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;
}
@Test
public void testEnglish() throws Exception {
long maxMemory = Runtime.getRuntime().maxMemory();
Assume.assumeTrue("Insufficient max memory: " + maxMemory, maxMemory > 3700000000l);
// Run the test pipeline. Note the full stop at the end of a sentence is preceded by a
// whitespace. This is necessary for it to be detected as a separate token!
JCas jcas = runTest("en", null, "SAP where John Doe works is in Germany .");
// Define the reference data that we expect to get back from the test
String[] namedEntity = {
"[ 10, 18]NamedEntity(PERSON) (John Doe)", "[ 31, 38]NamedEntity(GPE) (Germany)"
};
// Compare the annotations created in the pipeline to the reference data
AssertAnnotations.assertNamedEntity(namedEntity, select(jcas, NamedEntity.class));
}
@Ignore("We don't have these models integrated yet")
@Test
public void testPortuguese() throws Exception {
String[] bosqueTags =
new String[] {
"?",
"adj",
"adv",
"art",
"conj-c",
"conj-s",
"ec",
"in",
"n",
"num",
"pp",
"pron-det",
"pron-indp",
"pron-pers",
"prop",
"prp",
"punc",
"v-fin",
"v-ger",
"v-inf",
"v-pcp",
"vp"
};
JCas jcas =
runTest(
"pt",
null,
"Este é um teste .",
new String[] {"pron-det", "v-fin", "art", "n", "punc"},
new String[] {"PR", "V", "ART", "NN", "PUNC"});
AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
jcas =
runTest(
"pt",
"maxent",
"Este é um teste .",
new String[] {"pron-det", "v-fin", "art", "n", "punc"},
new String[] {"PR", "V", "ART", "NN", "PUNC"});
AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
jcas =
runTest(
"pt",
"perceptron",
"Este é um teste .",
new String[] {"pron-det", "v-fin", "art", "n", "punc"},
new String[] {"PR", "V", "ART", "NN", "PUNC"});
AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
jcas =
runTest(
"pt",
"mm-maxent",
"Este é um teste .",
new String[] {"PROSUB", "V", "ART", "N", "."},
new String[] {"POS", "POS", "POS", "POS", "POS"});
// AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
jcas =
runTest(
"pt",
"mm-perceptron",
"Este é um teste .",
new String[] {"PROSUB", "V", "ART", "N", "."},
new String[] {"POS", "POS", "POS", "POS", "POS"});
// AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
jcas =
runTest(
"pt",
"cogroo",
"Este é um teste .",
new String[] {"pron-det", "v-fin", "artm", "nm", "."},
new String[] {"POS", "POS", "POS", "POS", "POS"});
AssertAnnotations.assertTagset(POS.class, "bosque", bosqueTags, jcas);
}