use of edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary in project textdb by TextDB.
the class DictionaryMatcherTest method testMultipleWordsQueryUsingPhrase.
/**
* Scenario S-10:verifies ITuple returned by DictionaryMatcher and multiple
* word queries using PHRASE OPERATOR
*/
@Test
public void testMultipleWordsQueryUsingPhrase() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("george lin lin"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span = new Span("firstName", 0, 14, "george lin lin", "george lin lin");
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("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<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.PHRASE_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 testSingleWordQueryInStringFieldUsingScanChinese.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and single word
* queries in String Field using SUBSTRING_SCANBASED
* Test in Chinese.
*/
@Test
public void testSingleWordQueryInStringFieldUsingScanChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("孔明"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span = new Span("firstName", 0, 2, "孔明", "孔明");
list.add(span);
Schema resultSchema = new Schema.Builder().add(TestConstantsChinese.SCHEMA_PEOPLE).add(RESULTS_ATTRIBUTE).build();
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(resultSchema, fields1);
List<Tuple> expectedResults = new ArrayList<Tuple>();
expectedResults.add(tuple1);
List<String> attributeNames = Arrays.asList(TestConstants.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.dataflow.dictionarymatcher.Dictionary in project textdb by TextDB.
the class DictionaryMatcherTest method testMultipleWordsQueryUsingKeyword.
/**
* Scenario S-9:verifies ITuple returned by DictionaryMatcher and multiple
* word queries using KEYWORD OPERATOR
*/
@Test
public void testMultipleWordsQueryUsingKeyword() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("george lin lin"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span = new Span("firstName", 0, 14, "george lin lin", "george lin lin");
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("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<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.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 testGetNextOfDictionaryItem.
/**
* Scenario S1:verifies GetNextTuple of Dictionary
*
* checking if Dictionary returns all the strings given by the user
*/
@Test
public void testGetNextOfDictionaryItem() throws Exception {
ArrayList<String> expectedStrings = new ArrayList<String>(Arrays.asList("george", "lee", "bruce"));
Dictionary dictionary = new Dictionary(expectedStrings);
String dictionaryItem;
ArrayList<String> returnedStrings = new ArrayList<String>();
while ((dictionaryItem = dictionary.getNextEntry()) != null) {
returnedStrings.add(dictionaryItem);
}
Assert.assertEquals(expectedStrings, returnedStrings);
}
use of edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary in project textdb by TextDB.
the class DictionaryMatcherTest method testMatchingWithLimitOffset.
@Test
public void testMatchingWithLimitOffset() throws Exception {
ArrayList<String> word = new ArrayList<String>(Arrays.asList("angry"));
Dictionary dictionary = new Dictionary(word);
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;
Span span1 = new Span("description", 5, 10, "angry", "Angry");
Span span2 = new Span("description", 6, 11, "angry", "Angry");
Span span3 = new Span("description", 40, 45, "angry", "Angry");
Span span4 = new Span("description", 6, 11, "angry", "angry");
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);
List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
List<Tuple> expectedList = new ArrayList<>();
List<Tuple> resultList = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.PHRASE_INDEXBASED, 1, 3);
expectedList.add(tuple1);
expectedList.add(tuple2);
expectedList.add(tuple3);
expectedList.add(tuple4);
Assert.assertEquals(expectedList.size(), 4);
Assert.assertEquals(resultList.size(), 1);
Assert.assertTrue(TestUtils.containsAll(expectedList, resultList));
}
Aggregations