use of org.xml.sax.ContentHandler in project tika by apache.
the class TikaTest method getXML.
protected XMLResult getXML(InputStream input, Parser parser, Metadata metadata, ParseContext context) throws Exception {
if (context == null) {
context = new ParseContext();
}
try {
ContentHandler handler = new ToXMLContentHandler();
parser.parse(input, handler, metadata, context);
return new XMLResult(handler.toString(), metadata);
} finally {
input.close();
}
}
use of org.xml.sax.ContentHandler in project tika by apache.
the class AutoDetectParserTest method testOggFlacAudio.
/**
* Test to ensure that the Ogg Audio parsers (Vorbis, Opus, Flac etc)
* have been correctly included, and are available
*/
@SuppressWarnings("deprecation")
@Test
public void testOggFlacAudio() throws Exception {
// The three test files should all have similar test data
String[] testFiles = new String[] { "testVORBIS.ogg", "testFLAC.flac", "testFLAC.oga", "testOPUS.opus" };
MediaType[] mediaTypes = new MediaType[] { MediaType.parse(OGG_VORBIS), MediaType.parse(FLAC_NATIVE), MediaType.parse(OGG_FLAC), MediaType.parse(OGG_OPUS) };
// Check we can load the parsers, and they claim to do the right things
VorbisParser vParser = new VorbisParser();
assertNotNull("Parser not found for " + mediaTypes[0], vParser.getSupportedTypes(new ParseContext()));
FlacParser fParser = new FlacParser();
assertNotNull("Parser not found for " + mediaTypes[1], fParser.getSupportedTypes(new ParseContext()));
assertNotNull("Parser not found for " + mediaTypes[2], fParser.getSupportedTypes(new ParseContext()));
OpusParser oParser = new OpusParser();
assertNotNull("Parser not found for " + mediaTypes[3], oParser.getSupportedTypes(new ParseContext()));
// Check we found the parser
CompositeParser parser = (CompositeParser) tika.getParser();
for (MediaType mt : mediaTypes) {
assertNotNull("Parser not found for " + mt, parser.getParsers().get(mt));
}
// Have each file parsed, and check
for (int i = 0; i < testFiles.length; i++) {
String file = testFiles[i];
try (InputStream input = AutoDetectParserTest.class.getResourceAsStream("/test-documents/" + file)) {
if (input == null) {
fail("Could not find test file " + file);
}
Metadata metadata = new Metadata();
ContentHandler handler = new BodyContentHandler();
new AutoDetectParser(tika).parse(input, handler, metadata);
assertEquals("Incorrect content type for " + file, mediaTypes[i].toString(), metadata.get(Metadata.CONTENT_TYPE));
// Check some of the common metadata
// Old style metadata
assertEquals("Test Artist", metadata.get(Metadata.AUTHOR));
assertEquals("Test Title", metadata.get(Metadata.TITLE));
// New style metadata
assertEquals("Test Artist", metadata.get(TikaCoreProperties.CREATOR));
assertEquals("Test Title", metadata.get(TikaCoreProperties.TITLE));
// Check some of the XMPDM metadata
if (!file.endsWith(".opus")) {
assertEquals("Test Album", metadata.get(XMPDM.ALBUM));
}
assertEquals("Test Artist", metadata.get(XMPDM.ARTIST));
assertEquals("Stereo", metadata.get(XMPDM.AUDIO_CHANNEL_TYPE));
assertEquals("44100", metadata.get(XMPDM.AUDIO_SAMPLE_RATE));
// Check some of the text
String content = handler.toString();
assertTrue(content.contains("Test Title"));
assertTrue(content.contains("Test Artist"));
}
}
}
use of org.xml.sax.ContentHandler in project tika by apache.
the class MyFirstTika method parseUsingAutoDetect.
public static String parseUsingAutoDetect(String filename, TikaConfig tikaConfig, Metadata metadata) throws Exception {
System.out.println("Handling using AutoDetectParser: [" + filename + "]");
AutoDetectParser parser = new AutoDetectParser(tikaConfig);
ContentHandler handler = new BodyContentHandler();
TikaInputStream stream = TikaInputStream.get(new File(filename), metadata);
parser.parse(stream, handler, metadata, new ParseContext());
return handler.toString();
}
use of org.xml.sax.ContentHandler in project tika by apache.
the class ExtractEmbeddedFiles method extract.
public void extract(InputStream is, Path outputDir) throws SAXException, TikaException, IOException {
Metadata m = new Metadata();
ParseContext c = new ParseContext();
ContentHandler h = new BodyContentHandler(-1);
c.set(Parser.class, parser);
EmbeddedDocumentExtractor ex = new MyEmbeddedDocumentExtractor(outputDir, c);
c.set(EmbeddedDocumentExtractor.class, ex);
parser.parse(is, h, m, c);
}
use of org.xml.sax.ContentHandler in project tika by apache.
the class ContentHandlerExample method parseBodyToHTML.
/**
* Example of extracting just the body as HTML, without the
* head part, as a string
*/
public String parseBodyToHTML() throws IOException, SAXException, TikaException {
ContentHandler handler = new BodyContentHandler(new ToXMLContentHandler());
AutoDetectParser parser = new AutoDetectParser();
Metadata metadata = new Metadata();
try (InputStream stream = ContentHandlerExample.class.getResourceAsStream("test.doc")) {
parser.parse(stream, handler, metadata);
return handler.toString();
}
}
Aggregations