Package org.apache.tika.metadata

Examples of org.apache.tika.metadata.Metadata

67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
    public void testExcelParserFormatting() throws Exception {
        InputStream input = ExcelParserTest.class.getResourceAsStream(
                "/test-documents/testEXCEL-formats.xls");
        try {
            Metadata metadata = new Metadata();
            ContentHandler handler = new BodyContentHandler();
            new OfficeParser().parse(input, handler, metadata);

            assertEquals(
                    "application/vnd.ms-excel",
                    metadata.get(Metadata.CONTENT_TYPE));

            String content = handler.toString();

            // Number #,##0.00
            assertTrue(content.contains("1,599.99"));
View Full Code Here
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
    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));

            assertEquals("true", metadata.get(TikaMetadataKeys.PROTECTED));
        } finally {
            input.close();
        }
    }
View Full Code Here
129
130
131
132
133
134
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
        } else {
          throw new IllegalArgumentException("Parameter must be instance of byte[]");
        }

        ContentHandler textHandler = new BodyContentHandler(fileLengthLimit);
        Metadata metadata = new Metadata();
        ParseContext context = new ParseContext();

        try {
          metadata.set(Metadata.CONTENT_TYPE, tika.detect(inputStream));

          parser.parse(inputStream, textHandler, metadata, context);

          bean.set(headingField, metadata.get(TikaCoreProperties.TITLE));

          if (bean.get(createTimestampField) == null) {
            bean.set(createTimestampField, metadata.get(TikaCoreProperties.CREATED));
          }
          if (bean.get(editTimestampField) == null) {
            bean.set(editTimestampField, metadata.get(TikaCoreProperties.MODIFIED));
          }
          if (bean.get(keywordsField) == null) {
            bean.set(keywordsField, metadata.get(TikaCoreProperties.KEYWORDS));
          }
          if (bean.get(publishTimestampField) == null) {
            bean.set(publishTimestampField, metadata.get(TikaCoreProperties.PRINT_DATE));
          }
          if (bean.get(mimetypeField) == null) {
            //HttpHeaders.CONTENT_TYPE
            bean.set(mimetypeField, metadata.get(Metadata.CONTENT_TYPE));
          }

          String content = prepareContent(bean, textHandler);
          bean.set(this.targetAttributeField, content);
View Full Code Here
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
                new TikaServer(Integer.parseInt(arg)).start();
            } else if (arg.equals("-")) {
                InputStream stream =
                    TikaInputStream.get(new CloseShieldInputStream(System.in));
                try {
                    type.process(stream, System.out, new Metadata());
                } finally {
                    stream.close();
                }
            } else {
                URL url;
                File file = new File(arg);
                if (file.isFile()) {
                    url = file.toURI().toURL();
                } else {
                    url = new URL(arg);
                }
                Metadata metadata = new Metadata();
                InputStream input = TikaInputStream.get(url, metadata);
                try {
                    type.process(input, System.out, metadata);
                } finally {
                    input.close();
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
        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
210
211
212
213
214
215
216
217
218
219
        // Finally, assume plain text if no control bytes are found
        try {
            TextDetector detector = new TextDetector(getMinLength());
            ByteArrayInputStream stream = new ByteArrayInputStream(data);
            return forName(detector.detect(stream, new Metadata()).toString());
        } catch (Exception e) {
            return rootMimeType;
        }
    }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
    @Test
    public void testOutputStream() throws Exception {
        ByteArrayOutputStream buffer = new ByteArrayOutputStream();

        XHTMLContentHandler xhtml = new XHTMLContentHandler(
                new BodyContentHandler(buffer), new Metadata());
        xhtml.startDocument();
        xhtml.element("p", "Test text");
        xhtml.endDocument();

        assertEquals("Test text\n", buffer.toString());
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
89
90
    @Test
    public void testByteOrderMark() throws Exception {
        assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
                new ByteArrayInputStream("\ufefftest".getBytes("UTF-16LE")),
                new Metadata()));
        assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
                new ByteArrayInputStream("\ufefftest".getBytes("UTF-16BE")),
                new Metadata()));
        assertEquals(MediaType.TEXT_PLAIN, mimeTypes.detect(
                new ByteArrayInputStream("\ufefftest".getBytes("UTF-8")),
                new Metadata()));
    }
View Full Code Here
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
        }
        for (Map.Entry<String,COSObjectable> ent : embeddedFileNames.entrySet()) {
            PDComplexFileSpecification spec = (PDComplexFileSpecification) ent.getValue();
            PDEmbeddedFile file = spec.getEmbeddedFile();

            Metadata metadata = new Metadata();
            // TODO: other metadata?
            metadata.set(Metadata.RESOURCE_NAME_KEY, ent.getKey());
            metadata.set(Metadata.CONTENT_TYPE, file.getSubtype());
            metadata.set(Metadata.CONTENT_LENGTH, Long.toString(file.getSize()));

            if (embeddedExtractor.shouldParseEmbedded(metadata)) {
                TikaInputStream stream = TikaInputStream.get(file.createInputStream());
                try {
                    embeddedExtractor.parseEmbedded(
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
        assertNotNull("Test stream: ["+urlOrFileName+"] is null!", in);
        if (!in.markSupported()) {
            in = new java.io.BufferedInputStream(in);
        }
        try {
            Metadata metadata = new Metadata();
            String mime = this.mimeTypes.detect(in, metadata).toString();
            assertEquals(urlOrFileName + " is not properly detected: detected.", expected, mime);

            //Add resource name and test again
            metadata.set(Metadata.RESOURCE_NAME_KEY, urlOrFileName);
            mime = this.mimeTypes.detect(in, metadata).toString();
            assertEquals(urlOrFileName + " is not properly detected after adding resource name.", expected, mime);
        } finally {
            in.close();
        }       
View Full Code Here
TOP

Related Classes of org.apache.tika.metadata.Metadata

  • bixo.parser.TikaCallableTest
  • com.tamingtext.tika.TikaTest
  • cx.fbn.nevernote.threads.IndexRunner
  • org.apache.any23.mime.TikaMIMETypeDetector
  • org.apache.chemistry.opencmis.client.parser.MetadataParserTika
  • org.apache.cxf.jaxrs.ext.search.tika.TikaContentExtractor
  • org.apache.jackrabbit.core.query.lucene.NodeIndexer
  • org.apache.jackrabbit.oak.plugins.index.lucene.LuceneIndexEditor
  • org.apache.jackrabbit.server.io.DefaultHandler
  • org.apache.jackrabbit.server.io.ImportContextImpl
    • 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.