use of edu.uci.ics.texera.api.field.StringField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingPhraseChinese.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and multiple word
* queries in String Field using PHRASE_INDEXBASED in Chinese.
*/
@Test
public void testSingleWordQueryInStringFieldUsingPhraseChinese() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("长孙", "无忌"));
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.PHRASE_INDEXBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.StringField in project textdb by TextDB.
the class DictionaryMatcherTest method testWordInMultipleFieldsQueryUsingScan.
/**
* Scenario S-11:verifies: data source has multiple attributes, and an
* entity can appear in all the fields and multiple times using SUBSTRING_SCANBASE
* OPERATOR.
*/
@Test
public void testWordInMultipleFieldsQueryUsingScan() throws Exception {
ArrayList<String> names = new ArrayList<String>(Arrays.asList("lin clooney"));
Dictionary dictionary = new Dictionary(names);
// create a data tuple first
List<Span> list = new ArrayList<Span>();
Span span1 = new Span("lastName", 0, 11, "lin clooney", "lin clooney");
Span span2 = new Span("description", 0, 11, "lin clooney", "Lin Clooney");
Span span3 = new Span("description", 25, 36, "lin clooney", "lin clooney");
list.add(span1);
list.add(span2);
list.add(span3);
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.SUBSTRING_SCANBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.StringField in project textdb by TextDB.
the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingPhrase.
/**
* Scenario: verifies GetNextTuple of DictionaryMatcher and multiple word
* queries in String Field using PHRASEOPERATOR
*/
@Test
public void testSingleWordQueryInStringFieldUsingPhrase() 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.PHRASE_INDEXBASED);
boolean contains = TestUtils.equals(expectedResults, returnedResults);
Assert.assertTrue(contains);
}
use of edu.uci.ics.texera.api.field.StringField in project textdb by TextDB.
the class JoinDistanceTest method testSpansOverlapAndWithinThreshold.
/*
* This case tests for the spans to be joined have some overlap and both
* |(span 1 spanStartIndex) - (span 2 spanStartIndex)|,
* |(span 1 spanEndIndex) - (span 2 spanEndIndex)| are within threshold.
*
* e.g.
* [<75, 97>]
* [<92, 109>]
* threshold = 20 (within threshold)
* result: [<75, 109>]
*
* Test result: The list contains a tuple with all the fields and a span
* list consisting of the joined span. The joined span is made up of the
* field name, start and stop index (computed as <min(span1 spanStartIndex,
* span2 spanStartIndex), max(span1 spanEndIndex, span2 spanEndIndex)>)
* key (combination of span1 key and span2 key) and value (combination of
* span1 value and span2 value).
*/
@Test
public void testSpansOverlapAndWithinThreshold() throws Exception {
JoinTestHelper.insertToTable(BOOK_TABLE, JoinTestConstants.bookGroup1.get(0));
KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "gastrointestinal tract", phrase);
KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "tract interesting", phrase);
List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 20), Integer.MAX_VALUE, 0);
Schema resultSchema = new Schema.Builder().add(JoinTestConstants.BOOK_SCHEMA).add(SchemaConstants.SPAN_LIST_ATTRIBUTE).build();
List<Span> spanList = new ArrayList<>();
Span span1 = new Span(JoinTestConstants.REVIEW, 75, 109, "gastrointestinal tract_" + "tract interesting", "gastrointestinal " + "tract interesting");
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.texera.api.field.StringField in project textdb by TextDB.
the class JoinDistanceTest method testForLimitWhenLimitIsLesserThanActualNumberOfResults.
// ---------------------<Limit and offset test cases.>---------------------
/*
* 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 0 and join
* is performed.
* Test result: A list of tuples with number of tuples equal to limit.
*/
@Test
public void testForLimitWhenLimitIsLesserThanActualNumberOfResults() 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), 3, 0);
Schema resultSchema = new Schema.Builder().add(JoinTestConstants.BOOK_SCHEMA).add(SchemaConstants.SPAN_LIST_ATTRIBUTE).build();
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(51), new StringField("author unknown"), new StringField("typical"), new IntegerField(300), 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) };
IField[] book2 = { new IntegerField(53), new StringField("Noah Hawley"), new StringField("Before the Fall"), 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) };
IField[] book3 = { 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) };
IField[] book4 = { new IntegerField(55), new StringField("Matti Friedman"), new StringField("Pumpkinflowers: A Soldier's " + "Story"), new IntegerField(256), 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);
Tuple expectedTuple2 = new Tuple(resultSchema, book2);
Tuple expectedTuple3 = new Tuple(resultSchema, book3);
Tuple expectedTuple4 = new Tuple(resultSchema, book4);
List<Tuple> expectedResult = new ArrayList<>(3);
expectedResult.add(expectedTuple1);
expectedResult.add(expectedTuple2);
expectedResult.add(expectedTuple3);
expectedResult.add(expectedTuple4);
Assert.assertEquals(3, resultList.size());
Assert.assertTrue(TestUtils.containsAll(expectedResult, resultList));
}
Aggregations