use of org.apache.tika.Tika in project tika by apache.
the class ClassParserTest method testClassParsing.
@Test
public void testClassParsing() throws Exception {
String path = "/test-documents/AutoDetectParser.class";
Metadata metadata = new Metadata();
String content = new Tika().parseToString(ClassParserTest.class.getResourceAsStream(path), metadata);
assertEquals("AutoDetectParser", metadata.get(TikaCoreProperties.TITLE));
assertEquals("AutoDetectParser.class", metadata.get(Metadata.RESOURCE_NAME_KEY));
assertTrue(content.contains("package org.apache.tika.parser;"));
assertTrue(content.contains("class AutoDetectParser extends CompositeParser"));
assertTrue(content.contains("private org.apache.tika.mime.MimeTypes types"));
assertTrue(content.contains("public void parse(" + "java.io.InputStream, org.xml.sax.ContentHandler," + " org.apache.tika.metadata.Metadata) throws" + " java.io.IOException, org.xml.sax.SAXException," + " org.apache.tika.exception.TikaException;"));
assertTrue(content.contains("private byte[] getPrefix(java.io.InputStream, int)" + " throws java.io.IOException;"));
}
use of org.apache.tika.Tika in project tika by apache.
the class AudioParserTest method testWAV.
@Test
public void testWAV() throws Exception {
String path = "/test-documents/testWAV.wav";
Metadata metadata = new Metadata();
String content = new Tika().parseToString(AudioParserTest.class.getResourceAsStream(path), metadata);
assertEquals("audio/x-wav", metadata.get(Metadata.CONTENT_TYPE));
assertEquals("44100.0", metadata.get("samplerate"));
assertEquals("2", metadata.get("channels"));
assertEquals("16", metadata.get("bits"));
assertEquals("PCM_SIGNED", metadata.get("encoding"));
assertEquals("", content);
}
use of org.apache.tika.Tika in project tika by apache.
the class TikaVersionTest method testGetVersion.
@Test
public void testGetVersion() throws Exception {
Response response = WebClient.create(endPoint + VERSION_PATH).type("text/plain").accept("text/plain").get();
assertEquals(new Tika().toString(), getStringFromInputStream((InputStream) response.getEntity()));
}
use of org.apache.tika.Tika in project tika by apache.
the class TikaWelcomeTest method testGetTextWelcome.
@Test
public void testGetTextWelcome() throws Exception {
Response response = WebClient.create(endPoint + WELCOME_PATH).type("text/plain").accept("text/plain").get();
String text = getStringFromInputStream((InputStream) response.getEntity());
assertContains(new Tika().toString(), text);
// Check our details were found
assertContains("GET " + WELCOME_PATH, text);
assertContains("=> text/plain", text);
// Check that the Tika Version details come through too
assertContains("GET " + VERSION_PATH, text);
}
use of org.apache.tika.Tika in project tika by apache.
the class TIAParsingExample method parseToReaderExample.
public static void parseToReaderExample() throws Exception {
File document = new File("example.doc");
try (Reader reader = new Tika().parse(document)) {
char[] buffer = new char[1000];
int n = reader.read(buffer);
while (n != -1) {
System.out.append(CharBuffer.wrap(buffer, 0, n));
n = reader.read(buffer);
}
}
}
Aggregations