Package org.apache.tika.parser

Examples of org.apache.tika.parser.Parser

143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
    public void testPowerPoint() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testPPT.pptx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testPPT.pptx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.presentationml.presentation",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Powerpoint Slide", metadata.get(Metadata.TITLE));
View Full Code Here
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
    public void testWord() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/testWORD.docx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        // TODO: should auto-detect without the resource name
        metadata.set(Metadata.RESOURCE_NAME_KEY, "testWORD.docx");
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Word Document", metadata.get(Metadata.TITLE));
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
    public void testProtectedExcel() throws Exception {
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/protected.xlsx");

        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();

        try {
            parser.parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
321
322
323
324
325
326
327
328
329
330
331
                if (AutoDetectParser.class.isAssignableFrom(parserClass)) {
                    throw new TikaException(
                            "AutoDetectParser not supported in a <parser>"
                            + " configuration element: " + name);
                }
                Parser parser = parserClass.newInstance();

                NodeList mimes = node.getElementsByTagName("mime");
                if (mimes.getLength() > 0) {
                    Set<MediaType> types = new HashSet<MediaType>();
                    for (int j = 0; j < mimes.getLength(); j++) {
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
        assertTrue(xml.contains("tika-bundle"));

        // Package extraction
        ContentHandler handler = new BodyContentHandler();

        Parser parser = tika.getParser();
        ParseContext context = new ParseContext();
        context.set(Parser.class, parser);

        InputStream stream =
                new FileInputStream("src/test/resources/test-documents.zip");
        try {
            parser.parse(stream, handler, new Metadata(), context);
        } finally {
            stream.close();
        }

        String content = handler.toString();
View Full Code Here
617
618
619
620
621
622
623
624
625
626
627
            }
            MediaType supertype = registry.getSupertype(type);
            if (supertype != null) {
                System.out.println("  supertype: " + supertype);
            }
            Parser p = parsers.get(type);
            if (p != null) {
                System.out.println("  parser:    " + p.getClass().getName());
            }
        }
    }
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
    private class OutputType {

        public void process(
                InputStream input, OutputStream output, Metadata metadata)
                throws Exception {
            Parser p = parser;
            if (fork) {
                p = new ForkParser(TikaCLI.class.getClassLoader(), p);
            }
            ContentHandler handler = getContentHandler(output, metadata);
            p.parse(input, handler, metadata, context);
            // fix for TIKA-596: if a parser doesn't generate
            // XHTML output, the lack of an output document prevents
            // metadata from being output: this fixes that
            if (handler instanceof NoDocumentMetHandler){
                NoDocumentMetHandler metHandler = (NoDocumentMetHandler)handler;
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
    }

    @Test
    public void testWORDxtraction() throws Exception {
        File file = getResourceAsFile("/test-documents/testWORD.doc");
        Parser parser = tika.getParser();
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(
                    stream, new DefaultHandler(), metadata, new ParseContext());
        } finally {
            stream.close();
        }
        assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE));
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
        final String expected = "Numbers and their Squares";
        File file = getResourceAsFile("/test-documents/testEXCEL.xls");
        String s1 = tika.parseToString(file);
        assertTrue("Text does not contain '" + expected + "'", s1
                .contains(expected));
        Parser parser = tika.getParser();
        Metadata metadata = new Metadata();
        InputStream stream = new FileInputStream(file);
        try {
            parser.parse(
                    stream, new DefaultHandler(), metadata, new ParseContext());
        } finally {
            stream.close();
        }
        assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE));
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
*/
public class AdobeFontMetricParserTest {
 
    @Test
    public void testAdobeFontMetricParsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();
        TikaInputStream stream = TikaInputStream.get(
                AdobeFontMetricParserTest.class.getResource(
                        "/test-documents/testAFM.afm"));

        try {
            parser.parse(stream, handler, metadata, context);
        } finally {
            stream.close();
        }

        assertEquals("application/x-font-adobe-metric", metadata.get(Metadata.CONTENT_TYPE));
View Full Code Here
TOP

Related Classes of org.apache.tika.parser.Parser

  • bixo.parser.TikaCallableTest
  • com.baasbox.controllers.File
  • com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell
  • com.digitalpebble.behemoth.tika.TikaProcessor
  • com.findwise.hydra.stage.tika.SimpleFetchingTikaStageTest
  • com.ikanow.infinit.e.harvest.extraction.document.file.FileHarvester
  • com.ikanow.infinit.e.harvest.extraction.text.legacy.TextExtractorTika
  • com.nidhinova.tika.server.TikaService
  • com.tamingtext.tika.TikaTest
  • ipcress.Extraction
    • 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.