Package org.apache.tika.extractor

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

41
42
43
44
45
46
47
48
49
50
51
abstract class AbstractPOIFSExtractor {

    private final EmbeddedDocumentExtractor extractor;

    protected AbstractPOIFSExtractor(ParseContext context) {
        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
      
       // We work by recursing, so get the appropriate bits
       EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);
       EmbeddedDocumentExtractor embeddedExtractor;
       if (ex==null) {
           embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
       } else {
           embeddedExtractor = ex;
       }
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
                }
                entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
            }

            // Use the delegate parser to parse the compressed document
            EmbeddedDocumentExtractor extractor = context.get(
                    EmbeddedDocumentExtractor.class,
                    new ParsingEmbeddedDocumentExtractor(context));
            if (extractor.shouldParseEmbedded(entrydata)) {
                extractor.parseEmbedded(cis, xhtml, entrydata, true);
            }
        } finally {
            cis.close();
        }
View Full Code Here
51
52
53
54
55
56
57
58
59
60
61
    private MimeTypes mimeTypes;
    private Detector detector;
    private static final Log logger = LogFactory.getLog(AbstractPOIFSExtractor.class);

    protected AbstractPOIFSExtractor(ParseContext context) {
        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    private final EmbeddedDocumentExtractor embeddedExtractor;

    public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor) {
        this.extractor = extractor;

        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex==null) {
            embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            embeddedExtractor = ex;
View Full Code Here
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
        if (names != null) {

            PDEmbeddedFilesNameTreeNode embeddedFiles = names.getEmbeddedFiles();
            if (embeddedFiles != null) {

                EmbeddedDocumentExtractor embeddedExtractor = context.get(EmbeddedDocumentExtractor.class);
                if (embeddedExtractor == null) {
                    embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
                }

                Map<String, COSObjectable> embeddedFileNames = embeddedFiles.getNames();

                if (embeddedFileNames != null) {
                    for (Map.Entry<String,COSObjectable> ent : embeddedFileNames.entrySet()) {
                        PDComplexFileSpecification spec = (PDComplexFileSpecification) ent.getValue();
                        PDEmbeddedFile file = spec.getEmbeddedFile();

                        Metadata metadata = new Metadata();
                        // TODO: other metadata?
                        metadata.set(Metadata.RESOURCE_NAME_KEY, ent.getKey());
                        metadata.set(Metadata.CONTENT_TYPE, file.getSubtype());
                        metadata.set(Metadata.CONTENT_LENGTH, Long.toString(file.getSize()));

                        if (embeddedExtractor.shouldParseEmbedded(metadata)) {
                            TikaInputStream stream = TikaInputStream.get(file.createInputStream());
                            try {
                                embeddedExtractor.parseEmbedded(
                                                                stream,
                                                                new EmbeddedContentHandler(handler),
                                                                metadata, false);
                            } finally {
                                stream.close();
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
abstract class AbstractPOIFSExtractor {

    private final EmbeddedDocumentExtractor extractor;

    protected AbstractPOIFSExtractor(ParseContext context) {
        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    public PackageExtractor(
            ContentHandler handler, Metadata metadata, ParseContext context) {
        this.handler = handler;
        this.metadata = metadata;

        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex==null) {
            this.extractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            this.extractor = ex;
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
      
       // We work by recursing, so get the appropriate bits
       EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);
       EmbeddedDocumentExtractor embeddedExtractor;
       if (ex==null) {
           embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
       } else {
           embeddedExtractor = ex;
       }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
        return Collections.singleton(MediaType.application("x-fictionbook+xml"));
    }

    @Override
    protected ContentHandler getContentHandler(ContentHandler handler, Metadata metadata, ParseContext context) {
        EmbeddedDocumentExtractor ex = context.get(EmbeddedDocumentExtractor.class);

        if (ex == null) {
            ex = new ParsingEmbeddedDocumentExtractor(context);
        }
View Full Code Here
TOP

Related Classes of org.apache.tika.extractor.EmbeddedDocumentExtractor

  • de.innosystec.unrar.tika.RARParser
  • org.apache.tika.extractor.DocumentSelector
  • org.apache.tika.io.CloseShieldInputStream
  • org.apache.tika.parser.mbox.MboxParser
  • org.apache.tika.parser.mbox.OutlookPSTParser
  • org.apache.tika.parser.microsoft.AbstractPOIFSExtractor
  • org.apache.tika.parser.microsoft.ooxml.AbstractOOXMLExtractor
  • org.apache.tika.parser.microsoft.TNEFParser
  • org.apache.tika.parser.pdf.PDF2XHTML
  • org.apache.tika.parser.pdf.PDFParser
    • 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.