use of com.yahoo.language.simple.SimpleLinguistics in project vespa by vespa-engine.
the class DefaultFieldNameTestCase method requireThatDefaultFieldNameIsAppliedWhenArgumentIsMissing.
@Test
public void requireThatDefaultFieldNameIsAppliedWhenArgumentIsMissing() throws ParseException {
IndexingInput input = new IndexingInput("input");
InputExpression exp = (InputExpression) Expression.newInstance(new ScriptParserContext(new SimpleLinguistics()).setInputStream(input).setDefaultFieldName("foo"));
assertEquals("foo", exp.getFieldName());
}
use of com.yahoo.language.simple.SimpleLinguistics in project vespa by vespa-engine.
the class NGramTestCase method requireThatHashCodeAndEqualsAreImplemented.
@Test
public void requireThatHashCodeAndEqualsAreImplemented() {
Linguistics linguistics = new SimpleLinguistics();
NGramExpression exp = new NGramExpression(linguistics, 69);
assertFalse(exp.equals(new Object()));
assertFalse(exp.equals(new NGramExpression(Mockito.mock(Linguistics.class), 96)));
assertFalse(exp.equals(new NGramExpression(linguistics, 96)));
assertEquals(exp, new NGramExpression(linguistics, 69));
assertEquals(exp.hashCode(), new NGramExpression(new SimpleLinguistics(), 69).hashCode());
}
use of com.yahoo.language.simple.SimpleLinguistics in project vespa by vespa-engine.
the class NGramTestCase method testNGrams.
@Test
public void testNGrams() {
ExecutionContext context = new ExecutionContext(new SimpleTestAdapter());
context.setValue(new StringFieldValue("en gul Bille sang... "));
new NGramExpression(new SimpleLinguistics(), 3).execute(context);
StringFieldValue value = (StringFieldValue) context.getValue();
assertEquals("Grams are pure annotations - field value is unchanged", "en gul Bille sang... ", value.getString());
SpanTree gramTree = value.getSpanTree(SpanTrees.LINGUISTICS);
assertNotNull(gramTree);
SpanList grams = (SpanList) gramTree.getRoot();
Iterator<SpanNode> i = grams.childIterator();
// en
assertSpan(0, 2, true, i, gramTree);
// <space>
assertSpan(2, 1, false, i, gramTree);
// gul
assertSpan(3, 3, true, i, gramTree);
// <space>
assertSpan(6, 1, false, i, gramTree);
// Bil
assertSpan(7, 3, true, i, gramTree, "bil");
assertSpan(8, 3, true, i, gramTree);
assertSpan(9, 3, true, i, gramTree);
// <space>
assertSpan(12, 1, false, i, gramTree);
assertSpan(13, 3, true, i, gramTree);
assertSpan(14, 3, true, i, gramTree);
// <...space>
assertSpan(17, 4, false, i, gramTree);
assertFalse(i.hasNext());
}
use of com.yahoo.language.simple.SimpleLinguistics in project vespa by vespa-engine.
the class TokenizerTestCase method testSpecialTokenConfigurationOther.
@Test
public void testSpecialTokenConfigurationOther() {
String tokenFile = "file:src/test/java/com/yahoo/prelude/query/parser/test/specialtokens.cfg";
SpecialTokenRegistry r = new SpecialTokenRegistry(tokenFile);
assertEquals("Special tokens configured", 6, r.getSpecialTokens("default").size());
assertEquals("Special tokens configured", 4, r.getSpecialTokens("other").size());
Tokenizer tokenizer = new Tokenizer(new SimpleLinguistics());
tokenizer.setSpecialTokens(r.getSpecialTokens("other"));
List<?> tokens = tokenizer.tokenize("with space,!!!*** [huh] or ------ " + "know, &&&%%% b.s.d.");
assertEquals(new Token(WORD, "with"), tokens.get(0));
assertEquals(new Token(SPACE, " "), tokens.get(1));
assertEquals(new Token(WORD, "space"), tokens.get(2));
assertEquals(new Token(COMMA, ","), tokens.get(3));
assertEquals(new Token(WORD, "!!!***"), tokens.get(4));
assertEquals(new Token(SPACE, " "), tokens.get(5));
assertEquals(new Token(WORD, "[huh]"), tokens.get(6));
assertEquals(new Token(SPACE, " "), tokens.get(7));
assertEquals(new Token(WORD, "or"), tokens.get(8));
assertEquals(new Token(SPACE, " "), tokens.get(9));
assertEquals(new Token(WORD, "------"), tokens.get(10));
assertEquals(new Token(SPACE, " "), tokens.get(11));
assertEquals(new Token(WORD, "know"), tokens.get(12));
assertEquals(new Token(COMMA, ","), tokens.get(13));
assertEquals(new Token(SPACE, " "), tokens.get(14));
assertEquals(new Token(WORD, "&&&%%%"), tokens.get(15));
assertEquals(new Token(SPACE, " "), tokens.get(16));
assertEquals(new Token(WORD, "b"), tokens.get(17));
assertEquals(new Token(DOT, "."), tokens.get(18));
assertEquals(new Token(WORD, "s"), tokens.get(19));
assertEquals(new Token(DOT, "."), tokens.get(20));
assertEquals(new Token(WORD, "d"), tokens.get(21));
assertEquals(new Token(DOT, "."), tokens.get(22));
assertTrue(((Token) tokens.get(10)).isSpecial());
}
use of com.yahoo.language.simple.SimpleLinguistics in project vespa by vespa-engine.
the class TokenizerTestCase method testSpecialTokenCombination.
@Test
public void testSpecialTokenCombination() {
Tokenizer tokenizer = new Tokenizer(new SimpleLinguistics());
tokenizer.setSpecialTokens(createSpecialTokens());
List<?> tokens = tokenizer.tokenize("c#, c++ or .net know, not tcp/ip");
assertEquals(new Token(WORD, "c#"), tokens.get(0));
assertEquals(new Token(COMMA, ","), tokens.get(1));
assertEquals(new Token(SPACE, " "), tokens.get(2));
assertEquals(new Token(WORD, "c++"), tokens.get(3));
assertEquals(new Token(SPACE, " "), tokens.get(4));
assertEquals(new Token(WORD, "or"), tokens.get(5));
assertEquals(new Token(SPACE, " "), tokens.get(6));
assertEquals(new Token(WORD, ".net"), tokens.get(7));
assertEquals(new Token(SPACE, " "), tokens.get(8));
assertEquals(new Token(WORD, "know"), tokens.get(9));
assertEquals(new Token(COMMA, ","), tokens.get(10));
assertEquals(new Token(SPACE, " "), tokens.get(11));
assertEquals(new Token(WORD, "not"), tokens.get(12));
assertEquals(new Token(SPACE, " "), tokens.get(13));
assertEquals(new Token(WORD, "tcp/ip"), tokens.get(14));
}
Aggregations