Package org.apache.tika.mime

Examples of org.apache.tika.mime.MediaType

149
150
151
152
153
154
155
156
157
158
159
    errHeader = "ExtractingDocumentLoader: " + stream.getSourceInfo();
    Parser parser = null;
    String streamType = req.getParams().get(ExtractingParams.STREAM_TYPE, null);
    if (streamType != null) {
      //Cache?  Parsers are lightweight to construct and thread-safe, so I'm told
      MediaType mt = MediaType.parse(streamType.trim().toLowerCase());
      parser = config.getParser(mt);
    } else {
      parser = autoDetectParser;
    }
    if (parser != null) {
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
    errHeader = "ExtractingDocumentLoader: " + stream.getSourceInfo();
    Parser parser = null;
    String streamType = req.getParams().get(ExtractingParams.STREAM_TYPE, null);
    if (streamType != null) {
      //Cache?  Parsers are lightweight to construct and thread-safe, so I'm told
      MediaType mt = MediaType.parse(streamType.trim().toLowerCase());
      parser = config.getParser(mt);
    } else {
      parser = autoDetectParser;
    }
    if (parser != null) {
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
        if (!stream.markSupported()) {
            stream = new BufferedInputStream(stream);
        }

        // Automatically detect the MIME type of the document
        MediaType type = detector.detect(stream, metadata);
        metadata.set(Metadata.CONTENT_TYPE, type.toString());

        // TIKA-216: Zip bomb prevention
        CountingInputStream count = new CountingInputStream(stream);
        SecureContentHandler secure = new SecureContentHandler(handler, count);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                String charset = mt.getParameters().get("charset");
                if ((charset != null) && Charset.isSupported(charset)) {
                    incomingCharset = charset;
                }
            }
        }
View Full Code Here
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
          // It's OOXML
          TikaInputStream ooxmlStream = TikaInputStream.get(
                new DocumentInputStream((DocumentEntry)ooxml)
          );
          ZipContainerDetector detector = new ZipContainerDetector();
          MediaType type = detector.detect(ooxmlStream, new Metadata());
          handleEmbeddedResource(ooxmlStream, null, type.toString(), xhtml, true);
          return;
       } catch(FileNotFoundException e) {
          // It's regular OLE2
       }

       // Need to dump the directory out to a new temp file, so
       //  it's stand along
       POIFSFileSystem newFS = new POIFSFileSystem();
       copy(dir, newFS.getRoot());

       File tmpFile = File.createTempFile("tika", ".ole2");
       try {
           FileOutputStream out = new FileOutputStream(tmpFile);
           newFS.writeFilesystem(out);
           out.close();

           // What kind of document is it?
           Metadata metadata = new Metadata();
           POIFSDocumentType type = POIFSDocumentType.detectType(dir);
           metadata.set(Metadata.CONTENT_TYPE, type.getType().toString());

           // Trigger for the document itself
           TikaInputStream embedded = TikaInputStream.get(tmpFile);
           try {
               if (extractor.shouldParseEmbedded(metadata)) {
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
        CharsetDetector detector = new CharsetDetector();
        String incomingCharset = metadata.get(Metadata.CONTENT_ENCODING);
        String incomingType = metadata.get(Metadata.CONTENT_TYPE);
        if (incomingCharset == null && incomingType != null) {
            // TIKA-341: Use charset in content-type
            MediaType mt = MediaType.parse(incomingType);
            if (mt != null) {
                incomingCharset = mt.getParameters().get("charset");
            }
        }

        if (incomingCharset != null) {
            detector.setDeclaredEncoding(incomingCharset);
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
119
     * Does container-detector based detection, handling
     *  fallback in case of the default.
     */
    private MediaType detect(TikaInputStream input, Metadata metadata,
               ContainerDetector detector) throws IOException {
       MediaType detected = detector.detect(input, metadata);
       MediaType defaultType = detector.getDefault();
       if(! detected.equals(defaultType)) {
          return detected;
       }
      
       // See if the fallback can do better
View Full Code Here
380
381
382
383
384
385
386
387
388
389
390
        for (MediaType type : registry.getTypes()) {
            System.out.println(type);
            for (MediaType alias : registry.getAliases(type)) {
                System.out.println("  alias:     " + alias);
            }
            MediaType supertype = registry.getSupertype(type);
            if (supertype != null) {
                System.out.println("  supertype: " + supertype);
            }
            Parser parser = parsers.get(type);
            if (parser != null) {
View Full Code Here
222
223
224
225
226
227
228
229
230
231
232
        // First up a truncated OOXML (zip) file
        InputStream input = getTestDoc("testEXCEL.xlsx");
        byte [] buffer = new byte[300];
        assertEquals(300,input.read(buffer));
        Metadata metadata = new Metadata();
        MediaType mt = detector.detect(new ByteArrayInputStream(buffer), metadata);
        // no exception should be thrown
        assertEquals(MediaType.application("x-tika-ooxml"),mt);
       
        // Now a truncated OLE2 file
        input = getTestDoc("testEXCEL.xls");
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
         if(type != POIFSDocumentType.UNKNOWN) {
            return type.getType();
         }
        
         // Is it one of the Corel formats which use OLE2?
         MediaType mt = detectCorel(fs.getRoot());
         if(mt != null) return mt;
        
         // We don't know, sorry
         return DEFAULT;
    }
View Full Code Here
TOP

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

  • bixo.utils.HttpUtils
  • com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell
  • com.cloudera.cdk.morphline.tika.DetectMimeTypeBuilder$DetectMimeType
  • com.digitalpebble.behemoth.tika.TikaProcessor
  • controllers.CodeApp
  • dk.i2m.drupal.util.EntityUtils
  • edu.isi.karma.rdf.GenericRDFGenerator
  • io.lumify.tikaMimeType.TikaMimeTypeMapper
  • org.apache.cxf.jaxrs.ext.search.tika.TikaContentExtractor
  • org.apache.jackrabbit.oak.http.AcceptHeader
    • 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.