/
TikaContentExtractor.java
322 lines (294 loc) · 12.6 KB
/
TikaContentExtractor.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.apache.cxf.jaxrs.ext.search.tika;
import java.io.IOException;
import java.io.InputStream;
import java.io.Serializable;
import java.util.Collections;
import java.util.List;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
import org.apache.cxf.common.logging.LogUtils;
import org.apache.cxf.jaxrs.ext.search.SearchBean;
import org.apache.tika.detect.DefaultDetector;
import org.apache.tika.detect.Detector;
import org.apache.tika.exception.TikaException;
import org.apache.tika.metadata.HttpHeaders;
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AutoDetectParser;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.Parser;
import org.apache.tika.sax.ToTextContentHandler;
public class TikaContentExtractor {
private static final Logger LOG = LogUtils.getL7dLogger(TikaContentExtractor.class);
private final List<Parser> parsers;
private final Detector detector;
/**
* Create new Tika-based content extractor using AutoDetectParser.
*/
public TikaContentExtractor() {
this(new AutoDetectParser(), false);
}
/**
* Create new Tika-based content extractor using the provided parser instance.
* @param parser parser instance
*/
public TikaContentExtractor(final Parser parser) {
this(parser, false);
}
/**
* Create new Tika-based content extractor using the provided parser instances.
* @param parsers parser instances
*/
public TikaContentExtractor(final List<Parser> parsers) {
this(parsers, new DefaultDetector());
}
/**
* Create new Tika-based content extractor using the provided parser instances.
* @param parsers parser instances
*/
public TikaContentExtractor(final List<Parser> parsers, Detector detector) {
this.parsers = parsers;
this.detector = detector;
}
/**
* Create new Tika-based content extractor using the provided parser instance and
* optional media type validation. If validation is enabled, the implementation parser
* will try to detect the media type of the input and validate it against media types
* supported by the parser.
* @param parser parser instance
* @param validateMediaType enabled or disable media type validationparser
*/
public TikaContentExtractor(final Parser parser, final boolean validateMediaType) {
this(Collections.singletonList(parser), validateMediaType ? new DefaultDetector() : null);
}
/**
* Extract the content and metadata from the input stream. Depending on media type validation,
* the detector could be run against input stream in order to ensure that parser supports this
* type of content.
* @param in input stream to extract the content and metadata from
* @return the extracted content and metadata or null if extraction is not possible or was unsuccessful
*/
public TikaContent extract(final InputStream in) {
return extract(in, (jakarta.ws.rs.core.MediaType)null);
}
/**
* Extract the content and metadata from the input stream with a media type hint.
* @param in input stream to extract the content and metadata from
* @param mt JAX-RS MediaType of the stream content
* @return the extracted content and metadata or null if extraction is not possible or was unsuccessful
*/
public TikaContent extract(final InputStream in, jakarta.ws.rs.core.MediaType mt) {
return extract(in, new ToTextContentHandler(), mt);
}
/**
* Extract the content and metadata from the input stream. Depending on media type validation,
* the detector could be run against input stream in order to ensure that parser supports this
* type of content.
* @param in input stream to extract the content and metadata from
* @param handler custom ContentHandler
* @return the extracted content and metadata or null if extraction is not possible
* or was unsuccessful
*/
public TikaContent extract(final InputStream in, final ContentHandler handler) {
return extract(in, handler, (jakarta.ws.rs.core.MediaType)null);
}
/**
* Extract the content and metadata from the input stream with a media type hint.
* @param in input stream to extract the content and metadata from
* @param handler custom ContentHandler
* @param mt JAX-RS MediaType of the stream content
* @return the extracted content and metadata or null if extraction is not possible
* or was unsuccessful
*/
public TikaContent extract(final InputStream in, final ContentHandler handler,
jakarta.ws.rs.core.MediaType mt) {
return extract(in, handler, mt, (ParseContext)null);
}
/**
* Extract the content and metadata from the input stream. Depending on media type validation,
* the detector could be run against input stream in order to ensure that parser supports this
* type of content.
* @param in input stream to extract the content and metadata from
* @param handler custom ContentHandler
* @param context custom context
* @return the extracted content and metadata or null if extraction is not possible
* or was unsuccessful
*/
public TikaContent extract(final InputStream in, final ContentHandler handler, ParseContext context) {
return extract(in, handler, (jakarta.ws.rs.core.MediaType)null, context);
}
/**
* Extract the content and metadata from the input stream with a media type hint
* type of content.
* @param in input stream to extract the metadata from
* @param handler custom ContentHandler
* @param mtHint JAX-RS MediaType of the stream content
* @param context custom context
* @return the extracted content and metadata or null if extraction is not possible
* or was unsuccessful
*/
public TikaContent extract(final InputStream in, ContentHandler handler,
jakarta.ws.rs.core.MediaType mtHint, ParseContext context) {
if (in == null) {
return null;
}
final Metadata metadata = new Metadata();
try {
// Try to validate that input stream media type is supported by the parser
MediaType mediaType = null;
if (mtHint != null) {
mediaType = MediaType.parse(mtHint.toString());
} else if (detector != null && in.markSupported()) {
mediaType = detector.detect(in, metadata);
}
if (mediaType != null) {
metadata.set(HttpHeaders.CONTENT_TYPE, mediaType.toString());
}
Parser parser = null;
if (parsers.size() == 1) {
parser = parsers.get(0);
} else {
for (Parser p : parsers) {
if (mediaType != null && !p.getSupportedTypes(context).contains(mediaType)) {
continue;
}
parser = p;
break;
}
}
if (parser == null) {
return null;
}
if (context == null) {
context = new ParseContext();
}
if (context.get(Parser.class) == null) {
// to process the embedded attachments
context.set(Parser.class,
parser instanceof AutoDetectParser ? parser : new AutoDetectParser());
}
try {
parser.parse(in, handler, metadata, context);
} catch (Exception ex) {
// Starting from Tika 1.6 PDFParser (with other parsers to be updated in the future) will skip
// the content processing if the content handler is null. This can be used to optimize the
// extraction process. If we get an exception with a null handler then a given parser is still
// not ready to accept null handlers so lets retry with IgnoreContentHandler.
if (handler == null) {
handler = new IgnoreContentHandler();
parser.parse(in, handler, metadata, context);
} else {
throw ex;
}
}
return new TikaContent(handler, metadata, mediaType);
} catch (final IOException ex) {
LOG.log(Level.WARNING, "Unable to extract media type from input stream", ex);
} catch (final SAXException ex) {
LOG.log(Level.WARNING, "Unable to parse input stream", ex);
} catch (final TikaException ex) {
LOG.log(Level.WARNING, "Unable to parse input stream", ex);
}
return null;
}
/**
* Extract the metadata only from the input stream. Depending on media type validation,
* the detector could be run against input stream in order to ensure that parser supports this
* type of content.
* @param in input stream to extract the metadata from
* @return the extracted content or null if extraction is not possible or was unsuccessful
*/
public TikaContent extractMetadata(final InputStream in) {
return extract(in, (ContentHandler)null);
}
/**
* Extract the metadata only from the input stream. Depending on media type validation,
* the detector could be run against input stream in order to ensure that parser supports this
* type of content.
* @param in input stream to extract the metadata from
* @return the extracted metadata converted to SearchBean or null if extraction is not possible
* or was unsuccessful
*/
public SearchBean extractMetadataToSearchBean(final InputStream in) {
TikaContent tc = extractMetadata(in);
if (tc == null) {
return null;
}
Metadata metadata = tc.getMetadata();
SearchBean bean = new SearchBean();
for (final String property: metadata.names()) {
bean.set(property, metadata.get(property));
}
return bean;
}
/**
* Extracted content, metadata and media type container
*/
public static class TikaContent implements Serializable {
private static final long serialVersionUID = -1240120543378490963L;
private ContentHandler content;
private Metadata metadata;
private MediaType mediaType;
public TikaContent(ContentHandler content, Metadata metadata, MediaType mediaType) {
this.content = content;
this.metadata = metadata;
this.mediaType = mediaType;
}
/**
* Return the content cached by ContentHandler
* @return the content, may be empty or null if a custom non-caching ContentHandler was used
* to parse the content
*/
public String getContent() {
return content instanceof ToTextContentHandler ? content.toString() : null;
}
/**
* Return the metadata
* @return the metadata
*/
public Metadata getMetadata() {
return metadata;
}
/**
* Return the detected media type of the content
* @return the media type, null if no auto-detection was done
*/
public MediaType getMediaType() {
return mediaType;
}
}
private static final class IgnoreContentHandler extends ToTextContentHandler {
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
// Complete
}
@Override
public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
// Complete
}
@Override
public String toString() {
return "";
}
}
}