use of edu.uci.ics.textdb.api.span.Span in project textdb by TextDB.
the class KeywordConjunctionTest method testSingleWordQueryInTextField.
/**
* Verifies GetNextTuple of Keyword Matcher and single word queries in Text
* Field
*
* @throws Exception
*/
@Test
public void testSingleWordQueryInTextField() throws Exception {
// Prepare the query
String query = "TaLL";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstants.FIRST_NAME);
attributeNames.add(TestConstants.LAST_NAME);
attributeNames.add(TestConstants.DESCRIPTION);
// Prepare the expected result list
List<Span> list = new ArrayList<>();
Span span = new Span("description", 0, 4, "tall", "Tall", 0);
list.add(span);
Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
IField[] fields1 = { new StringField("bruce"), new StringField("john Lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("Tall Angry"), new ListField<>(list) };
IField[] fields2 = { new StringField("christian john wayne"), new StringField("rock bale"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Tall Fair"), new ListField<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
expectedResultList.add(tuple2);
// Perform the query
List<Tuple> resultList = KeywordTestHelper.getQueryResults(PEOPLE_TABLE, query, attributeNames, conjunction);
// check the results
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
use of edu.uci.ics.textdb.api.span.Span in project textdb by TextDB.
the class KeywordConjunctionTest method testWordInMultipleFieldsQueryChinese.
/**
* Verifies: data source has multiple attributes, and an entity can appear
* in all the fields and multiple times.
* Test for Chinese data.
*
* @throws Exception
*/
@Test
public void testWordInMultipleFieldsQueryChinese() throws Exception {
// Prepare the query
String query = "建筑";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstantsChinese.FIRST_NAME);
attributeNames.add(TestConstantsChinese.LAST_NAME);
attributeNames.add(TestConstantsChinese.DESCRIPTION);
// Prepare the expected result list
List<Span> list = new ArrayList<>();
Span span1 = new Span("lastName", 0, 2, "建筑", "建筑");
Span span2 = new Span("description", 3, 5, "建筑", "建筑", 2);
list.add(span1);
list.add(span2);
Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
IField[] fields1 = { new StringField("宋江"), new StringField("建筑"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("伟大的建筑是历史的坐标,具有传承的价值。"), new ListField<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
// Perform the query
List<Tuple> resultList = KeywordTestHelper.getQueryResults(CHINESE_TABLE, query, attributeNames, conjunction, Integer.MAX_VALUE, 0);
// check the results
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
use of edu.uci.ics.textdb.api.span.Span in project textdb by TextDB.
the class KeywordConjunctionTest method testMatchingWithLimitOffset.
@Test
public void testMatchingWithLimitOffset() throws TextDBException, ParseException, java.text.ParseException {
String query = "angry";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstants.FIRST_NAME);
attributeNames.add(TestConstants.LAST_NAME);
attributeNames.add(TestConstants.DESCRIPTION);
Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
List<Tuple> resultList = KeywordTestHelper.getQueryResults(PEOPLE_TABLE, query, attributeNames, conjunction, 3, 2);
List<Tuple> expectedList = new ArrayList<>();
Span span1 = new Span("description", 5, 10, "angry", "Angry", 1);
Span span2 = new Span("description", 6, 11, "angry", "Angry", 1);
Span span3 = new Span("description", 40, 45, "angry", "Angry", 8);
Span span4 = new Span("description", 6, 11, "angry", "angry", 1);
List<Span> list1 = new ArrayList<>();
list1.add(span1);
IField[] fields1 = { new StringField("bruce"), new StringField("john Lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("Tall Angry"), new ListField<>(list1) };
List<Span> list2 = new ArrayList<>();
list2.add(span2);
IField[] fields2 = { new StringField("brad lie angelina"), new StringField("pitt"), new IntegerField(44), new DoubleField(6.10), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-12-1972")), new TextField("White Angry"), new ListField<>(list2) };
List<Span> list3 = new ArrayList<>();
list3.add(span3);
IField[] fields3 = { new StringField("george lin lin"), new StringField("lin clooney"), new IntegerField(43), new DoubleField(6.06), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1973")), new TextField("Lin Clooney is Short and lin clooney is Angry"), new ListField<>(list3) };
List<Span> list4 = new ArrayList<>();
list4.add(span4);
IField[] fields4 = { new StringField("Mary brown"), new StringField("Lake Forest"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Short angry"), new ListField<>(list4) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
Tuple tuple3 = new Tuple(new Schema(schemaAttributes), fields3);
Tuple tuple4 = new Tuple(new Schema(schemaAttributes), fields4);
expectedList.add(tuple1);
expectedList.add(tuple2);
expectedList.add(tuple3);
expectedList.add(tuple4);
Assert.assertEquals(expectedList.size(), 4);
Assert.assertEquals(resultList.size(), 2);
Assert.assertTrue(TestUtils.containsAll(expectedList, resultList));
}
use of edu.uci.ics.textdb.api.span.Span in project textdb by TextDB.
the class KeywordConjunctionTest method testSingleWordQueryInStringField.
/**
* Verifies GetNextTuple of Keyword Matcher and single word queries in
* String Field
*
* @throws Exception
*/
@Test
public void testSingleWordQueryInStringField() throws Exception {
// Prepare the query
String query = "bruce";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstants.FIRST_NAME);
attributeNames.add(TestConstants.LAST_NAME);
attributeNames.add(TestConstants.DESCRIPTION);
// Prepare the expected result list
List<Span> list = new ArrayList<>();
Span span = new Span("firstName", 0, 5, "bruce", "bruce");
list.add(span);
Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
IField[] fields1 = { new StringField("bruce"), new StringField("john Lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("Tall Angry"), new ListField<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
// Perform the query
List<Tuple> resultList = KeywordTestHelper.getQueryResults(PEOPLE_TABLE, query, attributeNames, conjunction);
// check the results
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
use of edu.uci.ics.textdb.api.span.Span in project textdb by TextDB.
the class KeywordPhraseTest method testWordInMultipleFieldsQueryWithStopWords4.
/**
* Verifies: Query with Stop Words match corresponding phrases in the
* document Used to cause exception if there is a special symbol with the
* words, ex: big(
*
* @throws Exception
* with Medline data
*/
@Test
public void testWordInMultipleFieldsQueryWithStopWords4() throws Exception {
// Prepare Query
String query = "x-ray";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(keywordTestConstants.ABSTRACT);
// Prepare expected result list
List<Span> list = new ArrayList<>();
Span span1 = new Span(keywordTestConstants.ABSTRACT, 226, 231, "x-ray", "x-ray");
list.add(span1);
Attribute[] schemaAttributes = new Attribute[keywordTestConstants.ATTRIBUTES_MEDLINE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = keywordTestConstants.ATTRIBUTES_MEDLINE[count];
}
schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
IField[] fields = { new IntegerField(17832788), new TextField(""), new TextField("Cosmic X-ray Sources."), new TextField("S Bowyer, E T Byram, T A Chubb, H Friedman"), new StringField("147-3656 Jan 22, 1965"), new TextField("Science (New York, N.Y.)"), new TextField(""), new TextField(""), new TextField("Eight new sources of cosmic x-rays were detected by two Aerobee surveys in 1964. One source, from Sagittarius, is close to the galactic center, and the other, " + "from Ophiuchus, may coincide with Kepler's 1604 supernova. All the x-ray sources are fairly close to the galactic plane."), new DoubleField(0.667832788), new ListField<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
List<Tuple> results = KeywordTestHelper.getQueryResults(MEDLINE_TABLE, query, attributeNames, phrase);
// Perform Check
boolean contains = TestUtils.equals(expectedResultList, results);
Assert.assertTrue(contains);
}
Aggregations