View Javadoc
1   /*
2    * ====================================================================
3    * Licensed to the Apache Software Foundation (ASF) under one
4    * or more contributor license agreements.  See the NOTICE file
5    * distributed with this work for additional information
6    * regarding copyright ownership.  The ASF licenses this file
7    * to you under the Apache License, Version 2.0 (the
8    * "License"); you may not use this file except in compliance
9    * with the License.  You may obtain a copy of the License at
10   *
11   *   http://www.apache.org/licenses/LICENSE-2.0
12   *
13   * Unless required by applicable law or agreed to in writing,
14   * software distributed under the License is distributed on an
15   * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
16   * KIND, either express or implied.  See the License for the
17   * specific language governing permissions and limitations
18   * under the License.
19   * ====================================================================
20   *
21   * This software consists of voluntary contributions made by many
22   * individuals on behalf of the Apache Software Foundation.  For more
23   * information on the Apache Software Foundation, please see
24   * <http://www.apache.org/>.
25   *
26   */
27  
28  package org.apache.http.entity;
29  
30  import java.io.Serializable;
31  import java.nio.charset.Charset;
32  import java.nio.charset.UnsupportedCharsetException;
33  import java.util.ArrayList;
34  import java.util.Collections;
35  import java.util.HashMap;
36  import java.util.LinkedHashMap;
37  import java.util.List;
38  import java.util.Locale;
39  import java.util.Map;
40  
41  import org.apache.http.Consts;
42  import org.apache.http.Header;
43  import org.apache.http.HeaderElement;
44  import org.apache.http.HttpEntity;
45  import org.apache.http.NameValuePair;
46  import org.apache.http.ParseException;
47  import org.apache.http.annotation.Contract;
48  import org.apache.http.annotation.ThreadingBehavior;
49  import org.apache.http.message.BasicHeaderValueFormatter;
50  import org.apache.http.message.BasicHeaderValueParser;
51  import org.apache.http.message.BasicNameValuePair;
52  import org.apache.http.message.ParserCursor;
53  import org.apache.http.util.Args;
54  import org.apache.http.util.CharArrayBuffer;
55  import org.apache.http.util.TextUtils;
56  
57  /**
58   * Content type information consisting of a MIME type and an optional charset.
59   * <p>
60   * This class makes no attempts to verify validity of the MIME type.
61   * The input parameters of the {@link #create(String, String)} method, however, may not
62   * contain characters {@code <">, <;>, <,>} reserved by the HTTP specification.
63   *
64   * @since 4.2
65   */
66  @Contract(threading = ThreadingBehavior.IMMUTABLE)
67  public final class ContentType implements Serializable {
68  
69      private static final long serialVersionUID = -7768694718232371896L;
70  
71      // constants
72      public static final ContentType APPLICATION_ATOM_XML = create(
73              "application/atom+xml", Consts.ISO_8859_1);
74      public static final ContentType APPLICATION_FORM_URLENCODED = create(
75              "application/x-www-form-urlencoded", Consts.ISO_8859_1);
76      public static final ContentType APPLICATION_JSON = create(
77              "application/json", Consts.UTF_8);
78      public static final ContentType APPLICATION_OCTET_STREAM = create(
79              "application/octet-stream", (Charset) null);
80      public static final ContentType APPLICATION_SOAP_XML = create(
81              "application/soap+xml", Consts.UTF_8);
82      public static final ContentType APPLICATION_SVG_XML = create(
83              "application/svg+xml", Consts.ISO_8859_1);
84      public static final ContentType APPLICATION_XHTML_XML = create(
85              "application/xhtml+xml", Consts.ISO_8859_1);
86      public static final ContentType APPLICATION_XML = create(
87              "application/xml", Consts.ISO_8859_1);
88      public static final ContentType IMAGE_BMP = create(
89              "image/bmp");
90      public static final ContentType IMAGE_GIF= create(
91              "image/gif");
92      public static final ContentType IMAGE_JPEG = create(
93              "image/jpeg");
94      public static final ContentType IMAGE_PNG = create(
95              "image/png");
96      public static final ContentType IMAGE_SVG= create(
97              "image/svg+xml");
98      public static final ContentType IMAGE_TIFF = create(
99              "image/tiff");
100     public static final ContentType IMAGE_WEBP = create(
101             "image/webp");
102     public static final ContentType MULTIPART_FORM_DATA = create(
103             "multipart/form-data", Consts.ISO_8859_1);
104     public static final ContentType TEXT_HTML = create(
105             "text/html", Consts.ISO_8859_1);
106     public static final ContentType TEXT_PLAIN = create(
107             "text/plain", Consts.ISO_8859_1);
108     public static final ContentType TEXT_XML = create(
109             "text/xml", Consts.ISO_8859_1);
110     public static final ContentType WILDCARD = create(
111             "*/*", (Charset) null);
112 
113 
114     private static final Map<String, ContentType> CONTENT_TYPE_MAP;
115     static {
116 
117         final ContentType[] contentTypes = {
118             APPLICATION_ATOM_XML,
119             APPLICATION_FORM_URLENCODED,
120             APPLICATION_JSON,
121             APPLICATION_SVG_XML,
122             APPLICATION_XHTML_XML,
123             APPLICATION_XML,
124             IMAGE_BMP,
125             IMAGE_GIF,
126             IMAGE_JPEG,
127             IMAGE_PNG,
128             IMAGE_SVG,
129             IMAGE_TIFF,
130             IMAGE_WEBP,
131             MULTIPART_FORM_DATA,
132             TEXT_HTML,
133             TEXT_PLAIN,
134             TEXT_XML };
135         final HashMap<String, ContentType> map = new HashMap<String, ContentType>();
136         for (final ContentType contentType: contentTypes) {
137             map.put(contentType.getMimeType(), contentType);
138         }
139         CONTENT_TYPE_MAP = Collections.unmodifiableMap(map);
140     }
141 
142     // defaults
143     public static final ContentType DEFAULT_TEXT = TEXT_PLAIN;
144     public static final ContentType DEFAULT_BINARY = APPLICATION_OCTET_STREAM;
145 
146     private final String mimeType;
147     private final Charset charset;
148     private final NameValuePair[] params;
149 
150     ContentType(
151             final String mimeType,
152             final Charset charset) {
153         this.mimeType = mimeType;
154         this.charset = charset;
155         this.params = null;
156     }
157 
158     ContentType(
159             final String mimeType,
160             final Charset charset,
161             final NameValuePair[] params) {
162         this.mimeType = mimeType;
163         this.charset = charset;
164         this.params = params;
165     }
166 
167     public String getMimeType() {
168         return this.mimeType;
169     }
170 
171     public Charset getCharset() {
172         return this.charset;
173     }
174 
175     /**
176      * @since 4.3
177      */
178     public String getParameter(final String name) {
179         Args.notEmpty(name, "Parameter name");
180         if (this.params == null) {
181             return null;
182         }
183         for (final NameValuePair param: this.params) {
184             if (param.getName().equalsIgnoreCase(name)) {
185                 return param.getValue();
186             }
187         }
188         return null;
189     }
190 
191     /**
192      * Generates textual representation of this content type which can be used as the value
193      * of a {@code Content-Type} header.
194      */
195     @Override
196     public String toString() {
197         final CharArrayBufferer.html#CharArrayBuffer">CharArrayBuffer buf = new CharArrayBuffer(64);
198         buf.append(this.mimeType);
199         if (this.params != null) {
200             buf.append("; ");
201             BasicHeaderValueFormatter.INSTANCE.formatParameters(buf, this.params, false);
202         } else if (this.charset != null) {
203             buf.append("; charset=");
204             buf.append(this.charset.name());
205         }
206         return buf.toString();
207     }
208 
209     private static boolean valid(final String s) {
210         for (int i = 0; i < s.length(); i++) {
211             final char ch = s.charAt(i);
212             if (ch == '"' || ch == ',' || ch == ';') {
213                 return false;
214             }
215         }
216         return true;
217     }
218 
219     /**
220      * Creates a new instance of {@link ContentType}.
221      *
222      * @param mimeType MIME type. It may not be {@code null} or empty. It may not contain
223      *        characters {@code <">, <;>, <,>} reserved by the HTTP specification.
224      * @param charset charset.
225      * @return content type
226      */
227     public static ContentType create(final String mimeType, final Charset charset) {
228         final String normalizedMimeType = Args.notBlank(mimeType, "MIME type").toLowerCase(Locale.ROOT);
229         Args.check(valid(normalizedMimeType), "MIME type may not contain reserved characters");
230         return new ContentType(normalizedMimeType, charset);
231     }
232 
233     /**
234      * Creates a new instance of {@link ContentType} without a charset.
235      *
236      * @param mimeType MIME type. It may not be {@code null} or empty. It may not contain
237      *        characters {@code <">, <;>, <,>} reserved by the HTTP specification.
238      * @return content type
239      */
240     public static ContentType create(final String mimeType) {
241         return create(mimeType, (Charset) null);
242     }
243 
244     /**
245      * Creates a new instance of {@link ContentType}.
246      *
247      * @param mimeType MIME type. It may not be {@code null} or empty. It may not contain
248      *        characters {@code <">, <;>, <,>} reserved by the HTTP specification.
249      * @param charset charset. It may not contain characters {@code <">, <;>, <,>} reserved by the HTTP
250      *        specification. This parameter is optional.
251      * @return content type
252      * @throws UnsupportedCharsetException Thrown when the named charset is not available in
253      * this instance of the Java virtual machine
254      */
255     public static ContentType create(
256             final String mimeType, final String charset) throws UnsupportedCharsetException {
257         return create(mimeType, !TextUtils.isBlank(charset) ? Charset.forName(charset) : null);
258     }
259 
260     private static ContentType create(final HeaderElement helem, final boolean strict) {
261         return create(helem.getName(), helem.getParameters(), strict);
262     }
263 
264     private static ContentType create(final String mimeType, final NameValuePair[] params, final boolean strict) {
265         Charset charset = null;
266         for (final NameValuePair param: params) {
267             if (param.getName().equalsIgnoreCase("charset")) {
268                 final String s = param.getValue();
269                 if (!TextUtils.isBlank(s)) {
270                     try {
271                         charset =  Charset.forName(s);
272                     } catch (final UnsupportedCharsetException ex) {
273                         if (strict) {
274                             throw ex;
275                         }
276                     }
277                 }
278                 break;
279             }
280         }
281         return new ContentType(mimeType, charset, params != null && params.length > 0 ? params : null);
282     }
283 
284     /**
285      * Creates a new instance of {@link ContentType} with the given parameters.
286      *
287      * @param mimeType MIME type. It may not be {@code null} or empty. It may not contain
288      *        characters {@code <">, <;>, <,>} reserved by the HTTP specification.
289      * @param params parameters.
290      * @return content type
291      *
292      * @since 4.4
293      */
294     public static ContentType create(
295             final String mimeType, final NameValuePair... params) throws UnsupportedCharsetException {
296         final String type = Args.notBlank(mimeType, "MIME type").toLowerCase(Locale.ROOT);
297         Args.check(valid(type), "MIME type may not contain reserved characters");
298         return create(mimeType, params, true);
299     }
300 
301     /**
302      * Parses textual representation of {@code Content-Type} value.
303      *
304      * @param s text
305      * @return content type
306      * @throws ParseException if the given text does not represent a valid
307      * {@code Content-Type} value.
308      * @throws UnsupportedCharsetException Thrown when the named charset is not available in
309      * this instance of the Java virtual machine
310      */
311     public static ContentType parse(
312             final String s) throws ParseException, UnsupportedCharsetException {
313         Args.notNull(s, "Content type");
314         final CharArrayBufferer.html#CharArrayBuffer">CharArrayBuffer buf = new CharArrayBuffer(s.length());
315         buf.append(s);
316         final ParserCursoror.html#ParserCursor">ParserCursor cursor = new ParserCursor(0, s.length());
317         final HeaderElement[] elements = BasicHeaderValueParser.INSTANCE.parseElements(buf, cursor);
318         if (elements.length > 0) {
319             return create(elements[0], true);
320         }
321         throw new ParseException("Invalid content type: " + s);
322     }
323 
324     /**
325      * Extracts {@code Content-Type} value from {@link HttpEntity} exactly as
326      * specified by the {@code Content-Type} header of the entity. Returns {@code null}
327      * if not specified.
328      *
329      * @param entity HTTP entity
330      * @return content type
331      * @throws ParseException if the given text does not represent a valid
332      * {@code Content-Type} value.
333      * @throws UnsupportedCharsetException Thrown when the named charset is not available in
334      * this instance of the Java virtual machine
335      */
336     public static ContentType get(
337             final HttpEntity entity) throws ParseException, UnsupportedCharsetException {
338         if (entity == null) {
339             return null;
340         }
341         final Header header = entity.getContentType();
342         if (header != null) {
343             final HeaderElement[] elements = header.getElements();
344             if (elements.length > 0) {
345                 return create(elements[0], true);
346             }
347         }
348         return null;
349     }
350 
351     /**
352      * Extracts {@code Content-Type} value from {@link HttpEntity}. Returns {@code null}
353      * if not specified or incorrect (could not be parsed)..
354      *
355      * @param entity HTTP entity
356      * @return content type
357      *
358      * @since 4.4
359      *
360      */
361     public static ContentType getLenient(final HttpEntity entity) {
362         if (entity == null) {
363             return null;
364         }
365         final Header header = entity.getContentType();
366         if (header != null) {
367             try {
368                 final HeaderElement[] elements = header.getElements();
369                 if (elements.length > 0) {
370                     return create(elements[0], false);
371                 }
372             } catch (final ParseException ex) {
373                 // ignore
374             }
375         }
376         return null;
377     }
378 
379     /**
380      * Extracts {@code Content-Type} value from {@link HttpEntity} or returns the default value
381      * {@link #DEFAULT_TEXT} if not explicitly specified.
382      *
383      * @param entity HTTP entity
384      * @return content type
385      * @throws ParseException if the given text does not represent a valid
386      * {@code Content-Type} value.
387      * @throws UnsupportedCharsetException Thrown when the named charset is not available in
388      * this instance of the Java virtual machine
389      */
390     public static ContentType getOrDefault(
391             final HttpEntity entity) throws ParseException, UnsupportedCharsetException {
392         final ContentType contentType = get(entity);
393         return contentType != null ? contentType : DEFAULT_TEXT;
394     }
395 
396     /**
397      * Extracts {@code Content-Type} value from {@link HttpEntity} or returns the default value
398      * {@link #DEFAULT_TEXT} if not explicitly specified or incorrect (could not be parsed).
399      *
400      * @param entity HTTP entity
401      * @return content type
402      *
403      * @since 4.4
404      */
405     public static ContentType getLenientOrDefault(
406             final HttpEntity entity) throws ParseException, UnsupportedCharsetException {
407         final ContentType contentType = get(entity);
408         return contentType != null ? contentType : DEFAULT_TEXT;
409     }
410 
411 
412     /**
413      * Returns {@code Content-Type} for the given MIME type.
414      *
415      * @param mimeType MIME type
416      * @return content type or {@code null} if not known.
417      *
418      * @since 4.5
419      */
420     public static ContentType getByMimeType(final String mimeType) {
421         if (mimeType == null) {
422             return null;
423         }
424         return CONTENT_TYPE_MAP.get(mimeType);
425     }
426 
427     /**
428      * Creates a new instance with this MIME type and the given Charset.
429      *
430      * @param charset charset
431      * @return a new instance with this MIME type and the given Charset.
432      * @since 4.3
433      */
434     public ContentType withCharset(final Charset charset) {
435         return create(this.getMimeType(), charset);
436     }
437 
438     /**
439      * Creates a new instance with this MIME type and the given Charset name.
440      *
441      * @param charset name
442      * @return a new instance with this MIME type and the given Charset name.
443      * @throws UnsupportedCharsetException Thrown when the named charset is not available in
444      * this instance of the Java virtual machine
445      * @since 4.3
446      */
447     public ContentType withCharset(final String charset) {
448         return create(this.getMimeType(), charset);
449     }
450 
451     /**
452      * Creates a new instance with this MIME type and the given parameters.
453      *
454      * @param params
455      * @return a new instance with this MIME type and the given parameters.
456      * @since 4.4
457      */
458     public ContentType withParameters(
459             final NameValuePair... params) throws UnsupportedCharsetException {
460         if (params.length == 0) {
461             return this;
462         }
463         final Map<String, String> paramMap = new LinkedHashMap<String, String>();
464         if (this.params != null) {
465             for (final NameValuePair param: this.params) {
466                 paramMap.put(param.getName(), param.getValue());
467             }
468         }
469         for (final NameValuePair param: params) {
470             paramMap.put(param.getName(), param.getValue());
471         }
472         final List<NameValuePair> newParams = new ArrayList<NameValuePair>(paramMap.size() + 1);
473         if (this.charset != null && !paramMap.containsKey("charset")) {
474             newParams.add(new BasicNameValuePair("charset", this.charset.name()));
475         }
476         for (final Map.Entry<String, String> entry: paramMap.entrySet()) {
477             newParams.add(new BasicNameValuePair(entry.getKey(), entry.getValue()));
478         }
479         return create(this.getMimeType(), newParams.toArray(new NameValuePair[newParams.size()]), true);
480     }
481 
482 }