Search in sources :

Example 66 with Tuple

use of edu.uci.ics.textdb.api.tuple.Tuple 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));
}
Also used : Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) JoinDistancePredicate(edu.uci.ics.textdb.exp.join.JoinDistancePredicate) Span(edu.uci.ics.textdb.api.span.Span) KeywordMatcherSourceOperator(edu.uci.ics.textdb.exp.keywordmatcher.KeywordMatcherSourceOperator) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Example 67 with Tuple

use of edu.uci.ics.textdb.api.tuple.Tuple 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));
}
Also used : Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) JoinDistancePredicate(edu.uci.ics.textdb.exp.join.JoinDistancePredicate) Span(edu.uci.ics.textdb.api.span.Span) KeywordMatcherSourceOperator(edu.uci.ics.textdb.exp.keywordmatcher.KeywordMatcherSourceOperator) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Example 68 with Tuple

use of edu.uci.ics.textdb.api.tuple.Tuple in project textdb by TextDB.

the class JoinTestHelper method insertToTable.

public static void insertToTable(String tableName, List<Tuple> tuples) throws StorageException {
    RelationManager relationManager = RelationManager.getRelationManager();
    DataWriter outerDataWriter = relationManager.getTableDataWriter(tableName);
    outerDataWriter.open();
    for (Tuple tuple : tuples) {
        outerDataWriter.insertTuple(tuple);
    }
    outerDataWriter.close();
}
Also used : Tuple(edu.uci.ics.textdb.api.tuple.Tuple) RelationManager(edu.uci.ics.textdb.storage.RelationManager) DataWriter(edu.uci.ics.textdb.storage.DataWriter)

Example 69 with Tuple

use of edu.uci.ics.textdb.api.tuple.Tuple 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>();
    List<Span> list2 = 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);
    list2.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);
    IField[] fields2 = { 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>(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(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);
}
Also used : Dictionary(edu.uci.ics.textdb.exp.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.textdb.api.schema.Attribute) Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) Span(edu.uci.ics.textdb.api.span.Span) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) DateField(edu.uci.ics.textdb.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.textdb.api.field.DoubleField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Example 70 with Tuple

use of edu.uci.ics.textdb.api.tuple.Tuple in project textdb by TextDB.

the class DictionaryMatcherTestHelper method writeTestTables.

public static void writeTestTables() throws TextDBException {
    RelationManager relationManager = RelationManager.getRelationManager();
    // create the people table and write tuples
    relationManager.createTable(PEOPLE_TABLE, "../index/test_tables/" + PEOPLE_TABLE, TestConstants.SCHEMA_PEOPLE, LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter peopleDataWriter = relationManager.getTableDataWriter(PEOPLE_TABLE);
    peopleDataWriter.open();
    for (Tuple tuple : TestConstants.getSamplePeopleTuples()) {
        peopleDataWriter.insertTuple(tuple);
    }
    peopleDataWriter.close();
    // create the people table and write tuples in Chinese
    relationManager.createTable(CHINESE_TABLE, "../index/test_tables/" + CHINESE_TABLE, TestConstantsChinese.SCHEMA_PEOPLE, LuceneAnalyzerConstants.chineseAnalyzerString());
    DataWriter chineseDataWriter = relationManager.getTableDataWriter(CHINESE_TABLE);
    chineseDataWriter.open();
    for (Tuple tuple : TestConstantsChinese.getSamplePeopleTuples()) {
        chineseDataWriter.insertTuple(tuple);
    }
    chineseDataWriter.close();
}
Also used : Tuple(edu.uci.ics.textdb.api.tuple.Tuple) RelationManager(edu.uci.ics.textdb.storage.RelationManager) DataWriter(edu.uci.ics.textdb.storage.DataWriter)

Aggregations

Tuple (edu.uci.ics.textdb.api.tuple.Tuple)234 ArrayList (java.util.ArrayList)144 Test (org.junit.Test)135 IField (edu.uci.ics.textdb.api.field.IField)102 Schema (edu.uci.ics.textdb.api.schema.Schema)95 TextField (edu.uci.ics.textdb.api.field.TextField)92 StringField (edu.uci.ics.textdb.api.field.StringField)85 Attribute (edu.uci.ics.textdb.api.schema.Attribute)84 IntegerField (edu.uci.ics.textdb.api.field.IntegerField)80 Span (edu.uci.ics.textdb.api.span.Span)80 DoubleField (edu.uci.ics.textdb.api.field.DoubleField)64 DateField (edu.uci.ics.textdb.api.field.DateField)61 SimpleDateFormat (java.text.SimpleDateFormat)60 DataWriter (edu.uci.ics.textdb.storage.DataWriter)31 Dictionary (edu.uci.ics.textdb.exp.dictionarymatcher.Dictionary)25 KeywordMatcherSourceOperator (edu.uci.ics.textdb.exp.keywordmatcher.KeywordMatcherSourceOperator)20 RelationManager (edu.uci.ics.textdb.storage.RelationManager)19 JoinDistancePredicate (edu.uci.ics.textdb.exp.join.JoinDistancePredicate)18 ScanBasedSourceOperator (edu.uci.ics.textdb.exp.source.scan.ScanBasedSourceOperator)17 ScanSourcePredicate (edu.uci.ics.textdb.exp.source.scan.ScanSourcePredicate)17