Package org.apache.tika.parser.rtf

Examples of org.apache.tika.parser.rtf.RTFParser

157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
                Parser parser = new ImageParser();
                parsers.put(MediaType.image("png"), parser);
                parsers.put(MediaType.image("apng"), parser);
                parsers.put(MediaType.image("mng"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put(MediaType.application("rtf"), parser);
                parsers.put(MediaType.text("rtf"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put(MediaType.APPLICATION_XML, parser);
                parsers.put(MediaType.text("xml"), parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
214
           if(rtfChunk != null && !doneBody) {
              ByteChunk chunk = (ByteChunk)rtfChunk;
              MAPIRtfAttribute rtf = new MAPIRtfAttribute(
                    MAPIProperty.RTF_COMPRESSED, Types.BINARY, chunk.getValue()
              );
              RTFParser rtfParser = new RTFParser();
              rtfParser.parse(
                              new ByteArrayInputStream(rtf.getData()),
                              new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
                              new Metadata(), new ParseContext());
              doneBody = true;
           }
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
        // MS Office Binary File Format
        addConverter( new OfficeParser().getSupportedTypes( parseContext ),
                MSOfficeBinaryConverter.class );

        // Rich Text Format
        addConverter( new RTFParser().getSupportedTypes( parseContext ), RTFConverter.class );

        // MS Open XML Format
        addConverter( new OOXMLParser().getSupportedTypes( parseContext ),
                MSOfficeXMLConverter.class );
View Full Code Here
61
62
63
64
65
66
67
68
        TransformerHandler transform = factory.newTransformerHandler();
        transform.setResult(new StreamResult(System.out));

        // Analyze the RTF representation
        TikaRepresentation tr = new TikaRepresentation(rtfSample);
        tr.setTikaParser(new RTFParser());
        tr.parse(transform);
    }
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                parsers.put("image/png", parser);
                parsers.put("image/apng", parser);
                parsers.put("image/mng", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.RTFTextExtractor")) {
                Parser parser = new RTFParser();
                parsers.put("application/rtf", parser);
                parsers.put("text/rtf", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.XMLTextExtractor")) {
                Parser parser = new XMLParser();
                parsers.put("application/xml", parser);
                parsers.put("text/xml", parser);
            } else {
                logger.warn("Ignoring unknown text extractor class: {}", name);
            }
        }

        parser.setParsers(parsers);
    }
View Full Code Here
361
362
363
364
365
366
367
368
369
370
371
372
373
    InputStream input;
    try {
      input = new FileInputStream(new File(f.fileName()));
      ContentHandler textHandler = new BodyContentHandler(-1);
      Metadata metadata = new Metadata();
      RTFParser parser = new RTFParser(); 
      ParseContext context = new ParseContext();
      parser.parse(input, textHandler, metadata, context);
      String[] result = textHandler.toString().split(regex);
      for (int i=0; i<result.length && keepRunning; i++) {
        addToIndex(r.getNoteGuid(), result[i], "RESOURCE");
      }
      input.close();
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
        // MS Office Binary File Format
        addConverter( new OfficeParser().getSupportedTypes( parseContext ),
                MSOfficeBinaryConverter.class );

        // Rich Text Format
        addConverter( new RTFParser().getSupportedTypes( parseContext ), RTFConverter.class );

        // MS Open XML Format
        addConverter( new OOXMLParser().getSupportedTypes( parseContext ),
                MSOfficeXMLConverter.class );
View Full Code Here
203
204
205
206
207
208
209
210
211
212
213
214
           if(rtfChunk != null && !doneBody) {
              ByteChunk chunk = (ByteChunk)rtfChunk;
              MAPIRtfAttribute rtf = new MAPIRtfAttribute(
                    MAPIProperty.RTF_COMPRESSED, Types.BINARY, chunk.getValue()
              );
              RTFParser rtfParser = new RTFParser();
              rtfParser.parse(
                              new ByteArrayInputStream(rtf.getData()),
                              new EmbeddedContentHandler(new BodyContentHandler(xhtml)),
                              new Metadata(), new ParseContext());
              doneBody = true;
           }
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.rtf.RTFParser

  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.tika.io.TaggedInputStream
  • org.apache.tika.parser.microsoft.OutlookExtractor
  • org.apache.tika.parser.ParseContext
  • org.apache.tika.sax.XHTMLContentHandler
  • org.apache.tika.xmp.convert.TikaToXMP
  • org.restlet.test.ext.lucene.LuceneTestCase
  • javax.swing.text.Document
  • javax.swing.text.DefaultStyledDocument
    • 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.