Package org.apache.tika.io

Examples of org.apache.tika.io.CloseShieldInputStream

73
74
75
76
77
78
79
80
81
82
83
  @Override
  public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
      throws IOException, SAXException, TikaException {

    AutoDetectReader reader = new AutoDetectReader(new CloseShieldInputStream(stream), metadata, context.get(ServiceLoader.class, LOADER));

    try {
      Charset charset = reader.getCharset();
      String mediaType = metadata.get(Metadata.CONTENT_TYPE);
      String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
        xhtml.startDocument();

        final DirectoryNode root;
        TikaInputStream tstream = TikaInputStream.cast(stream);
        if (tstream == null) {
            root = new NPOIFSFileSystem(new CloseShieldInputStream(stream)).getRoot();
        } else {
            final Object container = tstream.getOpenContainer();
            if (container instanceof NPOIFSFileSystem) {
                root = ((NPOIFSFileSystem) container).getRoot();
            } else if (container instanceof DirectoryNode) {
                root = (DirectoryNode) container;
            } else if (tstream.hasFile()) {
                root = new NPOIFSFileSystem(tstream.getFileChannel()).getRoot();
            } else {
                root = new NPOIFSFileSystem(new CloseShieldInputStream(tstream)).getRoot();
            }
        }
        parse(root, context, metadata, xhtml);
        xhtml.endDocument();
    }
View Full Code Here
396
397
398
399
400
401
402
403
404
405
406
            pipeMode = false;
            if (serverMode) {
                new TikaServer(Integer.parseInt(arg)).start();
            } else if (arg.equals("-")) {
                InputStream stream =
                    TikaInputStream.get(new CloseShieldInputStream(System.in));
                try {
                    type.process(stream, System.out, new Metadata());
                } finally {
                    stream.close();
                }
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
            TikaInputStream tstream = TikaInputStream.cast(stream);
            if (tstream != null && tstream.hasFile()) {
                // File based, take that as a cue to use a temporary file
                RandomAccess scratchFile = new RandomAccessFile(tmp.createTemporaryFile(), "rw");
                if (localConfig.getUseNonSequentialParser() == true){
                    pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), scratchFile);
                } else {
                    pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), scratchFile, true);
                }
            } else {
                // Go for the normal, stream based in-memory parsing
                if (localConfig.getUseNonSequentialParser() == true){
                    pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), new RandomAccessBuffer());
                } else {
                    pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), true);
                }
            }
           
          
            if (pdfDocument.isEncrypted()) {
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
            factory.setValidating(false);
            factory.setNamespaceAware(true);
            factory.setFeature(XMLConstants.FEATURE_SECURE_PROCESSING, true);
            SAXParser parser = factory.newSAXParser();
            parser.parse(
                    new CloseShieldInputStream(stream),
                    new OfflineContentHandler(xhtml));
        } catch (ParserConfigurationException e) {
            throw new TikaException("XML parser configuration error", e);
        }
    }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
            Iterator<ImageReader> iterator =
                ImageIO.getImageReadersByMIMEType(type);
            if (iterator.hasNext()) {
                ImageReader reader = iterator.next();
                reader.setInput(ImageIO.createImageInputStream(
                        new CloseShieldInputStream(stream)));
                metadata.set("height", Integer.toString(reader.getHeight(0)));
                metadata.set("width", Integer.toString(reader.getWidth(0)));
                reader.dispose();
            }
        }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        // Protect the stream from being closed by CyberNeko
        stream = new CloseShieldInputStream(stream);

        // Prepare the input source using the encoding hint if available
        InputSource source = new InputSource(stream);
        String encoding = metadata.get(Metadata.CONTENT_ENCODING);
        if (encoding != null && Charset.isSupported(encoding)) {
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
        xhtml.startDocument();

        // At the end we want to close the gzip stream to release any associated
        // resources, but the underlying document stream should not be closed
        InputStream gzip =
            new GZIPInputStream(new CloseShieldInputStream(stream));
        try {
            Metadata entrydata = new Metadata();
            String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
            if (name != null && name.length() > 0) {
                entrydata.set(
                        Metadata.RESOURCE_NAME_KEY,
                        GzipUtils.getUncompressedFilename(name));
            }
            // Use the delegate parser to parse the compressed document
            super.parse(
                    new CloseShieldInputStream(gzip),
                    new EmbeddedContentHandler(
                            new BodyContentHandler(xhtml)),
                    entrydata, context);
        } finally {
            gzip.close();
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
                    xhtml.element("h1", name);
                }
                try {
                    // Use the delegate parser to parse this entry
                    super.parse(
                            new CloseShieldInputStream(archive),
                            new EmbeddedContentHandler(
                                    new BodyContentHandler(xhtml)),
                            entrydata, context);
                } catch (TikaException e) {
                    // Could not parse the entry, just skip the content
View Full Code Here
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
        xhtml.startDocument();

        // At the end we want to close the bzip2 stream to release any associated
        // resources, but the underlying document stream should not be closed
        InputStream bzip2 =
            new BZip2CompressorInputStream(new CloseShieldInputStream(stream));
        try {
            Metadata entrydata = new Metadata();
            String name = metadata.get(Metadata.RESOURCE_NAME_KEY);
            if (name != null) {
                if (name.endsWith(".tbz")) {
                    name = name.substring(0, name.length() - 4) + ".tar";
                } else if (name.endsWith(".tbz2")) {
                    name = name.substring(0, name.length() - 5) + ".tar";
                } else if (name.endsWith(".bz")) {
                    name = name.substring(0, name.length() - 3);
                } else if (name.endsWith(".bz2")) {
                    name = name.substring(0, name.length() - 4);
                }
                entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
            }
            // Use the delegate parser to parse the compressed document
            super.parse(
                    new CloseShieldInputStream(bzip2),
                    new EmbeddedContentHandler(
                            new BodyContentHandler(xhtml)),
                    entrydata, context);
        } finally {
            bzip2.close();
View Full Code Here
TOP

Related Classes of org.apache.tika.io.CloseShieldInputStream

  • com.cloudera.cdk.morphline.tika.decompress.DecompressBuilder$Decompress
  • com.cloudera.cdk.morphline.tika.decompress.EmbeddedExtractor
  • com.cloudera.cdk.morphline.tika.decompress.UnpackBuilder$Unpack
  • org.apache.tika.cli.TikaCLI
  • org.apache.tika.detect.POIFSContainerDetector
  • org.apache.tika.detect.XmlRootExtractor
  • org.apache.tika.extractor.EmbeddedDocumentExtractor
  • org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor
  • org.apache.tika.parser.code.SourceCodeParser
  • org.apache.tika.parser.crypto.Pkcs7Parser
    • 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.