@Test
public void testEnglishAutoLoad() throws Exception {
String oldModelCache =
System.setProperty(ResourceObjectProviderBase.PROP_REPO_CACHE, "target/test-output/models");
String oldOfflineMode =
System.setProperty(
ResourceObjectProviderBase.PROP_REPO_OFFLINE,
ResourceObjectProviderBase.FORCE_AUTO_LOAD);
try {
TestRunner.autoloadModelsOnNextTestRun();
runTest(
"en",
null,
"This is a test .",
new String[] {"DT", "VBZ", "DT", "NN", "."},
new String[] {"ART", "V", "ART", "NN", "PUNC"});
} finally {
if (oldModelCache != null) {
System.setProperty(ResourceObjectProviderBase.PROP_REPO_CACHE, oldModelCache);
} else {
System.getProperties().remove(ResourceObjectProviderBase.PROP_REPO_CACHE);
}
if (oldOfflineMode != null) {
System.setProperty(ResourceObjectProviderBase.PROP_REPO_OFFLINE, oldOfflineMode);
} else {
System.getProperties().remove(ResourceObjectProviderBase.PROP_REPO_OFFLINE);
}
}
}
private JCas runTest(String text) throws Exception {
AnalysisEngine engine = createEngine(LangDetectLanguageIdentifier.class);
JCas aJCas = TestRunner.runTest(engine, "en", text);
return aJCas;
}
/**
* Simple test case: one stopword file.
*
* @throws UIMAException
*/
@Test
public void test() throws UIMAException {
String[] expectedTokens = new String[] {"text", "containing", "stopwords", "."};
AnalysisEngineDescription stopwordremover =
createEngineDescription(
StopWordRemover.class, StopWordRemover.PARAM_MODEL_LOCATION, STOPWORDSFILE_LOCATION1);
JCas jcas = TestRunner.runTest(stopwordremover, LANGUAGE, TEXT);
assertToken(expectedTokens, select(jcas, Token.class));
}
private void runTest(
String language, String variant, String testDocument, String[] tags, String[] tagClasses)
throws Exception {
AnalysisEngine engine = createEngine(LbjPosTagger.class);
JCas jcas = TestRunner.runTest(engine, language, testDocument);
AssertAnnotations.assertPOS(tagClasses, tags, select(jcas, POS.class));
}
private JCas runTest(
String language, String variant, String testDocument, String[] tags, String[] tagClasses)
throws Exception {
AnalysisEngine engine =
createEngine(
OpenNlpPosTagger.class,
OpenNlpPosTagger.PARAM_VARIANT,
variant,
OpenNlpPosTagger.PARAM_PRINT_TAGSET,
true);
JCas jcas = TestRunner.runTest(engine, language, testDocument);
AssertAnnotations.assertPOS(tagClasses, tags, select(jcas, POS.class));
return jcas;
}
// Auxiliary method that sets up the analysis engine or pipeline used in the test.
// Typically, we have multiple tests per unit test file that each invoke this method.
private JCas runTest(String language, String variant, String testDocument) throws Exception {
AnalysisEngineDescription postagger = createEngineDescription(Nlp4JPosTagger.class);
AnalysisEngineDescription lemmatizer = createEngineDescription(Nlp4JLemmatizer.class);
AnalysisEngineDescription ner =
createEngineDescription(
Nlp4JNamedEntityRecognizer.class,
Nlp4JNamedEntityRecognizer.PARAM_VARIANT,
variant,
Nlp4JNamedEntityRecognizer.PARAM_PRINT_TAGSET,
true);
AnalysisEngineDescription engine = createEngineDescription(postagger, lemmatizer, ner);
// Here we invoke the TestRunner which performs basic whitespace tokenization and
// sentence splitting, creates a CAS, runs the pipeline, etc. TestRunner explicitly
// disables automatic model loading. Thus, models used in unit tests must be explicitly
// made dependencies in the pom.xml file.
return TestRunner.runTest(engine, language, testDocument);
}