Package org.apache.tika.extractor

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

357
358
359
360
361
362
363
364
365
366
367
        if (embeddedFiles == null) {
            return;
        }

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

        Map<String, COSObjectable> embeddedFileNames = embeddedFiles.getNames();
View Full Code Here
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws SAXException, IOException, TikaException {
        EmbeddedDocumentExtractor extractor =
            new EmbeddedDocumentExtractor(context);

        try {
            File file = TikaInputStream.get(stream).getFile();
            Archive archive = new Archive(file);

            metadata.set(Metadata.CONTENT_TYPE, TYPE.toString());
            XHTMLContentHandler xhtml =
                new XHTMLContentHandler(handler, metadata);
            xhtml.startDocument();
            for (FileHeader header : archive.getFileHeaders()) {
                Metadata entrydata = new Metadata();
                entrydata.set(
                        Metadata.RESOURCE_NAME_KEY,
                        header.getFileNameString());
                if (extractor.shouldParseEmbedded(entrydata)) {
                    extractor.parseEmbedded(stream, xhtml, entrydata, true);
                }
            }
            xhtml.endDocument();
        } catch (RarException e) {
            throw new TikaException("Unable to parse a RAR archive", e);
View Full Code Here
41
42
43
44
45
46
47
abstract class AbstractPOIFSExtractor {

    private final EmbeddedDocumentExtractor extractor;

    protected AbstractPOIFSExtractor(ParseContext context) {
        this.extractor = new EmbeddedDocumentExtractor(context);
    }
View Full Code Here
51
52
53
54
55
56
57
    public PackageExtractor(
            ContentHandler handler, Metadata metadata, ParseContext context) {
        this.handler = handler;
        this.metadata = metadata;
        this.extractor = new EmbeddedDocumentExtractor(context);
    }
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
119
120
121
122
123
124
125
126
127
128
129
        if (!type.equals(MediaType.OCTET_STREAM)) {
            metadata.set(CONTENT_TYPE, type.toString());
        }

        // Use the delegate parser to parse the contained document
        EmbeddedDocumentExtractor extractor = context.get(
                EmbeddedDocumentExtractor.class,
                new ParsingEmbeddedDocumentExtractor(context));

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
View Full Code Here
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
                }
                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
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
        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,Object> embeddedFileNames = embeddedFiles.getNames();

                if (embeddedFileNames != null) {
                    for (Map.Entry<String,Object> 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
48
49
50
51
52
53
54
55
56
57
58
    private TikaConfig tikaConfig;
    private MimeTypes mimeTypes;
    private Detector detector;

    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
46
47
48
49
50
51
52
53
54
55
56
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
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.