1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * https://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.lang3;
18
19 import org.apache.commons.lang3.stream.Streams;
20
21 /**
22 * Operations on {@link CharSet} instances.
23 *
24 * <p>This class handles {@code null} input gracefully.
25 * An exception will not be thrown for a {@code null} input.
26 * Each method documents its behavior in more detail.</p>
27 *
28 * <p>#ThreadSafe#</p>
29 * @see CharSet
30 * @since 1.0
31 */
32 public class CharSetUtils {
33
34 /**
35 * Takes an argument in set-syntax, see evaluateSet,
36 * and identifies whether any of the characters are present in the specified string.
37 *
38 * <pre>
39 * CharSetUtils.containsAny(null, *) = false
40 * CharSetUtils.containsAny("", *) = false
41 * CharSetUtils.containsAny(*, null) = false
42 * CharSetUtils.containsAny(*, "") = false
43 * CharSetUtils.containsAny("hello", "k-p") = true
44 * CharSetUtils.containsAny("hello", "a-d") = false
45 * </pre>
46 *
47 * @see CharSet#getInstance(String...) for set-syntax.
48 * @param str String to look for characters in, may be null
49 * @param set String[] set of characters to identify, may be null
50 * @return whether or not the characters in the set are in the primary string
51 * @since 3.2
52 */
53 public static boolean containsAny(final String str, final String... set) {
54 if (StringUtils.isEmpty(str) || deepEmpty(set)) {
55 return false;
56 }
57 final CharSet chars = CharSet.getInstance(set);
58 for (final char c : str.toCharArray()) {
59 if (chars.contains(c)) {
60 return true;
61 }
62 }
63 return false;
64 }
65
66 /**
67 * Takes an argument in set-syntax, see evaluateSet,
68 * and returns the number of characters present in the specified string.
69 *
70 * <pre>
71 * CharSetUtils.count(null, *) = 0
72 * CharSetUtils.count("", *) = 0
73 * CharSetUtils.count(*, null) = 0
74 * CharSetUtils.count(*, "") = 0
75 * CharSetUtils.count("hello", "k-p") = 3
76 * CharSetUtils.count("hello", "a-e") = 1
77 * </pre>
78 *
79 * @see CharSet#getInstance(String...) for set-syntax.
80 * @param str String to count characters in, may be null
81 * @param set String[] set of characters to count, may be null
82 * @return the character count, zero if null string input
83 */
84 public static int count(final String str, final String... set) {
85 if (StringUtils.isEmpty(str) || deepEmpty(set)) {
86 return 0;
87 }
88 final CharSet chars = CharSet.getInstance(set);
89 int count = 0;
90 for (final char c : str.toCharArray()) {
91 if (chars.contains(c)) {
92 count++;
93 }
94 }
95 return count;
96 }
97
98 /**
99 * Determines whether or not all the Strings in an array are
100 * empty or not.
101 *
102 * @param strings String[] whose elements are being checked for emptiness
103 * @return whether or not the String is empty
104 */
105 private static boolean deepEmpty(final String[] strings) {
106 return Streams.of(strings).allMatch(StringUtils::isEmpty);
107 }
108
109 /**
110 * Takes an argument in set-syntax, see evaluateSet,
111 * and deletes any of characters present in the specified string.
112 *
113 * <pre>
114 * CharSetUtils.delete(null, *) = null
115 * CharSetUtils.delete("", *) = ""
116 * CharSetUtils.delete(*, null) = *
117 * CharSetUtils.delete(*, "") = *
118 * CharSetUtils.delete("hello", "hl") = "eo"
119 * CharSetUtils.delete("hello", "le") = "ho"
120 * </pre>
121 *
122 * @see CharSet#getInstance(String...) for set-syntax.
123 * @param str String to delete characters from, may be null
124 * @param set String[] set of characters to delete, may be null
125 * @return the modified String, {@code null} if null string input
126 */
127 public static String delete(final String str, final String... set) {
128 if (StringUtils.isEmpty(str) || deepEmpty(set)) {
129 return str;
130 }
131 return modify(str, set, false);
132 }
133
134 /**
135 * Takes an argument in set-syntax, see evaluateSet,
136 * and keeps any of characters present in the specified string.
137 *
138 * <pre>
139 * CharSetUtils.keep(null, *) = null
140 * CharSetUtils.keep("", *) = ""
141 * CharSetUtils.keep(*, null) = ""
142 * CharSetUtils.keep(*, "") = ""
143 * CharSetUtils.keep("hello", "hl") = "hll"
144 * CharSetUtils.keep("hello", "le") = "ell"
145 * </pre>
146 *
147 * @see CharSet#getInstance(String...) for set-syntax.
148 * @param str String to keep characters from, may be null
149 * @param set String[] set of characters to keep, may be null
150 * @return the modified String, {@code null} if null string input
151 * @since 2.0
152 */
153 public static String keep(final String str, final String... set) {
154 if (str == null) {
155 return null;
156 }
157 if (str.isEmpty() || deepEmpty(set)) {
158 return StringUtils.EMPTY;
159 }
160 return modify(str, set, true);
161 }
162
163 /**
164 * Implements delete and keep.
165 *
166 * @param str String to modify characters within
167 * @param set String[] set of characters to modify
168 * @param expect whether to evaluate on match, or non-match
169 * @return the modified String, not null
170 */
171 private static String modify(final String str, final String[] set, final boolean expect) {
172 final CharSet chars = CharSet.getInstance(set);
173 final StringBuilder buffer = new StringBuilder(str.length());
174 final char[] chrs = str.toCharArray();
175 for (final char chr : chrs) {
176 if (chars.contains(chr) == expect) {
177 buffer.append(chr);
178 }
179 }
180 return buffer.toString();
181 }
182
183 /**
184 * Squeezes any repetitions of a character that is mentioned in the
185 * supplied set.
186 *
187 * <pre>
188 * CharSetUtils.squeeze(null, *) = null
189 * CharSetUtils.squeeze("", *) = ""
190 * CharSetUtils.squeeze(*, null) = *
191 * CharSetUtils.squeeze(*, "") = *
192 * CharSetUtils.squeeze("hello", "k-p") = "helo"
193 * CharSetUtils.squeeze("hello", "a-e") = "hello"
194 * </pre>
195 *
196 * @see CharSet#getInstance(String...) for set-syntax.
197 * @param str the string to squeeze, may be null
198 * @param set the character set to use for manipulation, may be null
199 * @return the modified String, {@code null} if null string input
200 */
201 public static String squeeze(final String str, final String... set) {
202 if (StringUtils.isEmpty(str) || deepEmpty(set)) {
203 return str;
204 }
205 final CharSet chars = CharSet.getInstance(set);
206 final StringBuilder buffer = new StringBuilder(str.length());
207 final char[] chrs = str.toCharArray();
208 final int sz = chrs.length;
209 char lastChar = chrs[0];
210 char ch;
211 Character inChars = null;
212 Character notInChars = null;
213 buffer.append(lastChar);
214 for (int i = 1; i < sz; i++) {
215 ch = chrs[i];
216 if (ch == lastChar) {
217 if (inChars != null && ch == inChars) {
218 continue;
219 }
220 if (notInChars == null || ch != notInChars) {
221 if (chars.contains(ch)) {
222 inChars = ch;
223 continue;
224 }
225 notInChars = ch;
226 }
227 }
228 buffer.append(ch);
229 lastChar = ch;
230 }
231 return buffer.toString();
232 }
233
234 /**
235 * CharSetUtils instances should NOT be constructed in standard programming.
236 * Instead, the class should be used as {@code CharSetUtils.evaluateSet(null);}.
237 *
238 * <p>This constructor is public to permit tools that require a JavaBean instance
239 * to operate.</p>
240 *
241 * @deprecated TODO Make private in 4.0.
242 */
243 @Deprecated
244 public CharSetUtils() {
245 }
246 }