use of edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary 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);
}
use of edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingKeyword.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and multiple word
* queries in String Field using KEYWORDOPERATOR
*/
@Test
public void testSingleWordQueryInStringFieldUsingKeyword() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("john Lee", "bruce"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list1 = new ArrayList<Span>();
Span span1 = new Span("lastName", 0, 8, "john Lee", "john Lee");
Span span2 = new Span("firstName", 0, 5, "bruce", "bruce");
list1.add(span1);
list1.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] = 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>(list1) };
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.CONJUNCTION_INDEXBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary in project textdb by TextDB.
the class DictionaryMatcherTest method testMultipleWordsQueryUsingScanChinese.
/**
* Scenario: verifies ITuple returned by DictionaryMatcher and multiple
* word queries using SCAN OPERATOR in Chinese
*/
@Test
public void testMultipleWordsQueryUsingScanChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("洛克贝尔"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span = new Span("lastName", 0, 4, "洛克贝尔", "洛克贝尔");
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("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);
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.SUBSTRING_SCANBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
Aggregations