Search in sources :

Example 31 with DataWriter

use of edu.uci.ics.texera.storage.DataWriter in project textdb by TextDB.

the class NlpEntityTest method getNextTupleTest10.

@Test
public void getNextTupleTest10() throws Exception {
    List<Tuple> data = NlpEntityTestConstants.getOneSentenceTestTuple();
    DataWriter oneSentenceDataWriter = RelationManager.getInstance().getTableDataWriter(ONE_SENTENCE_TABLE);
    oneSentenceDataWriter.open();
    for (Tuple tuple : data) {
        oneSentenceDataWriter.insertTuple(tuple);
    }
    oneSentenceDataWriter.close();
    String attribute1 = NlpEntityTestConstants.SENTENCE_ONE;
    List<String> attributeNames = Arrays.asList(attribute1);
    List<Tuple> returnedResults = getQueryResults(ONE_SENTENCE_TABLE, attributeNames, NlpEntityType.NE_ALL);
    List<Tuple> expectedResults = NlpEntityTestConstants.getTest10ResultTuples();
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Tuple(edu.uci.ics.texera.api.tuple.Tuple) DataWriter(edu.uci.ics.texera.storage.DataWriter) Test(org.junit.Test)

Example 32 with DataWriter

use of edu.uci.ics.texera.storage.DataWriter in project textdb by TextDB.

the class NlpEntityTest method getNextTupleTest11.

@Test
public void getNextTupleTest11() throws Exception {
    List<Tuple> data = NlpEntityTestConstants.getTwoSentenceTestTuple();
    DataWriter twoSentenceDataWriter = RelationManager.getInstance().getTableDataWriter(TWO_SENTENCE_TABLE);
    twoSentenceDataWriter.open();
    for (Tuple tuple : data) {
        twoSentenceDataWriter.insertTuple(tuple);
    }
    twoSentenceDataWriter.close();
    String attribute1 = NlpEntityTestConstants.SENTENCE_ONE;
    String attribute2 = NlpEntityTestConstants.SENTENCE_TWO;
    List<String> attributeNames = Arrays.asList(attribute1, attribute2);
    List<Tuple> returnedResults = getQueryResults(TWO_SENTENCE_TABLE, attributeNames, NlpEntityType.NE_ALL);
    List<Tuple> expectedResults = NlpEntityTestConstants.getTest11ResultTuple();
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Tuple(edu.uci.ics.texera.api.tuple.Tuple) DataWriter(edu.uci.ics.texera.storage.DataWriter) Test(org.junit.Test)

Example 33 with DataWriter

use of edu.uci.ics.texera.storage.DataWriter in project textdb by TextDB.

the class NlpEntityTest method getNextTupleTest3.

/**
 * Scenario 3: Test getNextTuple with more than one span in the return list
 * and with different recognized classes. Text: Microsoft, Google and
 * Facebook are organizations and Donald Trump and Barack Obama are persons.
 * Search for all NE_ALL entity types
 */
@Test
public void getNextTupleTest3() throws Exception {
    List<Tuple> data = NlpEntityTestConstants.getTest3Tuple();
    DataWriter oneSentenceDataWriter = RelationManager.getInstance().getTableDataWriter(ONE_SENTENCE_TABLE);
    oneSentenceDataWriter.open();
    for (Tuple tuple : data) {
        oneSentenceDataWriter.insertTuple(tuple);
    }
    oneSentenceDataWriter.close();
    String attribute1 = NlpEntityTestConstants.SENTENCE_ONE;
    List<String> attributeNames = new ArrayList<>();
    attributeNames.add(attribute1);
    List<Tuple> returnedResults = getQueryResults(ONE_SENTENCE_TABLE, attributeNames, NlpEntityType.NE_ALL);
    List<Tuple> expectedResults = NlpEntityTestConstants.getTest3ResultTuples();
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : ArrayList(java.util.ArrayList) Tuple(edu.uci.ics.texera.api.tuple.Tuple) DataWriter(edu.uci.ics.texera.storage.DataWriter) Test(org.junit.Test)

Example 34 with DataWriter

use of edu.uci.ics.texera.storage.DataWriter in project textdb by TextDB.

the class NlpEntityTest method getNextTupleTest6.

/**
 * Scenario 6:Test getNextTuple using two fields:
 * <p>
 * Sentence1: Microsoft, Google and Facebook are organizations. Sentence2:
 * Donald Trump and Barack Obama are persons.
 * <p>
 * Only search for Organization for all fields.
 */
@Test
public void getNextTupleTest6() throws Exception {
    List<Tuple> data = NlpEntityTestConstants.getTest4Tuple();
    DataWriter twoSentenceDataWriter = RelationManager.getInstance().getTableDataWriter(TWO_SENTENCE_TABLE);
    twoSentenceDataWriter.open();
    for (Tuple tuple : data) {
        twoSentenceDataWriter.insertTuple(tuple);
    }
    twoSentenceDataWriter.close();
    String attribute1 = NlpEntityTestConstants.SENTENCE_ONE;
    String attribute2 = NlpEntityTestConstants.SENTENCE_TWO;
    List<String> attributeNames = new ArrayList<>();
    attributeNames.add(attribute1);
    attributeNames.add(attribute2);
    List<Tuple> returnedResults = getQueryResults(TWO_SENTENCE_TABLE, attributeNames, NlpEntityType.ORGANIZATION);
    List<Tuple> expectedResults = NlpEntityTestConstants.getTest6ResultTuples();
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : ArrayList(java.util.ArrayList) Tuple(edu.uci.ics.texera.api.tuple.Tuple) DataWriter(edu.uci.ics.texera.storage.DataWriter) Test(org.junit.Test)

Example 35 with DataWriter

use of edu.uci.ics.texera.storage.DataWriter in project textdb by TextDB.

the class ComparableMatcherTest method setUp.

@BeforeClass
public static void setUp() throws TexeraException {
    RelationManager relationManager = RelationManager.getInstance();
    // create the people table and write tuples
    relationManager.createTable(PEOPLE_TABLE, TestUtils.getDefaultTestIndex().resolve(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 2 and write tuples
    relationManager.createTable(PEOPLE_TABLE_2, TestUtils.getDefaultTestIndex().resolve(PEOPLE_TABLE_2), TestConstantsRegexSplit.SCHEMA_PEOPLE, LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter people2DataWriter = relationManager.getTableDataWriter(PEOPLE_TABLE_2);
    people2DataWriter.open();
    for (Tuple tuple : TestConstantsRegexSplit.constructSamplePeopleTuples()) {
        people2DataWriter.insertTuple(tuple);
    }
    people2DataWriter.close();
}
Also used : Tuple(edu.uci.ics.texera.api.tuple.Tuple) RelationManager(edu.uci.ics.texera.storage.RelationManager) DataWriter(edu.uci.ics.texera.storage.DataWriter) BeforeClass(org.junit.BeforeClass)

Aggregations

DataWriter (edu.uci.ics.texera.storage.DataWriter)37 Tuple (edu.uci.ics.texera.api.tuple.Tuple)33 RelationManager (edu.uci.ics.texera.storage.RelationManager)19 Test (org.junit.Test)11 ArrayList (java.util.ArrayList)10 BeforeClass (org.junit.BeforeClass)8 StorageException (edu.uci.ics.texera.api.exception.StorageException)3 IDField (edu.uci.ics.texera.api.field.IDField)3 StringField (edu.uci.ics.texera.api.field.StringField)3 IOException (java.io.IOException)3 JsonNode (com.fasterxml.jackson.databind.JsonNode)2 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)2 Term (org.apache.lucene.index.Term)2 TermQuery (org.apache.lucene.search.TermQuery)2 TexeraException (edu.uci.ics.texera.api.exception.TexeraException)1 IField (edu.uci.ics.texera.api.field.IField)1 TupleSink (edu.uci.ics.texera.dataflow.sink.tuple.TupleSink)1 TupleSinkPredicate (edu.uci.ics.texera.dataflow.sink.tuple.TupleSinkPredicate)1 TwitterJsonConverter (edu.uci.ics.texera.dataflow.twitter.TwitterJsonConverter)1 TwitterJsonConverterPredicate (edu.uci.ics.texera.dataflow.twitter.TwitterJsonConverterPredicate)1