use of edu.uci.ics.textdb.api.field.StringField 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 = Utils.addAttributeToSchema(TestConstantsChinese.SCHEMA_PEOPLE, 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(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.textdb.api.field.StringField 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>();
List<Span> list2 = 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);
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) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
IField[] fields2 = { 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>(list2) };
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.textdb.api.field.StringField 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.textdb.api.field.StringField in project textdb by TextDB.
the class JoinDistanceTest method testBothTheSpansAreSame.
// This case tests for the scenario when the spans to be joined are the same, i.e. both the keywords
// are same.
// e.g.
// [<11, 18>]
// [<11, 18>]
// threshold = 20 (can be any non-negative number)
// [ ]
// [ ]
// Test result: Join should return same span and key and the value in span
// should be the same.
// [<11, 18>]
@Test
public void testBothTheSpansAreSame() throws Exception {
JoinTestHelper.insertToTable(BOOK_TABLE, JoinTestConstants.bookGroup1.get(0));
KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 20), Integer.MAX_VALUE, 0);
Schema resultSchema = Utils.createSpanSchema(JoinTestConstants.BOOK_SCHEMA);
List<Span> spanList = new ArrayList<>();
Span span1 = new Span(JoinTestConstants.REVIEW, 11, 18, "special_special", "special");
spanList.add(span1);
IField[] book1 = { new IntegerField(52), new StringField("Mary Roach"), new StringField("Grunt: The Curious Science of Humans at War"), new IntegerField(288), new TextField("It takes a special kind " + "of writer to make topics ranging from death to our " + "gastrointestinal tract interesting (sometimes " + "hilariously so), and pop science writer Mary Roach is " + "always up to the task."), new ListField<>(spanList) };
Tuple expectedTuple = new Tuple(resultSchema, book1);
List<Tuple> expectedResult = new ArrayList<>();
expectedResult.add(expectedTuple);
Assert.assertEquals(1, resultList.size());
Assert.assertTrue(TestUtils.equals(expectedResult, resultList));
}
use of edu.uci.ics.textdb.api.field.StringField in project textdb by TextDB.
the class JoinDistanceTest method testForLimitWhenLimitIsLesserThanActualNumberOfResultsAndHasOffset.
/*
* This case tests for the scenario when limit is some integer greater than
* 0 and less than the actual number of results and offset is some integer
* greater than 0 and less than actual number of results and join is
* performed.
* Test result: A list of tuples with number of tuples equal to limit
* starting from the set offset.
*/
@Test
public void testForLimitWhenLimitIsLesserThanActualNumberOfResultsAndHasOffset() throws Exception {
List<Tuple> tuples = JoinTestConstants.bookGroup1.subList(1, 5);
JoinTestHelper.insertToTable(BOOK_TABLE, tuples);
KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "typical", conjunction);
KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "actually", conjunction);
List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 90), 1, 2);
Schema resultSchema = Utils.createSpanSchema(JoinTestConstants.BOOK_SCHEMA);
List<Span> spanList = new ArrayList<>();
Span span1 = new Span(JoinTestConstants.REVIEW, 28, 119, "typical_actually", "typical review. " + "This is a test. A book review test. " + "A test to test queries without actually");
spanList.add(span1);
Span span2 = new Span(JoinTestConstants.REVIEW, 186, 234, "typical_actually", "actually a review " + "even if it is not your typical");
spanList.add(span2);
IField[] book1 = { new IntegerField(54), new StringField("Andria Williams"), new StringField("The Longest Night: A Novel"), new IntegerField(400), new TextField("Review of a Book. This is a typical " + "review. This is a test. A book review " + "test. A test to test queries without " + "actually using actual review. From " + "here onwards, we can pretend this to " + "be actually a review even if it is not " + "your typical book review."), new ListField<>(spanList) };
Tuple expectedTuple1 = new Tuple(resultSchema, book1);
List<Tuple> expectedResult = new ArrayList<>(1);
expectedResult.add(expectedTuple1);
Assert.assertEquals(1, resultList.size());
Assert.assertTrue(TestUtils.equals(expectedResult, resultList));
}
Aggregations