Package org.apache.tika.extractor

Examples of org.apache.tika.extractor.EmbeddedDocumentExtractor

65
66
67
68
69
70
71
72
73
74
75
    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
53
54
55
56
57
58
59
60
61
62
63
    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
62
63
64
65
66
67
68
69
70
71
72
    public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor extractor, String type) {
        this.extractor = extractor;
        this.type = type;

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

        if (ex==null) {
            embeddedExtractor = new ParsingEmbeddedDocumentExtractor(context);
        } else {
            embeddedExtractor = 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
73
74
75
76
77
78
79
80
81
82
83
    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
76
77
78
79
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
  }

  public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
      throws IOException, TikaException, SAXException {

    EmbeddedDocumentExtractor extractor = context.get(EmbeddedDocumentExtractor.class,
        new ParsingEmbeddedDocumentExtractor(context));

    String charsetName = "windows-1252";

    metadata.set(Metadata.CONTENT_TYPE, MBOX_MIME_TYPE);
    metadata.set(Metadata.CONTENT_ENCODING, charsetName);

    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
    xhtml.startDocument();

    InputStreamReader isr = new InputStreamReader(stream, charsetName);
    BufferedReader reader = new BufferedReader(isr);
    try {
      String curLine = reader.readLine();
      int mailItem = 0;
      do {
        if (curLine.startsWith(MBOX_RECORD_DIVIDER)) {
          Metadata mailMetadata = new Metadata();
          Queue<String> multiline = new LinkedList<String>();
          mailMetadata.add(EMAIL_FROMLINE_METADATA, curLine.substring(MBOX_RECORD_DIVIDER.length()));
          mailMetadata.set(Metadata.CONTENT_TYPE, "message/rfc822");
          curLine = reader.readLine();

          ByteArrayOutputStream message = new ByteArrayOutputStream(100000);
          do {
            if (curLine.startsWith(" ") || curLine.startsWith("\t")) {
              String latestLine = multiline.poll();
              latestLine += " " + curLine.trim();
              multiline.add(latestLine);
            } else {
              multiline.add(curLine);
            }

            message.write(curLine.getBytes(charsetName));
            message.write(0x0A);
            curLine = reader.readLine();
          } while (curLine != null && !curLine.startsWith(MBOX_RECORD_DIVIDER) && message.size() < MAIL_MAX_SIZE);

          for (String item : multiline) {
            saveHeaderInMetadata(mailMetadata, item);
          }

          ByteArrayInputStream messageStream = new ByteArrayInputStream(message.toByteArray());
          message = null;

          if (extractor.shouldParseEmbedded(mailMetadata)) {
            extractor.parseEmbedded(messageStream, xhtml, mailMetadata, true);
          }

          if (tracking) {
            getTrackingMetadata().put(mailItem++, mailMetadata);
          }
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
  public void parse(InputStream stream, ContentHandler handler, Metadata metadata, ParseContext context)
      throws IOException, SAXException, TikaException {

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

    metadata.set(Metadata.CONTENT_TYPE, MS_OUTLOOK_PST_MIMETYPE.toString());

    XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
        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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
                }
                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
180
181
182
183
184
185
186
187
188
189
190
     * @throws IOException
     * @throws SAXException
     * @throws TikaException
     */
    protected void handleCompletedObject() throws IOException, SAXException, TikaException {
       EmbeddedDocumentExtractor embeddedExtractor = context.get(EmbeddedDocumentExtractor.class);
      
       if (embeddedExtractor == null) {
           embeddedExtractor = 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.