Package org.apache.tika.mime

Examples of org.apache.tika.mime.MimeType

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
   * @param data
   * @param url
   * @return
   */
  private NutchDocument addType(NutchDocument doc, ParseData data, String url) {
    MimeType mimeType = null;
    String contentType = data.getMeta(Response.CONTENT_TYPE);
    if (contentType == null) {
      // Note by Jerome Charron on 20050415:
      // Content Type not solved by a previous plugin
      // Or unable to solve it... Trying to find it
      // Should be better to use the doc content too
      // (using MimeTypes.getMimeType(byte[], String), but I don't know
      // which field it is?
      // if (MAGIC) {
      //   contentType = MIME.getMimeType(url, content);
      // } else {
      //   contentType = MIME.getMimeType(url);
      // }
      mimeType = MIME.getMimeType(url);
    } else {
      mimeType = MIME.forName(MimeUtil.cleanMimeType(contentType));
    }
       
    // Checks if we solved the content-type.
    if (mimeType == null) {
      return doc;
    }

    contentType = mimeType.getName();
   
    doc.add("type", contentType);

    // Check if we need to split the content type in sub parts
    if (conf.getBoolean("moreIndexingFilter.indexMimeTypeParts", true)) {
View Full Code Here
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
   * @param data
   *          The byte data, returned from the crawl, if any.
   * @return The correctly, automatically guessed {@link MimeType} name.
   */
  public String autoResolveContentType(String typeName, String url, byte[] data) {
    MimeType type = null;
    String cleanedMimeType = null;

    try {
      cleanedMimeType = MimeUtil.cleanMimeType(typeName) != null ? this.mimeTypes
          .forName(MimeUtil.cleanMimeType(typeName)).getName()
          : null;
    } catch (MimeTypeException mte) {
      // Seems to be a malformed mime type name...
    }

    // first try to get the type from the cleaned type name
    try {
      type = cleanedMimeType != null ? this.mimeTypes.forName(cleanedMimeType)
          : null;
    } catch (MimeTypeException e) {
      type = null;
    }

    // if returned null, or if it's the default type then try url resolution
    if (type == null
        || (type != null && type.getName().equals(MimeTypes.OCTET_STREAM))) {
      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern
      type = this.mimeTypes.getMimeType(url) != null ? this.mimeTypes
          .getMimeType(url) : type;
    }

    // if magic is enabled use mime magic to guess if the mime type returned
    // from the magic guess is different than the one that's already set so far
    // if it is, and it's not the default mime type, then go with the mime type
    // returned by the magic
    if (this.mimeMagic) {
      MimeType magicType = this.mimeTypes.getMimeType(data);
      if (magicType != null && !magicType.getName().equals(MimeTypes.OCTET_STREAM)
          && !magicType.getName().equals(MimeTypes.PLAIN_TEXT)
          && type != null && !type.getName().equals(magicType.getName())) {
        // If magic enabled and the current mime type differs from that of the
        // one returned from the magic, take the magic mimeType
        type = magicType;
      }

View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
            File file = entry.getKey();

            byte[] buf = IOUtils.toByteArray(new FileInputStream(file));
            MediaType mediaType = mimeTypes.
                    detect(new ByteArrayInputStream(buf), new Metadata());
            MimeType mimeType = mimeTypes.forName(mediaType.toString());
            FileBody fb = new FileBody(file, name + mimeType.getExtension(),
                    mimeType.getName(), Consts.UTF_8.name());

            multipartEntity.addPart("files[" + x + "]", fb);
            x++;
        }
View Full Code Here
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
   * @param data
   *          The byte data, returned from the crawl, if any.
   * @return The correctly, automatically guessed {@link MimeType} name.
   */
  public String autoResolveContentType(String typeName, String url, byte[] data) {
    MimeType type = null;
    String cleanedMimeType = null;

    try {
      cleanedMimeType = MimeUtil.cleanMimeType(typeName) != null ? this.mimeTypes
          .forName(MimeUtil.cleanMimeType(typeName)).getName()
          : null;
    } catch (MimeTypeException mte) {
      // Seems to be a malformed mime type name...
    }

    // first try to get the type from the cleaned type name
    try {
      type = cleanedMimeType != null ? this.mimeTypes.forName(cleanedMimeType)
          : null;
    } catch (MimeTypeException e) {
      type = null;
    }

    // if returned null, or if it's the default type then try url resolution
    if (type == null
        || (type != null && type.getName().equals(MimeTypes.OCTET_STREAM))) {
      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern
      type = this.mimeTypes.getMimeType(url) != null ? this.mimeTypes
          .getMimeType(url) : type;
    }

    // if magic is enabled use mime magic to guess if the mime type returned
    // from the magic guess is different than the one that's already set so far
    // if it is, and it's not the default mime type, then go with the mime type
    // returned by the magic
    if (this.mimeMagic) {
      MimeType magicType = this.mimeTypes.getMimeType(data);
      if (magicType != null && !magicType.getName().equals(MimeTypes.OCTET_STREAM)
          && !magicType.getName().equals(MimeTypes.PLAIN_TEXT)
          && type != null && !type.getName().equals(magicType.getName())) {
        // If magic enabled and the current mime type differs from that of the
        // one returned from the magic, take the magic mimeType
        type = magicType;
      }

View Full Code Here
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
   * @param data
   * @param url
   * @return
   */
  private NutchDocument addType(NutchDocument doc, ParseData data, String url) {
    MimeType mimeType = null;
    String contentType = data.getMeta(Response.CONTENT_TYPE);
    if (contentType == null) {
      // Note by Jerome Charron on 20050415:
      // Content Type not solved by a previous plugin
      // Or unable to solve it... Trying to find it
      // Should be better to use the doc content too
      // (using MimeTypes.getMimeType(byte[], String), but I don't know
      // which field it is?
      // if (MAGIC) {
      //   contentType = MIME.getMimeType(url, content);
      // } else {
      //   contentType = MIME.getMimeType(url);
      // }
      mimeType = MIME.getMimeType(url);
    } else {
      mimeType = MIME.forName(MimeUtil.cleanMimeType(contentType));
    }
       
    // Checks if we solved the content-type.
    if (mimeType == null) {
      return doc;
    }

    contentType = mimeType.getName();
   
    doc.add("type", contentType);

    // Check if we need to split the content type in sub parts
    if (conf.getBoolean("moreIndexingFilter.indexMimeTypeParts", true)) {
View Full Code Here
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
   * @return The correctly, automatically guessed {@link MimeType} name.
   */
  public String autoResolveContentType(String typeName, String url, byte[] data) {
    String retType = null;
    String magicType = null;
    MimeType type = null;
    String cleanedMimeType = null;

    try {
      cleanedMimeType = MimeUtil.cleanMimeType(typeName) != null ? this.mimeTypes
          .forName(MimeUtil.cleanMimeType(typeName)).getName()
          : null;
    } catch (MimeTypeException mte) {
      // Seems to be a malformed mime type name...
    }

    // first try to get the type from the cleaned type name
    try {
      type = cleanedMimeType != null ? this.mimeTypes.forName(cleanedMimeType)
          : null;
    } catch (MimeTypeException e) {
      type = null;
    }

    // if returned null, or if it's the default type then try url resolution
    if (type == null
        || (type != null && type.getName().equals(MimeTypes.OCTET_STREAM))) {
      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern
      type = this.mimeTypes.getMimeType(url) != null ? this.mimeTypes
          .getMimeType(url) : type;
    }

    retType= type.getName();

    // if magic is enabled use mime magic to guess if the mime type returned
    // from the magic guess is different than the one that's already set so far
    // if it is, and it's not the default mime type, then go with the mime type
    // returned by the magic
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
169
                  
                   // Try to work out what it is
                   MediaType mediaType = getDetector().detect(embedded, new Metadata());
                   String extension = type.getExtension();
                   try {
                      MimeType mimeType = getMimeTypes().forName(mediaType.toString());
                      extension = mimeType.getExtension();
                   } catch(MimeTypeException mte) {
                      // No details on this type are known
                   }
                  
                   // Record what we can do about it
View Full Code Here
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
   * @return The correctly, automatically guessed {@link MimeType} name.
   */
  public String autoResolveContentType(String typeName, String url, byte[] data) {
    String retType = null;
    String magicType = null;
    MimeType type = null;
    String cleanedMimeType = null;

    try {
      cleanedMimeType = MimeUtil.cleanMimeType(typeName) != null ? this.mimeTypes
          .forName(MimeUtil.cleanMimeType(typeName)).getName()
          : null;
    } catch (MimeTypeException mte) {
      // Seems to be a malformed mime type name...
    }

    // first try to get the type from the cleaned type name
    try {
      type = cleanedMimeType != null ? this.mimeTypes.forName(cleanedMimeType)
          : null;
    } catch (MimeTypeException e) {
      type = null;
    }

    // if returned null, or if it's the default type then try url resolution
    if (type == null
        || (type != null && type.getName().equals(MimeTypes.OCTET_STREAM))) {
      // If no mime-type header, or cannot find a corresponding registered
      // mime-type, then guess a mime-type from the url pattern

      try {
        TikaConfig tikaConfig = TikaConfig.getDefaultConfig();
        Tika tika = new Tika(tikaConfig);
        retType = tika.detect(url) != null ? tika.detect(url) : null;
      } catch (Exception e) {
        String message = "Problem loading default Tika configuration";
        LOG.error(message, e);
        throw new RuntimeException(e);
      }
    } else {
        retType = type.getName();
    }

    // if magic is enabled use mime magic to guess if the mime type returned
    // from the magic guess is different than the one that's already set so far
    // if it is, and it's not the default mime type, then go with the mime type
View Full Code Here
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
            // using the original content
            if (mimeType == null | forceMTDetection) {
                if (inputDoc.getContent() != null) {
                    Metadata meta = new Metadata();
                    meta.set(Metadata.RESOURCE_NAME_KEY, inputDoc.getUrl());
                    MimeType mimetype = null;
                    try {
                        MediaType mediaType = detector
                                .detect(new ByteArrayInputStream(inputDoc
                                        .getContent()), meta);
                        mimetype = mimetypes.forName(mediaType.getType() + "/"
                                + mediaType.getSubtype());
                    } catch (IOException e) {
                        LOG.error("Exception", e);
                    } catch (MimeTypeException e) {
                        LOG.error("Exception", e);
                    }
                    mt = mimetype.getName();
                } else if (mimeType == null && inputDoc.getText() != null) {
                    // force it to text
                    mt = "text/plain";
                }
            } else {
View Full Code Here
174
175
176
177
178
179
180
181
182
183
184
185
                  
                   // Try to work out what it is
                   MediaType mediaType = getDetector().detect(embedded, new Metadata());
                   String extension = type.getExtension();
                   try {
                      MimeType mimeType = getMimeTypes().forName(mediaType.toString());
                      extension = mimeType.getExtension();
                   } catch(MimeTypeException mte) {
                      // No details on this type are known
                   }
                  
                   // Record what we can do about it
View Full Code Here
TOP

Related Classes of org.apache.tika.mime.MimeType

  • com.digitalpebble.behemoth.tika.TikaProcessor
  • dk.i2m.drupal.util.EntityUtils
  • org.apache.any23.mime.TikaMIMETypeDetector
  • org.apache.nutch.indexer.more.MoreIndexingFilter
  • org.apache.nutch.protocol.file.FileResponse
  • org.apache.nutch.util.MimeUtil
  • org.apache.oodt.cas.metadata.util.MimeTypeUtils
  • org.apache.oodt.cas.product.jaxrs.resources.ReferenceResource
  • org.apache.oodt.cas.product.jaxrs.writers.ReferenceFileWriter
  • org.apache.sling.commons.mime.internal.TikaMimeTypeProvider
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.