Package org.apache.tika.sax

Examples of org.apache.tika.sax.TextContentHandler

101
102
103
104
105
106
107
        parse(stream, handler, metadata, new ParseContext());
    }

    protected ContentHandler getContentHandler(
            ContentHandler handler, Metadata metadata) {
        return new TextContentHandler(handler);
    }
View Full Code Here
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
      for (int i = 0; i < count; i++)
        content.append(getContentFromHTML(mp.getBodyPart(i)));
    } else if (p.isMimeType("text/html")) {
      HtmlParser parser = new HtmlParser();
      Metadata met = new Metadata();
      TextContentHandler handler = new TextContentHandler(
          new BodyContentHandler());
      parser.parse(new ByteArrayInputStream(((String) p.getContent())
          .getBytes()), handler, met);
      content.append(handler.toString());
    } else {
      Object obj = p.getContent();
      if (obj instanceof Part)
        content.append(getContentFromHTML((Part) p.getContent()));
    }
View Full Code Here
87
88
89
90
91
92
93
        parse(stream, handler, metadata, new ParseContext());
    }

    protected ContentHandler getContentHandler(
            ContentHandler handler, Metadata metadata) {
        return new TextContentHandler(handler);
    }
View Full Code Here
80
81
82
83
84
85
86
        parse(stream, handler, metadata, new ParseContext());
    }

    protected ContentHandler getContentHandler(
            ContentHandler handler, Metadata metadata) {
        return new TextContentHandler(handler);
    }
View Full Code Here
82
83
84
85
86
87
88
        xhtml.endDocument();
    }

    protected ContentHandler getContentHandler(
            ContentHandler handler, Metadata metadata, ParseContext context) {
        return new TextContentHandler(handler, true);
    }
View Full Code Here
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
      for (int i = 0; i < count; i++)
        content.append(getContentFromHTML(mp.getBodyPart(i)));
    } else if (p.isMimeType("text/html")) {
      HtmlParser parser = new HtmlParser();
      Metadata met = new Metadata();
      TextContentHandler handler = new TextContentHandler(
          new BodyContentHandler());
      parser.parse(new ByteArrayInputStream(((String) p.getContent())
          .getBytes()), handler, met);
      content.append(handler.toString());
    } else {
      Object obj = p.getContent();
      if (obj instanceof Part)
        content.append(getContentFromHTML((Part) p.getContent()));
    }
View Full Code Here
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
      for (int i = 0; i < count; i++)
        content.append(getContentFromHTML(mp.getBodyPart(i)));
    } else if (p.isMimeType("text/html")) {
      HtmlParser parser = new HtmlParser();
      Metadata met = new Metadata();
      TextContentHandler handler = new TextContentHandler(
          new BodyContentHandler());
      parser.parse(new ByteArrayInputStream(((String) p.getContent())
          .getBytes()), handler, met);
      content.append(handler.toString());
    } else {
      Object obj = p.getContent();
      if (obj instanceof Part)
        content.append(getContentFromHTML((Part) p.getContent()));
    }
View Full Code Here
65
66
67
68
69
70
71
        xhtml.endDocument();
    }

    protected DefaultHandler getDefaultHandler(
            ContentHandler handler, Metadata metadata) {
        return new TextContentHandler(handler);
    }
View Full Code Here
134
135
136
137
138
139
140
141
142
143
144
            }
        };
    }

    private ContentHandler getBodyHandler(final XHTMLContentHandler xhtml) {
        return new TextContentHandler(xhtml) {

            private int discardLevel = 0;

            @Override
            public void startElement(
View Full Code Here
68
69
70
71
72
73
74
        xhtml.endDocument();
    }

    protected ContentHandler getContentHandler(
            ContentHandler handler, Metadata metadata) {
        return new TextContentHandler(handler);
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.sax.TextContentHandler

  • org.apache.oodt.cas.protocol.imaps.ImapsProtocol
  • org.apache.oodt.cas.pushpull.protocol.imaps.ImapsClient
  • org.apache.tika.parser.chm.CHM2XHTML
  • org.apache.tika.parser.html.HtmlParser
  • org.apache.tika.parser.xml.XMLParser
    • 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.