Source code: org/apache/http/impl/entity/DefaultEntityDeserializer.java
1 /*
2 * $HeadURL: https://svn.apache.org/repos/asf/jakarta/httpcomponents/httpcore/tags/4.0-alpha2/src/java/org/apache/http/impl/entity/DefaultEntityDeserializer.java $
3 * $Revision: 390875 $
4 * $Date: 2006-04-02 20:06:20 +0200 (Sun, 02 Apr 2006) $
5 *
6 * ====================================================================
7 *
8 * Copyright 1999-2006 The Apache Software Foundation
9 *
10 * Licensed under the Apache License, Version 2.0 (the "License");
11 * you may not use this file except in compliance with the License.
12 * You may obtain a copy of the License at
13 *
14 * http://www.apache.org/licenses/LICENSE-2.0
15 *
16 * Unless required by applicable law or agreed to in writing, software
17 * distributed under the License is distributed on an "AS IS" BASIS,
18 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
19 * See the License for the specific language governing permissions and
20 * limitations under the License.
21 * ====================================================================
22 *
23 * This software consists of voluntary contributions made by many
24 * individuals on behalf of the Apache Software Foundation. For more
25 * information on the Apache Software Foundation, please see
26 * <http://www.apache.org/>.
27 *
28 */
29
30 package org.apache.http.impl.entity;
31
32 import java.io.IOException;
33
34 import org.apache.http.Header;
35 import org.apache.http.HeaderElement;
36 import org.apache.http.HttpException;
37 import org.apache.http.HttpMessage;
38 import org.apache.http.HttpEntity;
39 import org.apache.http.ProtocolException;
40 import org.apache.http.entity.BasicHttpEntity;
41 import org.apache.http.entity.EntityDeserializer;
42 import org.apache.http.io.ChunkedInputStream;
43 import org.apache.http.io.ContentLengthInputStream;
44 import org.apache.http.io.HttpDataInputStream;
45 import org.apache.http.io.HttpDataReceiver;
46 import org.apache.http.params.HttpParams;
47 import org.apache.http.params.HttpProtocolParams;
48 import org.apache.http.protocol.HTTP;
49
50 /**
51 * Default implementation of an entity generator.
52 * <p>
53 * This entity generator comforms to the entity transfer rules outlined in the
54 * <a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec4.4">Section 4.4</a>,
55 * <a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec3.6">Section 3.6</a>,
56 * <a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec14.html#sec14.41">Section 14.41</a>
57 * and <a href="http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec14.13">Section 14.13</a>
58 * of <a href="http://www.w3.org/Protocols/rfc2616/rfc2616.txt">RFC 2616</a>
59 * </p>
60 * <h>4.4 Message Length</h>
61 * <p>
62 * The transfer-length of a message is the length of the message-body as it appears in the
63 * message; that is, after any transfer-codings have been applied. When a message-body is
64 * included with a message, the transfer-length of that body is determined by one of the
65 * following (in order of precedence):
66 * </p>
67 * <p>
68 * 1.Any response message which "MUST NOT" include a message-body (such as the 1xx, 204,
69 * and 304 responses and any response to a HEAD request) is always terminated by the first
70 * empty line after the header fields, regardless of the entity-header fields present in the
71 * message.
72 * </p>
73 * <p>
74 * 2.If a Transfer-Encoding header field (section 14.41) is present and has any value other
75 * than "identity", then the transfer-length is defined by use of the "chunked" transfer-
76 * coding (section 3.6), unless the message is terminated by closing the connection.
77 * </p>
78 * <p>
79 * 3.If a Content-Length header field (section 14.13) is present, its decimal value in
80 * OCTETs represents both the entity-length and the transfer-length. The Content-Length
81 * header field MUST NOT be sent if these two lengths are different (i.e., if a
82 * Transfer-Encoding
83 * </p>
84 * <pre>
85 * header field is present). If a message is received with both a
86 * Transfer-Encoding header field and a Content-Length header field,
87 * the latter MUST be ignored.
88 * </pre>
89 * <p>
90 * 4.If the message uses the media type "multipart/byteranges", and the ransfer-length is not
91 * otherwise specified, then this self- elimiting media type defines the transfer-length.
92 * This media type UST NOT be used unless the sender knows that the recipient can arse it; the
93 * presence in a request of a Range header with ultiple byte- range specifiers from a 1.1
94 * client implies that the lient can parse multipart/byteranges responses.
95 * </p>
96 * <pre>
97 * A range header might be forwarded by a 1.0 proxy that does not
98 * understand multipart/byteranges; in this case the server MUST
99 * delimit the message using methods defined in items 1,3 or 5 of
100 * this section.
101 * </pre>
102 * <p>
103 * 5.By the server closing the connection. (Closing the connection cannot be used to indicate
104 * the end of a request body, since that would leave no possibility for the server to send back
105 * a response.)
106 * </p>
107 * <p>
108 * For compatibility with HTTP/1.0 applications, HTTP/1.1 requests containing a message-body
109 * MUST include a valid Content-Length header field unless the server is known to be HTTP/1.1
110 * compliant. If a request contains a message-body and a Content-Length is not given, the
111 * server SHOULD respond with 400 (bad request) if it cannot determine the length of the
112 * message, or with 411 (length required) if it wishes to insist on receiving a valid
113 * Content-Length.
114 * </p>
115 * <p>All HTTP/1.1 applications that receive entities MUST accept the "chunked" transfer-coding
116 * (section 3.6), thus allowing this mechanism to be used for messages when the message
117 * length cannot be determined in advance.
118 * </p>
119 * <h>3.6 Transfer Codings</h>
120 * <p>
121 * Transfer-coding values are used to indicate an encoding transformation that
122 * has been, can be, or may need to be applied to an entity-body in order to ensure
123 * "safe transport" through the network. This differs from a content coding in that
124 * the transfer-coding is a property of the message, not of the original entity.
125 * </p>
126 * <pre>
127 * transfer-coding = "chunked" | transfer-extension
128 * transfer-extension = token *( ";" parameter )
129 * </pre>
130 * <p>
131 * Parameters are in the form of attribute/value pairs.
132 * </p>
133 * <pre>
134 * parameter = attribute "=" value
135 * attribute = token
136 * value = token | quoted-string
137 * </pre>
138 * <p>
139 * All transfer-coding values are case-insensitive. HTTP/1.1 uses transfer-coding values in
140 * the TE header field (section 14.39) and in the Transfer-Encoding header field (section 14.41).
141 * </p>
142 * <p>
143 * Whenever a transfer-coding is applied to a message-body, the set of transfer-codings MUST
144 * include "chunked", unless the message is terminated by closing the connection. When the
145 * "chunked" transfer-coding is used, it MUST be the last transfer-coding applied to the
146 * message-body. The "chunked" transfer-coding MUST NOT be applied more than once to a
147 * message-body. These rules allow the recipient to determine the transfer-length of the
148 * message (section 4.4).
149 * </p>
150 * <h>14.41 Transfer-Encoding</h>
151 * <p>
152 * The Transfer-Encoding general-header field indicates what (if any) type of transformation has
153 * been applied to the message body in order to safely transfer it between the sender and the
154 * recipient. This differs from the content-coding in that the transfer-coding is a property of
155 * the message, not of the entity.
156 * </p>
157 * <pre>
158 * Transfer-Encoding = "Transfer-Encoding" ":" 1#transfer-coding
159 * </pre>
160 * <p>
161 * If multiple encodings have been applied to an entity, the transfer- codings MUST be listed in
162 * the order in which they were applied. Additional information about the encoding parameters
163 * MAY be provided by other entity-header fields not defined by this specification.
164 * </p>
165 * <h>14.13 Content-Length</h>
166 * <p>
167 * The Content-Length entity-header field indicates the size of the entity-body, in decimal
168 * number of OCTETs, sent to the recipient or, in the case of the HEAD method, the size of
169 * the entity-body that would have been sent had the request been a GET.
170 * </p>
171 * <pre>
172 * Content-Length = "Content-Length" ":" 1*DIGIT
173 * </pre>
174 * <p>
175 * Applications SHOULD use this field to indicate the transfer-length of the message-body,
176 * unless this is prohibited by the rules in section 4.4.
177 * </p>
178 * <p>
179 * This entity generator currently supports only "chunked" and "identitiy" transfer-coding</a>
180 * </p>
181 *
182 * @author <a href="mailto:oleg at ural.ru">Oleg Kalnichevski</a>
183 *
184 * @version $Revision: 390875 $
185 *
186 * @since 4.0
187 */
188 public class DefaultEntityDeserializer implements EntityDeserializer {
189
190 public DefaultEntityDeserializer() {
191 super();
192 }
193
194 protected BasicHttpEntity doDeserialize(
195 final HttpDataReceiver datareceiver,
196 final HttpMessage message) throws HttpException, IOException {
197 if (datareceiver == null) {
198 throw new IllegalArgumentException("HTTP data receiver may not be null");
199 }
200 if (message == null) {
201 throw new IllegalArgumentException("HTTP message may not be null");
202 }
203
204 BasicHttpEntity entity = new BasicHttpEntity();
205
206 HttpParams params = message.getParams();
207 boolean strict = params.isParameterTrue(HttpProtocolParams.STRICT_TRANSFER_ENCODING);
208
209 Header contentTypeHeader = message.getFirstHeader(HTTP.CONTENT_TYPE);
210 Header contentEncodingHeader = message.getFirstHeader(HTTP.CONTENT_ENCODING);
211 Header transferEncodingHeader = message.getFirstHeader(HTTP.TRANSFER_ENCODING);
212 Header contentLengthHeader = message.getFirstHeader(HTTP.CONTENT_LEN);
213 // We use Transfer-Encoding if present and ignore Content-Length.
214 // RFC2616, 4.4 item number 3
215 if (transferEncodingHeader != null) {
216 HeaderElement[] encodings = transferEncodingHeader.getElements();
217 if (strict) {
218 // Currently only chunk and identity are supported
219 for (int i = 0; i < encodings.length; i++) {
220 String encoding = encodings[i].getName();
221 if (encoding != null && !encoding.equals("")
222 && !encoding.equalsIgnoreCase(HTTP.CHUNK_CODING)
223 && !encoding.equalsIgnoreCase(HTTP.IDENTITY_CODING)) {
224 throw new ProtocolException("Unsupported transfer encoding: " + encoding);
225 }
226 }
227 }
228 // The chunked encoding must be the last one applied RFC2616, 14.41
229 int len = encodings.length;
230 if (HTTP.IDENTITY_CODING.equalsIgnoreCase(transferEncodingHeader.getValue())) {
231 entity.setChunked(false);
232 entity.setContentLength(-1);
233 entity.setContent(new HttpDataInputStream(datareceiver));
234 } else if ((len > 0) && (HTTP.CHUNK_CODING.equalsIgnoreCase(
235 encodings[len - 1].getName()))) {
236 entity.setChunked(true);
237 entity.setContentLength(-1);
238 entity.setContent(new ChunkedInputStream(datareceiver));
239 } else {
240 if (strict) {
241 throw new ProtocolException("Chunk-encoding must be the last one applied");
242 }
243 entity.setChunked(false);
244 entity.setContentLength(-1);
245 entity.setContent(new HttpDataInputStream(datareceiver));
246 }
247 } else if (contentLengthHeader != null) {
248 long contentlen = -1;
249 Header[] headers = message.getHeaders(HTTP.CONTENT_LEN);
250 if (strict && headers.length > 1) {
251 throw new ProtocolException("Multiple content length headers");
252 }
253 for (int i = headers.length - 1; i >= 0; i--) {
254 Header header = headers[i];
255 try {
256 contentlen = Long.parseLong(header.getValue());
257 break;
258 } catch (NumberFormatException e) {
259 if (strict) {
260 throw new ProtocolException("Invalid content length: " + header.getValue());
261 }
262 }
263 // See if we can have better luck with another header, if present
264 }
265 entity.setChunked(false);
266 entity.setContentLength(contentlen);
267 if (contentlen >= 0) {
268 entity.setContent(new ContentLengthInputStream(datareceiver, contentlen));
269 } else {
270 entity.setContent(new HttpDataInputStream(datareceiver));
271 }
272 } else {
273 entity.setChunked(false);
274 entity.setContentLength(-1);
275 entity.setContent(new HttpDataInputStream(datareceiver));
276 }
277 if (contentTypeHeader != null) {
278 entity.setContentType(contentTypeHeader);
279 }
280 if (contentEncodingHeader != null) {
281 entity.setContentEncoding(contentEncodingHeader);
282 }
283 return entity;
284 }
285
286 public HttpEntity deserialize(
287 final HttpDataReceiver datareceiver,
288 final HttpMessage message) throws HttpException, IOException {
289 return doDeserialize(datareceiver, message);
290 }
291
292 }