '-') {
231 out.append(pattern.charAt(i));
232 }
233 }
234
235 return out.toString();
236 }
237
238 /**
239 * Expands the characters between {@code a} and {@code b}.
240 *
241 * @param a the start character.
242 * @param b the stop character.
243 * @return the expanded characters.
244 */
245 public static String expand(final char a, final char b) {
246 final StringBuilder out = new StringBuilder();
247
248 if (a < b) {
249 char c = a;
250 while (c <= b) {
251 out.append(c);
252 c = (char) (c + 1);
253 }
254 } else if (a > b) {
255 char c = a;
256 while (c >= b) {
257 out.append(c);
258 c = (char) (c - 1);
259 }
260 }
261
262 return out.toString();
263 }
264
265 /**
266 * Expands the character range for the given {@code pattern}. E.g
267 * {@code a-zA-Z0-1} will return a string containing all upper and lower
268 * case characters (from a to z) and all digits form 0 to 9.
269 *
270 * @see #expand(CharSequence)
271 *
272 * @param pattern the {@code pattern} to expand.
273 * @return the expanded pattern.
274 * @throws PatternSyntaxException if the pattern could not be expanded.
275 * @throws NullPointerException if the pattern is {@code null}.
276 */
277 public static CharSeq of(final CharSequence pattern) {
278 return new CharSeq(expand(pattern));
279 }
280
281 /**
282 * Expands the characters between {@code a} and {@code b}.
283 *
284 * @see #expand(char, char)
285 *
286 * @param a the start character.
287 * @param b the stop character.
288 * @return the expanded characters.
289 */
290 public static CharSeq of(final char a, final char b) {
291 return new CharSeq(expand(a, b));
292 }
293
294 /**
295 * Helper method for creating a sequence of characters from the given
296 * {@code CharSequence}. The returned sequence will contain all characters
297 * in the original order.
298 *
299 * @param chars the char sequence to convert.
300 * @return a sequence which will contain all given chars in the original
301 * order.
302 */
303 public static ISeq<Character> toISeq(final CharSequence chars) {
304 final MSeq<Character> seq = MSeq.ofLength(chars.length());
305 for (int i = 0; i < chars.length(); ++i) {
306 seq.set(i, chars.charAt(i));
307 }
308
309 return seq.toISeq();
310 }
311 }
312
313 abstract class CharSeqBase extends ArrayProxyISeq<Character, CharArrayProxy> {
314 private static final long serialVersionUID = 1L;
315 protected CharSeqBase(final char[] characters) {
316 super(new CharArrayProxy(characters, 0, characters.length));
317 }
318 }
|