Package org.apache.tika.parser

Examples of org.apache.tika.parser.ParseContext

34
35
36
37
38
39
40
41
42
43
44
        InputStream input = Pkcs7ParserTest.class.getResourceAsStream(
                "/test-documents/testDetached.p7s");
        try {
            ContentHandler handler = new BodyContentHandler();
            Metadata metadata = new Metadata();
            new Pkcs7Parser().parse(input, handler, metadata, new ParseContext());
        } catch (NullPointerException npe) {
            fail("should not get NPE");
        } catch (TikaException te) {
            assertTrue(te.toString().indexOf("cannot parse detached pkcs7 signature") != -1);
        } finally {
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
    @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 {
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
        StringWriter writer = new StringWriter();
        tika.getParser().parse(
                     new FileInputStream(file),
                     new WriteOutContentHandler(writer),
                     metadata,
                     new ParseContext());
        String content = writer.toString();

        assertEquals("application/rtf", metadata.get(Metadata.CONTENT_TYPE));
        assertContains("Test", content);
        assertContains("indexation Word", content);
View Full Code Here
384
385
386
387
388
389
390
391
392
        StringWriter writer = new StringWriter();
        tika.getParser().parse(
                     new FileInputStream(file),
                     new WriteOutContentHandler(writer),
                     metadata,
                     new ParseContext());
        String content = writer.toString();
        return new Result(content, metadata);
    }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
                    }
                }
            };
            new HtmlParser().parse(
                    stream, new TeeContentHandler(body, link),
                    metadata, new ParseContext());
        } finally {
            stream.close();
        }

        assertEquals(
View Full Code Here
147
148
149
150
151
152
153
154
    @Test
    public void testParseEmpty() throws Exception {
        ContentHandler handler = new BodyContentHandler();
        new HtmlParser().parse(
                new ByteArrayInputStream(new byte[0]),
                handler,  new Metadata(), new ParseContext());
        assertEquals("", handler.toString());
    }
View Full Code Here
227
228
229
230
231
232
233
234
235
                            links.add(atts.getValue("", "href"));
                        }
                    }
                },
                new Metadata(),
                new ParseContext());
        assertEquals(1, links.size());
        assertEquals(url, links.get(0));
    }
View Full Code Here
261
262
263
264
265
266
267
268
            + "<title>the name is \u00e1ndre</title>"
            + "</head><body></body></html>";
        Metadata metadata = new Metadata();
        new HtmlParser().parse (
                new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
                new BodyContentHandler(),  metadata, new ParseContext());
        assertEquals("ISO-8859-1", metadata.get(Metadata.CONTENT_ENCODING));
    }
View Full Code Here
278
279
280
281
282
283
284
285
                + "<title>the name is \u00e1ndre</title>"
                + "</head><body></body></html>";
        Metadata metadata = new Metadata();
        new HtmlParser().parse(
                new ByteArrayInputStream(test.getBytes("ISO-8859-1")),
                new BodyContentHandler(), metadata, new ParseContext());
        assertEquals("ISO-8859-15", metadata.get(Metadata.CONTENT_ENCODING));
    }
View Full Code Here
293
294
295
296
297
298
299
300
        String test =
            "<html><head><title>\u017d</title></head><body></body></html>";
        Metadata metadata = new Metadata();
        new HtmlParser().parse (
                new ByteArrayInputStream(test.getBytes("UTF-8")),
                new BodyContentHandler(),  metadata, new ParseContext());
        assertEquals("\u017d", metadata.get(TikaCoreProperties.TITLE));
    }
View Full Code Here
TOP

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

  • com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell
  • com.nidhinova.tika.server.TikaService
  • com.tamingtext.tika.TikaTest
  • cx.fbn.nevernote.threads.IndexRunner
  • gov.nara.nwts.ftappImg.jpeg.JpegExtractor
  • org.apache.chemistry.opencmis.client.parser.MetadataParserTika
  • org.apache.jackrabbit.core.query.lucene.JackrabbitParser
  • org.apache.jackrabbit.core.query.lucene.LazyTextExtractorField$ParsingTask
  • org.apache.jackrabbit.oak.plugins.index.lucene.LuceneIndexEditor
  • org.apache.nutch.parse.tika.DOMContentUtilsTest
    • 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.