use of edu.uci.ics.texera.api.field.IntegerField 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);
}
use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingScan.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and single word
* queries in String Field using SCANOPERATOR
*/
@Test
public void testSingleWordQueryInStringFieldUsingScan() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("bruce"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
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] = RESULTS_ATTRIBUTE;
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<Span>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResults = new ArrayList<Tuple>();
expectedResults.add(tuple1);
List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.SUBSTRING_SCANBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingScanChinese.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and single word
* queries in Text Field using SCANOPERATOR in Chinese.
*/
@Test
public void testSingleWordQueryInTextFieldUsingScanChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("学院"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list1 = new ArrayList<Span>();
Span span1 = new Span("description", 8, 10, "学院", "学院");
list1.add(span1);
List<Span> list2 = new ArrayList<Span>();
Span span2 = new Span("description", 7, 9, "学院", "学院");
list2.add(span2);
Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
IField[] fields1 = { new StringField("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list1) };
IField[] fields2 = { new StringField("孔明"), new StringField("洛克贝尔"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("北京大学计算机学院"), new ListField<Span>(list2) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
List<Tuple> expectedResults = new ArrayList<Tuple>();
expectedResults.add(tuple1);
expectedResults.add(tuple2);
List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.SUBSTRING_SCANBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingKeywordChinese.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and multiple word
* queries in String Field using KEYWORDOPERATOR
* Test in Chinese.
*/
@Test
public void testSingleWordQueryInStringFieldUsingKeywordChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("无忌", "长孙"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list1 = new ArrayList<Span>();
Span span1 = new Span("lastName", 0, 2, "长孙", "长孙");
Span span2 = new Span("firstName", 0, 2, "无忌", "无忌");
list1.add(span1);
list1.add(span2);
Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
IField[] fields1 = { new StringField("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list1) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResults = new ArrayList<Tuple>();
expectedResults.add(tuple1);
List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.CONJUNCTION_INDEXBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingKeywordChinese.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and single word
* queries in Text Field using KEYWORD OPERATOR in Chinese
*/
@Test
public void testSingleWordQueryInTextFieldUsingKeywordChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("北京大学"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span = new Span("description", 0, 4, "北京大学", "北京大学", 0);
list.add(span);
Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
for (int count = 0; count < schemaAttributes.length - 1; count++) {
schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
}
schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
IField[] fields1 = { new StringField("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list) };
IField[] fields2 = { new StringField("孔明"), new StringField("洛克贝尔"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("北京大学计算机学院"), new ListField<Span>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
List<Tuple> expectedResults = new ArrayList<Tuple>();
expectedResults.add(tuple1);
expectedResults.add(tuple2);
List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.CONJUNCTION_INDEXBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
Aggregations