Package org.apache.tika.parser.odf

Examples of org.apache.tika.parser.odf.OpenDocumentParser

136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
                parsers.put(MediaType.application("vnd.ms-excel"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.wordprocessingml.document"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.presentationml.presentation"), parser);
                parsers.put(MediaType.application("vnd.openxmlformats-officedocument.spreadsheetml.sheet"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put(MediaType.application("vnd.oasis.opendocument.database"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.formula"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.graphics"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.presentation"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.spreadsheet"), parser);
                parsers.put(MediaType.application("vnd.oasis.opendocument.text"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.calc"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.draw"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.impress"), parser);
                parsers.put(MediaType.application("vnd.sun.xml.writer"), parser);
            } else if (name.equals("org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put(MediaType.application("pdf"), new PDFParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put(MediaType.TEXT_PLAIN, new TXTParser());
            } else if (name.equals("org.apache.jackrabbit.extractor.PngTextExtractor")) {
                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
32
33
34
35
36
37
38
39
40
41
42
        InputStream input = ODFParserTest.class.getResourceAsStream(
                "/test-documents/testODFwithOOo3.odt");
        try {
            Metadata metadata = new Metadata();
            ContentHandler handler = new BodyContentHandler();
            new OpenDocumentParser().parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.oasis.opendocument.text",
                    metadata.get(Metadata.CONTENT_TYPE));
           
View Full Code Here
187
188
189
190
191
192
193
194
        // MS Open XML Format
        addConverter( new OOXMLParser().getSupportedTypes( parseContext ),
                MSOfficeXMLConverter.class );

        // Open document format
        addConverter( new OpenDocumentParser().getSupportedTypes( parseContext ),
                OpenDocumentConverter.class );
    }
View Full Code Here
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                parsers.put("application/vnd.openxmlformats-officedocument.wordprocessingml.document", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.presentationml.presentation", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put("application/vnd.oasis.opendocument.database", parser);
                parsers.put("application/vnd.oasis.opendocument.formula", parser);
                parsers.put("application/vnd.oasis.opendocument.graphics", parser);
                parsers.put("application/vnd.oasis.opendocument.presentation", parser);
                parsers.put("application/vnd.oasis.opendocument.spreadsheet", parser);
                parsers.put("application/vnd.oasis.opendocument.text", parser);
                parsers.put("application/vnd.sun.xml.calc", parser);
                parsers.put("application/vnd.sun.xml.draw", parser);
                parsers.put("application/vnd.sun.xml.impress", parser);
                parsers.put("application/vnd.sun.xml.writer", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
                parsers.put("application/vnd.openxmlformats-officedocument.wordprocessingml.document", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.presentationml.presentation", parser);
                parsers.put("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.OpenOfficeTextExtractor")) {
                Parser parser = new OpenDocumentParser();
                parsers.put("application/vnd.oasis.opendocument.database", parser);
                parsers.put("application/vnd.oasis.opendocument.formula", parser);
                parsers.put("application/vnd.oasis.opendocument.graphics", parser);
                parsers.put("application/vnd.oasis.opendocument.presentation", parser);
                parsers.put("application/vnd.oasis.opendocument.spreadsheet", parser);
                parsers.put("application/vnd.oasis.opendocument.text", parser);
                parsers.put("application/vnd.sun.xml.calc", parser);
                parsers.put("application/vnd.sun.xml.draw", parser);
                parsers.put("application/vnd.sun.xml.impress", parser);
                parsers.put("application/vnd.sun.xml.writer", parser);
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PdfTextExtractor")) {
                parsers.put("application/pdf", new PDFParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PlainTextExtractor")) {
                parsers.put("text/plain", new TXTParser());
            } else if (name.equals(
                    "org.apache.jackrabbit.extractor.PngTextExtractor")) {
                Parser parser = new ImageParser();
                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
408
409
410
411
412
413
414
415
416
417
418
419
420
    InputStream input;
    try {
      input = new FileInputStream(new File(f.fileName()));
      ContentHandler textHandler = new BodyContentHandler(-1);
      Metadata metadata = new Metadata();
      OpenDocumentParser parser = new OpenDocumentParser(); 
      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++) {
        if (interrupt) {
          processInterrupt();
        }
View Full Code Here
187
188
189
190
191
192
193
194
        // MS Open XML Format
        addConverter( new OOXMLParser().getSupportedTypes( parseContext ),
                MSOfficeXMLConverter.class );

        // Open document format
        addConverter( new OpenDocumentParser().getSupportedTypes( parseContext ),
                OpenDocumentConverter.class );
    }
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.odf.OpenDocumentParser

  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.tika.io.TikaInputStream
  • org.apache.tika.parser.opendocument.ODFParserTest
  • org.apache.tika.parser.ParseContext
  • org.apache.tika.sax.EndDocumentShieldingContentHandler
  • org.apache.tika.sax.XHTMLContentHandler
  • org.apache.tika.xmp.convert.TikaToXMP
  • org.xml.sax.helpers.DefaultHandler
  • java.util.zip.ZipFile
    • 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.