@Test
public void testWriteRead() throws IOException {
StripAfterTransformer t = new StripAfterTransformer();
t.setInclusive(true);
t.setStripAfterRegex("<p>");
System.out.println("Writing/Reading this: " + t);
ConfigurationUtil.assertWriteRead(t);
}
@Test
public void testTransformTextDocument() throws IOException, ImporterHandlerException {
StripAfterTransformer t = new StripAfterTransformer();
t.setStripAfterRegex("<p>");
t.setCaseSensitive(false);
t.setInclusive(true);
File htmlFile = TestUtil.getAliceHtmlFile();
FileInputStream is = new FileInputStream(htmlFile);
ByteArrayOutputStream os = new ByteArrayOutputStream();
ImporterMetadata metadata = new ImporterMetadata();
metadata.setString(ImporterMetadata.DOC_CONTENT_TYPE, "text/html");
t.transformDocument(htmlFile.getAbsolutePath(), is, os, metadata, false);
System.out.println(os.toString());
Assert.assertEquals(
"Length of doc content after transformation is incorrect.", 552, os.toString().length());
is.close();
os.close();
}
