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 package org.apache.commons.io.output;
18
19 import java.io.File;
20 import java.io.FileNotFoundException;
21 import java.io.FileOutputStream;
22 import java.io.IOException;
23 import java.io.OutputStream;
24 import java.io.OutputStreamWriter;
25 import java.io.StringWriter;
26 import java.io.Writer;
27 import java.nio.charset.Charset;
28 import java.nio.charset.StandardCharsets;
29 import java.util.Locale;
30 import java.util.Objects;
31 import java.util.regex.Matcher;
32
33 import org.apache.commons.io.Charsets;
34 import org.apache.commons.io.IOUtils;
35 import org.apache.commons.io.build.AbstractStreamBuilder;
36 import org.apache.commons.io.input.XmlStreamReader;
37
38 /**
39 * Character stream that handles all the necessary work to figure out the charset encoding of the XML document written to the stream.
40 * <p>
41 * To build an instance, use {@link Builder}.
42 * </p>
43 *
44 * @see Builder
45 * @see XmlStreamReader
46 * @since 2.0
47 */
48 public class XmlStreamWriter extends Writer {
49
50 // @formatter:off
51 /**
52 * Builds a new {@link XmlStreamWriter}.
53 *
54 * <p>
55 * For example:
56 * </p>
57 * <pre>{@code
58 * WriterOutputStream w = WriterOutputStream.builder()
59 * .setPath(path)
60 * .setCharset(StandardCharsets.UTF_8)
61 * .get();}
62 * </pre>
63 *
64 * @see #get()
65 * @since 2.12.0
66 */
67 // @formatter:off
68 public static class Builder extends AbstractStreamBuilder<XmlStreamWriter, Builder> {
69
70 /**
71 * Constructs a new {@link Builder}.
72 */
73 public Builder() {
74 setCharsetDefault(StandardCharsets.UTF_8);
75 setCharset(StandardCharsets.UTF_8);
76 }
77
78 /**
79 * Builds a new {@link XmlStreamWriter}.
80 * <p>
81 * You must set input that supports {@link #getOutputStream()} on this builder, otherwise, this method throws an exception.
82 * </p>
83 * <p>
84 * This builder use the following aspects:
85 * </p>
86 * <ul>
87 * <li>{@link #getOutputStream()}</li>
88 * <li>{@link #getCharset()}</li>
89 * </ul>
90 *
91 * @return a new instance.
92 * @throws IllegalStateException if the {@code origin} is {@code null}.
93 * @throws UnsupportedOperationException if the origin cannot be converted to an {@link OutputStream}.
94 * @throws IOException if an I/O error occurs.
95 * @see #getOutputStream()
96 */
97 @SuppressWarnings("resource")
98 @Override
99 public XmlStreamWriter get() throws IOException {
100 return new XmlStreamWriter(getOutputStream(), getCharset());
101 }
102
103 }
104
105 private static final int BUFFER_SIZE = IOUtils.DEFAULT_BUFFER_SIZE;
106
107 /**
108 * Constructs a new {@link Builder}.
109 *
110 * @return a new {@link Builder}.
111 * @since 2.12.0
112 */
113 public static Builder builder() {
114 return new Builder();
115 }
116
117 private final OutputStream out;
118
119 private final Charset defaultCharset;
120
121 private StringWriter prologWriter = new StringWriter(BUFFER_SIZE);
122
123 private Writer writer;
124
125 private Charset charset;
126
127 /**
128 * Constructs a new XML stream writer for the specified file
129 * with a default encoding of UTF-8.
130 *
131 * @param file The file to write to
132 * @throws FileNotFoundException if there is an error creating or
133 * opening the file
134 * @deprecated Use {@link #builder()}, {@link Builder}, and {@link Builder#get()}
135 */
136 @Deprecated
137 public XmlStreamWriter(final File file) throws FileNotFoundException {
138 this(file, null);
139 }
140
141 /**
142 * Constructs a new XML stream writer for the specified file
143 * with the specified default encoding.
144 *
145 * @param file The file to write to
146 * @param defaultEncoding The default encoding if not encoding could be detected
147 * @throws FileNotFoundException if there is an error creating or
148 * opening the file
149 * @deprecated Use {@link #builder()}, {@link Builder}, and {@link Builder#get()}
150 */
151 @Deprecated
152 @SuppressWarnings("resource")
153 public XmlStreamWriter(final File file, final String defaultEncoding) throws FileNotFoundException {
154 this(new FileOutputStream(file), defaultEncoding);
155 }
156
157 /**
158 * Constructs a new XML stream writer for the specified output stream
159 * with a default encoding of UTF-8.
160 *
161 * @param out The output stream
162 * @deprecated Use {@link #builder()}, {@link Builder}, and {@link Builder#get()}
163 */
164 @Deprecated
165 public XmlStreamWriter(final OutputStream out) {
166 this(out, StandardCharsets.UTF_8);
167 }
168
169 /**
170 * Constructs a new XML stream writer for the specified output stream
171 * with the specified default encoding.
172 *
173 * @param out The output stream
174 * @param defaultEncoding The default encoding if not encoding could be detected
175 */
176 private XmlStreamWriter(final OutputStream out, final Charset defaultEncoding) {
177 this.out = out;
178 this.defaultCharset = Objects.requireNonNull(defaultEncoding);
179 }
180
181 /**
182 * Constructs a new XML stream writer for the specified output stream
183 * with the specified default encoding.
184 *
185 * @param out The output stream
186 * @param defaultEncoding The default encoding if not encoding could be detected
187 * @deprecated Use {@link #builder()}, {@link Builder}, and {@link Builder#get()}
188 */
189 @Deprecated
190 public XmlStreamWriter(final OutputStream out, final String defaultEncoding) {
191 this(out, Charsets.toCharset(defaultEncoding, StandardCharsets.UTF_8));
192 }
193
194 /**
195 * Closes the underlying writer.
196 *
197 * @throws IOException if an error occurs closing the underlying writer
198 */
199 @Override
200 public void close() throws IOException {
201 if (writer == null) {
202 charset = defaultCharset;
203 writer = new OutputStreamWriter(out, charset);
204 writer.write(prologWriter.toString());
205 }
206 writer.close();
207 }
208
209 /**
210 * Detects the encoding.
211 *
212 * @param cbuf the buffer to write the characters from
213 * @param off The start offset
214 * @param len The number of characters to write
215 * @throws IOException if an error occurs detecting the encoding
216 */
217 private void detectEncoding(final char[] cbuf, final int off, final int len)
218 throws IOException {
219 int size = len;
220 final StringBuffer xmlProlog = prologWriter.getBuffer();
221 if (xmlProlog.length() + len > BUFFER_SIZE) {
222 size = BUFFER_SIZE - xmlProlog.length();
223 }
224 prologWriter.write(cbuf, off, size);
225
226 // try to determine encoding
227 if (xmlProlog.length() >= 5) {
228 if (xmlProlog.substring(0, 5).equals("<?xml")) {
229 // try to extract encoding from XML prolog
230 final int xmlPrologEnd = xmlProlog.indexOf("?>");
231 if (xmlPrologEnd > 0) {
232 // ok, full XML prolog written: let's extract encoding
233 final Matcher m = XmlStreamReader.ENCODING_PATTERN.matcher(xmlProlog.substring(0,
234 xmlPrologEnd));
235 if (m.find()) {
236 final String encName = m.group(1).toUpperCase(Locale.ROOT);
237 charset = Charset.forName(encName.substring(1, encName.length() - 1));
238 } else {
239 // no encoding found in XML prolog: using default
240 // encoding
241 charset = defaultCharset;
242 }
243 } else if (xmlProlog.length() >= BUFFER_SIZE) {
244 // no encoding found in first characters: using default
245 // encoding
246 charset = defaultCharset;
247 }
248 } else {
249 // no XML prolog: using default encoding
250 charset = defaultCharset;
251 }
252 if (charset != null) {
253 // encoding has been chosen: let's do it
254 prologWriter = null;
255 writer = new OutputStreamWriter(out, charset);
256 writer.write(xmlProlog.toString());
257 if (len > size) {
258 writer.write(cbuf, off + size, len - size);
259 }
260 }
261 }
262 }
263
264 /**
265 * Flushes the underlying writer.
266 *
267 * @throws IOException if an error occurs flushing the underlying writer
268 */
269 @Override
270 public void flush() throws IOException {
271 if (writer != null) {
272 writer.flush();
273 }
274 }
275
276 /**
277 * Returns the default encoding.
278 *
279 * @return the default encoding
280 */
281 public String getDefaultEncoding() {
282 return defaultCharset.name();
283 }
284
285 /**
286 * Returns the detected encoding.
287 *
288 * @return the detected encoding
289 */
290 public String getEncoding() {
291 return charset.name();
292 }
293
294 /**
295 * Writes the characters to the underlying writer, detecting encoding.
296 *
297 * @param cbuf the buffer to write the characters from
298 * @param off The start offset
299 * @param len The number of characters to write
300 * @throws IOException if an error occurs detecting the encoding
301 */
302 @Override
303 public void write(final char[] cbuf, final int off, final int len) throws IOException {
304 if (prologWriter != null) {
305 detectEncoding(cbuf, off, len);
306 } else {
307 writer.write(cbuf, off, len);
308 }
309 }
310 }