Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
StringUtils |
|
| 1.7647058823529411;1.765 |
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 | * http://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 | ||
18 | package org.apache.commons.codec.binary; | |
19 | ||
20 | import java.io.UnsupportedEncodingException; | |
21 | import java.nio.charset.Charset; | |
22 | ||
23 | import org.apache.commons.codec.CharEncoding; | |
24 | import org.apache.commons.codec.Charsets; | |
25 | ||
26 | /** | |
27 | * Converts String to and from bytes using the encodings required by the Java specification. These encodings are | |
28 | * specified in <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html"> | |
29 | * Standard charsets</a>. | |
30 | * | |
31 | * <p>This class is immutable and thread-safe.</p> | |
32 | * | |
33 | * @see CharEncoding | |
34 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
35 | * @version $Id$ | |
36 | * @since 1.4 | |
37 | */ | |
38 | 1 | public class StringUtils { |
39 | ||
40 | /** | |
41 | * Calls {@link String#getBytes(Charset)} | |
42 | * | |
43 | * @param string | |
44 | * The string to encode (if null, return null). | |
45 | * @param charset | |
46 | * The {@link Charset} to encode the {@code String} | |
47 | * @return the encoded bytes | |
48 | */ | |
49 | private static byte[] getBytes(String string, Charset charset) { | |
50 | 239 | if (string == null) { |
51 | 3 | return null; |
52 | } | |
53 | 236 | return string.getBytes(charset); |
54 | } | |
55 | ||
56 | /** | |
57 | * Encodes the given string into a sequence of bytes using the ISO-8859-1 charset, storing the result into a new | |
58 | * byte array. | |
59 | * | |
60 | * @param string | |
61 | * the String to encode, may be {@code null} | |
62 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
63 | * @throws NullPointerException | |
64 | * Thrown if {@link Charsets#ISO_8859_1} is not initialized, which should never happen since it is | |
65 | * required by the Java platform specification. | |
66 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
67 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
68 | * @see #getBytesUnchecked(String, String) | |
69 | */ | |
70 | public static byte[] getBytesIso8859_1(String string) { | |
71 | 13 | return getBytes(string, Charsets.ISO_8859_1); |
72 | } | |
73 | ||
74 | ||
75 | /** | |
76 | * Encodes the given string into a sequence of bytes using the named charset, storing the result into a new byte | |
77 | * array. | |
78 | * <p> | |
79 | * This method catches {@link UnsupportedEncodingException} and rethrows it as {@link IllegalStateException}, which | |
80 | * should never happen for a required charset name. Use this method when the encoding is required to be in the JRE. | |
81 | * </p> | |
82 | * | |
83 | * @param string | |
84 | * the String to encode, may be {@code null} | |
85 | * @param charsetName | |
86 | * The name of a required {@link java.nio.charset.Charset} | |
87 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
88 | * @throws IllegalStateException | |
89 | * Thrown when a {@link UnsupportedEncodingException} is caught, which should never happen for a | |
90 | * required charset name. | |
91 | * @see CharEncoding | |
92 | * @see String#getBytes(String) | |
93 | */ | |
94 | public static byte[] getBytesUnchecked(String string, String charsetName) { | |
95 | 8 | if (string == null) { |
96 | 1 | return null; |
97 | } | |
98 | try { | |
99 | 7 | return string.getBytes(charsetName); |
100 | 1 | } catch (UnsupportedEncodingException e) { |
101 | 1 | throw StringUtils.newIllegalStateException(charsetName, e); |
102 | } | |
103 | } | |
104 | ||
105 | /** | |
106 | * Encodes the given string into a sequence of bytes using the US-ASCII charset, storing the result into a new byte | |
107 | * array. | |
108 | * | |
109 | * @param string | |
110 | * the String to encode, may be {@code null} | |
111 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
112 | * @throws NullPointerException | |
113 | * Thrown if {@link Charsets#US_ASCII} is not initialized, which should never happen since it is | |
114 | * required by the Java platform specification. | |
115 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
116 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
117 | * @see #getBytesUnchecked(String, String) | |
118 | */ | |
119 | public static byte[] getBytesUsAscii(String string) { | |
120 | 34 | return getBytes(string, Charsets.US_ASCII); |
121 | } | |
122 | ||
123 | /** | |
124 | * Encodes the given string into a sequence of bytes using the UTF-16 charset, storing the result into a new byte | |
125 | * array. | |
126 | * | |
127 | * @param string | |
128 | * the String to encode, may be {@code null} | |
129 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
130 | * @throws NullPointerException | |
131 | * Thrown if {@link Charsets#UTF_16} is not initialized, which should never happen since it is | |
132 | * required by the Java platform specification. | |
133 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
134 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
135 | * @see #getBytesUnchecked(String, String) | |
136 | */ | |
137 | public static byte[] getBytesUtf16(String string) { | |
138 | 1 | return getBytes(string, Charsets.UTF_16); |
139 | } | |
140 | ||
141 | /** | |
142 | * Encodes the given string into a sequence of bytes using the UTF-16BE charset, storing the result into a new byte | |
143 | * array. | |
144 | * | |
145 | * @param string | |
146 | * the String to encode, may be {@code null} | |
147 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
148 | * @throws NullPointerException | |
149 | * Thrown if {@link Charsets#UTF_16BE} is not initialized, which should never happen since it is | |
150 | * required by the Java platform specification. | |
151 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
152 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
153 | * @see #getBytesUnchecked(String, String) | |
154 | */ | |
155 | public static byte[] getBytesUtf16Be(String string) { | |
156 | 1 | return getBytes(string, Charsets.UTF_16BE); |
157 | } | |
158 | ||
159 | /** | |
160 | * Encodes the given string into a sequence of bytes using the UTF-16LE charset, storing the result into a new byte | |
161 | * array. | |
162 | * | |
163 | * @param string | |
164 | * the String to encode, may be {@code null} | |
165 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
166 | * @throws NullPointerException | |
167 | * Thrown if {@link Charsets#UTF_16LE} is not initialized, which should never happen since it is | |
168 | * required by the Java platform specification. | |
169 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
170 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
171 | * @see #getBytesUnchecked(String, String) | |
172 | */ | |
173 | public static byte[] getBytesUtf16Le(String string) { | |
174 | 1 | return getBytes(string, Charsets.UTF_16LE); |
175 | } | |
176 | ||
177 | /** | |
178 | * Encodes the given string into a sequence of bytes using the UTF-8 charset, storing the result into a new byte | |
179 | * array. | |
180 | * | |
181 | * @param string | |
182 | * the String to encode, may be {@code null} | |
183 | * @return encoded bytes, or {@code null} if the input string was {@code null} | |
184 | * @throws NullPointerException | |
185 | * Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is | |
186 | * required by the Java platform specification. | |
187 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
188 | * @see <a href="http://download.oracle.com/javase/6/docs/api/java/nio/charset/Charset.html">Standard charsets</a> | |
189 | * @see #getBytesUnchecked(String, String) | |
190 | */ | |
191 | public static byte[] getBytesUtf8(String string) { | |
192 | 189 | return getBytes(string, Charsets.UTF_8); |
193 | } | |
194 | ||
195 | private static IllegalStateException newIllegalStateException(String charsetName, UnsupportedEncodingException e) { | |
196 | 2 | return new IllegalStateException(charsetName + ": " + e); |
197 | } | |
198 | ||
199 | /** | |
200 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the given charset. | |
201 | * | |
202 | * @param bytes | |
203 | * The bytes to be decoded into characters | |
204 | * @param charset | |
205 | * The {@link Charset} to encode the {@code String} | |
206 | * @return A new <code>String</code> decoded from the specified array of bytes using the given charset, | |
207 | * or {@code null} if the input byte array was {@code null}. | |
208 | * @throws NullPointerException | |
209 | * Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is | |
210 | * required by the Java platform specification. | |
211 | */ | |
212 | private static String newString(byte[] bytes, Charset charset) { | |
213 | 73 | return bytes == null ? null : new String(bytes, charset); |
214 | } | |
215 | ||
216 | /** | |
217 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the given charset. | |
218 | * <p> | |
219 | * This method catches {@link UnsupportedEncodingException} and re-throws it as {@link IllegalStateException}, which | |
220 | * should never happen for a required charset name. Use this method when the encoding is required to be in the JRE. | |
221 | * </p> | |
222 | * | |
223 | * @param bytes | |
224 | * The bytes to be decoded into characters, may be {@code null} | |
225 | * @param charsetName | |
226 | * The name of a required {@link java.nio.charset.Charset} | |
227 | * @return A new <code>String</code> decoded from the specified array of bytes using the given charset, | |
228 | * or {@code null} if the input byte array was {@code null}. | |
229 | * @throws IllegalStateException | |
230 | * Thrown when a {@link UnsupportedEncodingException} is caught, which should never happen for a | |
231 | * required charset name. | |
232 | * @see CharEncoding | |
233 | * @see String#String(byte[], String) | |
234 | */ | |
235 | public static String newString(byte[] bytes, String charsetName) { | |
236 | 8 | if (bytes == null) { |
237 | 1 | return null; |
238 | } | |
239 | try { | |
240 | 7 | return new String(bytes, charsetName); |
241 | 1 | } catch (UnsupportedEncodingException e) { |
242 | 1 | throw StringUtils.newIllegalStateException(charsetName, e); |
243 | } | |
244 | } | |
245 | ||
246 | /** | |
247 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the ISO-8859-1 charset. | |
248 | * | |
249 | * @param bytes | |
250 | * The bytes to be decoded into characters, may be {@code null} | |
251 | * @return A new <code>String</code> decoded from the specified array of bytes using the ISO-8859-1 charset, or | |
252 | * {@code null} if the input byte array was {@code null}. | |
253 | * @throws NullPointerException | |
254 | * Thrown if {@link Charsets#ISO_8859_1} is not initialized, which should never happen since it is | |
255 | * required by the Java platform specification. | |
256 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
257 | */ | |
258 | public static String newStringIso8859_1(byte[] bytes) { | |
259 | 1 | return new String(bytes, Charsets.ISO_8859_1); |
260 | } | |
261 | ||
262 | /** | |
263 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the US-ASCII charset. | |
264 | * | |
265 | * @param bytes | |
266 | * The bytes to be decoded into characters | |
267 | * @return A new <code>String</code> decoded from the specified array of bytes using the US-ASCII charset, | |
268 | * or {@code null} if the input byte array was {@code null}. | |
269 | * @throws NullPointerException | |
270 | * Thrown if {@link Charsets#US_ASCII} is not initialized, which should never happen since it is | |
271 | * required by the Java platform specification. | |
272 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
273 | */ | |
274 | public static String newStringUsAscii(byte[] bytes) { | |
275 | 67 | return new String(bytes, Charsets.US_ASCII); |
276 | } | |
277 | ||
278 | /** | |
279 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16 charset. | |
280 | * | |
281 | * @param bytes | |
282 | * The bytes to be decoded into characters | |
283 | * @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16 charset | |
284 | * or {@code null} if the input byte array was {@code null}. | |
285 | * @throws NullPointerException | |
286 | * Thrown if {@link Charsets#UTF_16} is not initialized, which should never happen since it is | |
287 | * required by the Java platform specification. | |
288 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
289 | */ | |
290 | public static String newStringUtf16(byte[] bytes) { | |
291 | 1 | return new String(bytes, Charsets.UTF_16); |
292 | } | |
293 | ||
294 | /** | |
295 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16BE charset. | |
296 | * | |
297 | * @param bytes | |
298 | * The bytes to be decoded into characters | |
299 | * @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16BE charset, | |
300 | * or {@code null} if the input byte array was {@code null}. | |
301 | * @throws NullPointerException | |
302 | * Thrown if {@link Charsets#UTF_16BE} is not initialized, which should never happen since it is | |
303 | * required by the Java platform specification. | |
304 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
305 | */ | |
306 | public static String newStringUtf16Be(byte[] bytes) { | |
307 | 1 | return new String(bytes, Charsets.UTF_16BE); |
308 | } | |
309 | ||
310 | /** | |
311 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-16LE charset. | |
312 | * | |
313 | * @param bytes | |
314 | * The bytes to be decoded into characters | |
315 | * @return A new <code>String</code> decoded from the specified array of bytes using the UTF-16LE charset, | |
316 | * or {@code null} if the input byte array was {@code null}. | |
317 | * @throws NullPointerException | |
318 | * Thrown if {@link Charsets#UTF_16LE} is not initialized, which should never happen since it is | |
319 | * required by the Java platform specification. | |
320 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
321 | */ | |
322 | public static String newStringUtf16Le(byte[] bytes) { | |
323 | 1 | return new String(bytes, Charsets.UTF_16LE); |
324 | } | |
325 | ||
326 | /** | |
327 | * Constructs a new <code>String</code> by decoding the specified array of bytes using the UTF-8 charset. | |
328 | * | |
329 | * @param bytes | |
330 | * The bytes to be decoded into characters | |
331 | * @return A new <code>String</code> decoded from the specified array of bytes using the UTF-8 charset, | |
332 | * or {@code null} if the input byte array was {@code null}. | |
333 | * @throws NullPointerException | |
334 | * Thrown if {@link Charsets#UTF_8} is not initialized, which should never happen since it is | |
335 | * required by the Java platform specification. | |
336 | * @since As of 1.7, throws {@link NullPointerException} instead of UnsupportedEncodingException | |
337 | */ | |
338 | public static String newStringUtf8(byte[] bytes) { | |
339 | 73 | return newString(bytes, Charsets.UTF_8); |
340 | } | |
341 | ||
342 | } |