Package org.apache.tika.sax

Examples of org.apache.tika.sax.BodyContentHandler

57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    }

    @Test
    public void testExcel() throws Exception {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();
        context.set(Locale.class, Locale.US);

        InputStream input = getTestDocument("testEXCEL.xlsx");
        try {
            parser.parse(input, handler, metadata, context);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Simple Excel document", metadata.get(TikaCoreProperties.TITLE));
            assertEquals("Keith Bennett", metadata.get(TikaCoreProperties.CREATOR));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            assertTrue(content.contains("Sample Excel Worksheet"));
            assertTrue(content.contains("Numbers and their Squares"));
            assertTrue(content.contains("9"));
            assertFalse(content.contains("9.0"));
            assertTrue(content.contains("196"));
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    }

    @Test
    public void testExcelFormats() throws Exception {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();
        context.set(Locale.class, Locale.US);

        InputStream input = getTestDocument("testEXCEL-formats.xlsx");
        try {
            parser.parse(input, handler, metadata, context);

            assertEquals(
                    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
                    metadata.get(Metadata.CONTENT_TYPE));

            String content = handler.toString();

            // Number #,##0.00
            assertTrue(content.contains("1,599.99"));
            assertTrue(content.contains("-1,599.99"));
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
            Parser parser = new AutoDetectParser();
            Metadata metadata = new Metadata();
            // TODO: should auto-detect without the resource name
            metadata.set(Metadata.RESOURCE_NAME_KEY, filename);
            ContentHandler handler = new BodyContentHandler();
            ParseContext context = new ParseContext();
   
            InputStream input = getTestDocument(filename);
            try {
                parser.parse(input, handler, metadata, context);
   
                assertEquals(
                        "Mime-type checking for " + filename,
                        mimeTypes[i],
                        metadata.get(Metadata.CONTENT_TYPE));
                assertEquals("Attachment Test", metadata.get(TikaCoreProperties.TITLE));
                assertEquals("Rajiv", metadata.get(TikaCoreProperties.CREATOR));
                assertEquals("Rajiv", metadata.get(Metadata.AUTHOR));
               
                String content = handler.toString();
                // Theme files don't have the text in them
                if(extension.equals("thmx")) {
                    assertEquals("", content);
                } else {
                    assertTrue(
View Full Code Here
265
266
267
268
269
270
271
272
273
274
275
            // TODO: should auto-detect without the resource name
            metadata.set(Metadata.RESOURCE_NAME_KEY, filename);

      // Allow the value to be access from the inner class
      final int currentI = i;
            ContentHandler handler = new BodyContentHandler()
    {
        public void startDocument ()
        {
      assertEquals(
             "Mime-type checking for " + filename,
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
public class TarParserTest extends AbstractPkgTest {

    @Test
    public void testTarParsing() throws Exception {
        Parser parser = new AutoDetectParser(); // Should auto-detect!
        ContentHandler handler = new BodyContentHandler();
        Metadata metadata = new Metadata();

        InputStream stream = TarParserTest.class.getResourceAsStream(
                "/test-documents/test-documents.tar");
        try {
            parser.parse(stream, handler, metadata, recursingContext);
        } finally {
            stream.close();
        }

        assertEquals("application/x-tar", metadata.get(Metadata.CONTENT_TYPE));
        String content = handler.toString();
        assertTrue(content.contains("test-documents/testEXCEL.xls"));
        assertTrue(content.contains("Sample Excel Worksheet"));
        assertTrue(content.contains("test-documents/testHTML.html"));
        assertTrue(content.contains("Test Indexation Html"));
        assertTrue(content.contains("test-documents/testOpenOffice2.odt"));
View Full Code Here
310
311
312
313
314
315
316
317
318
319
320
          String filename = "testPPT." + extension;

          Parser parser = new AutoDetectParser();
          Metadata metadata = new Metadata();
          metadata.set(Metadata.RESOURCE_NAME_KEY, filename);
          ContentHandler handler = new BodyContentHandler();
          ParseContext context = new ParseContext();
 
          InputStream input = getTestDocument(filename);
          try {
              parser.parse(input, handler, metadata, context);
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
     *  fired for all the embedded entries.
     */
    @Test
    public void testEmbedded() throws Exception {
       Parser parser = new AutoDetectParser(); // Should auto-detect!
       ContentHandler handler = new BodyContentHandler();
       Metadata metadata = new Metadata();

       InputStream stream = ZipParserTest.class.getResourceAsStream(
               "/test-documents/test-documents.tar");
       try {
View Full Code Here
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
     * @throws Exception
     */
    @Test
    public void testWord() throws Exception {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();

        InputStream input = getTestDocument("testWORD.docx");
        try {
            parser.parse(input, handler, metadata, context);
            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Sample Word Document", metadata.get(TikaCoreProperties.TITLE));
            assertEquals("Keith Bennett", metadata.get(TikaCoreProperties.CREATOR));
            assertEquals("Keith Bennett", metadata.get(Metadata.AUTHOR));
            assertTrue(handler.toString().contains("Sample Word Document"));
        } finally {
            input.close();
        }
    }
View Full Code Here
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
     * @throws Exception
     */
    @Test
    public void testWordFootnote() throws Exception {
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        ParseContext context = new ParseContext();

        InputStream input = getTestDocument("footnotes.docx");
        try {
            parser.parse(input, handler, metadata, context);
            assertEquals(
                    "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
                    metadata.get(Metadata.CONTENT_TYPE));
            assertTrue(handler.toString().contains("snoska"));
        } finally {
            input.close();
        }
    }
View Full Code Here
487
488
489
490
491
492
493
494
495
496
497
        InputStream input = OOXMLParserTest.class
                .getResourceAsStream("/test-documents/protectedSheets.xlsx");

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

        try {
            parser.parse(input, handler, metadata, context);
View Full Code Here
TOP

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

  • com.nidhinova.tika.server.TikaService
  • com.tamingtext.tika.TikaTest
  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.droids.tika.TikaDocumentParser
  • org.apache.oodt.cas.protocol.imaps.ImapsProtocol
  • org.apache.stanbol.enhancer.engines.tika.TikaEngine
  • org.apache.tika.bundle.BundleIT
  • org.apache.tika.embedder.ExternalEmbedderTest
  • org.apache.tika.example.ContentHandlerExample
  • org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor
    • 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.