import
static
org.hamcrest.CoreMatchers.containsString;
import
static
org.junit.Assert.assertEquals;
import
static
org.junit.Assert.assertThat;
import
java.io.IOException;
import
java.io.InputStream;
import
org.apache.tika.exception.TikaException;
import
org.apache.tika.metadata.Metadata;
import
org.junit.Test;
import
org.xml.sax.SAXException;
public
class
SampleTikaWayUnitTest {
@Test
public
void
withDetectorFindingTheResultTypeAsDocumentType()
throws
IOException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"pdfdocument.txt"
);
String resultantMediaType = SampleTikaAnalysis.detectingTheDocTypeByUsingDetector(inputStream);
assertEquals(
"application/pdf"
, resultantMediaType);
inputStream.close();
}
@Test
public
void
withFacadeFindingTheResultTypeAsDocumentType()
throws
IOException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"pdfdocument.txt"
);
String resultantMediaType = SampleTikaAnalysis.detectDocTypeUsingFacade(inputStream);
assertEquals(
"application/pdf"
, resultantMediaType);
inputStream.close();
}
@Test
public
void
byUsingParserAndGettingContent()
throws
IOException, TikaException, SAXException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"worddocument.docx"
);
String documentContent = SampleTikaAnalysis.extractContentUsingParser(inputStream);
assertThat(documentContent, containsString(
"OpenSource REST API URL"
));
assertThat(documentContent, containsString(
"Spring MVC"
));
inputStream.close();
}
@Test
public
void
byUsingFacadeAndGettingContent()
throws
IOException, TikaException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"worddocument.docx"
);
String documentContent = SampleTikaAnalysis.extractContentUsingFacade(inputStream);
assertThat(documentContent, containsString(
"OpenSource REST API URL"
));
assertThat(documentContent, containsString(
"Spring MVC"
));
inputStream.close();
}
@Test
public
void
byUsingParserAndGettingMetadata()
throws
IOException, TikaException, SAXException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"exceldocument.xlsx"
);
Metadata retrieveMetadata = SampleTikaAnalysis.extractMetadatatUsingParser(inputStream);
assertEquals(
"org.apache.tika.parser.DefaultParser"
, retrieveMetadata.get(
"X-Parsed-By"
));
assertEquals(
"Microsoft Office User"
, retrieveMetadata.get(
"Author"
));
inputStream.close();
}
@Test
public
void
byUsingFacadeAndGettingMetadata()
throws
IOException, TikaException {
InputStream inputStream =
this
.getClass().getClassLoader().getResourceAsStream(
"exceldocument.xlsx"
);
Metadata retrieveMetadata = SampleTikaAnalysis.extractMetadatatUsingFacade(inputStream);
assertEquals(
"org.apache.tika.parser.DefaultParser"
, retrieveMetadata.get(
"X-Parsed-By"
));
assertEquals(
"Microsoft Office User"
, retrieveMetadata.get(
"Author"
));
inputStream.close();
}
}