@Test
public void testJavaScript() throws IOException, ImporterHandlerException {
String script =
"metadata.addString('test', 'success');"
+ "text = content.replace(/Alice/g, 'Roger');"
+ "/*return*/ text;";
ScriptTransformer t = new ScriptTransformer();
t.setScript(script);
File htmlFile = TestUtil.getAliceHtmlFile();
FileInputStream is = new FileInputStream(htmlFile);
ByteArrayOutputStream out = new ByteArrayOutputStream();
ImporterMetadata metadata = new ImporterMetadata();
metadata.setString(ImporterMetadata.DOC_CONTENT_TYPE, "text/html");
t.transformDocument(htmlFile.getAbsolutePath(), is, out, metadata, false);
is.close();
String successField = metadata.getString("test");
Assert.assertEquals("success", successField);
String content = new String(out.toString());
Assert.assertEquals(0, StringUtils.countMatches(content, "Alice"));
Assert.assertEquals(34, StringUtils.countMatches(content, "Roger"));
}
@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();
}
