Search in sources :

Example 41 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.

the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingPhraseChinese.

/**
 * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
 * queries in Text Field using PHRASE OPERATOR in Chinese.
 */
@Test
public void testSingleWordQueryInTextFieldUsingPhraseChinese() 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");
    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.PHRASE_INDEXBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 42 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.

the class FuzzyTokenMatcherTest method TestFuzzyTokenMatcherWithLargeTokens.

@Test
public void TestFuzzyTokenMatcherWithLargeTokens() throws Exception {
    String query = "Twelve Angry Men Came Cafe Have Coffee Eat Chocolate Burger Fries SandWidch Cool Food Drinks American drama film elements film noir adapted teleplay same name Reginald Rose Written Rose directed  Sidney Lumet trial film tells story jury made deliberate guilt acquittal defendant basis reasonable doubt United States verdict most criminal ";
    double threshold = 0.02;
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstants.DESCRIPTION);
    Schema schema = new Schema.Builder().add(TestConstants.SCHEMA_PEOPLE).add(RESULTS_ATTR).build();
    List<Span> spanList1 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 5, 10, "angry", "Angry", 1));
    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>(spanList1) };
    List<Span> spanList2 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 6, 11, "angry", "Angry", 1));
    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<Span>(spanList2) };
    List<Span> spanList3 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 40, 45, "angry", "Angry", 8));
    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<Span>(spanList3) };
    List<Span> spanList4 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 6, 11, "angry", "angry", 1));
    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<Span>(spanList4) };
    Tuple tuple1 = new Tuple(schema, fields1);
    Tuple tuple2 = new Tuple(schema, fields2);
    Tuple tuple3 = new Tuple(schema, fields3);
    Tuple tuple4 = new Tuple(schema, fields4);
    List<Tuple> expectedResultList = new ArrayList<>();
    expectedResultList.add(tuple1);
    expectedResultList.add(tuple2);
    expectedResultList.add(tuple3);
    expectedResultList.add(tuple4);
    List<Tuple> results = FuzzyTokenMatcherTestHelper.getQueryResults(PEOPLE_TABLE, query, threshold, attributeNames);
    boolean contains = TestUtils.equals(expectedResultList, results);
    Assert.assertTrue(contains);
}
Also used : Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 43 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.

the class WordCountOperator method computeNextMatchingTuple.

@Override
protected Tuple computeNextMatchingTuple() throws TexeraException {
    if (sortedWordCountMap == null) {
        computeWordCount();
    }
    if (wordCountIterator.hasNext()) {
        Entry<String, Integer> entry = wordCountIterator.next();
        List<IField> tupleFieldList = new ArrayList<>();
        // Generate the new UUID.
        tupleFieldList.add(IDField.newRandomID());
        tupleFieldList.add(new StringField(entry.getKey()));
        tupleFieldList.add(new IntegerField(entry.getValue()));
        return new Tuple(outputSchema, tupleFieldList);
    }
    return null;
}
Also used : StringField(edu.uci.ics.texera.api.field.StringField) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Tuple(edu.uci.ics.texera.api.tuple.Tuple)

Example 44 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.

the class AggregatorTest method testMinHeightMaxAgeAggregation.

// TEST 7: Find min in height and max in age column
@Test
public void testMinHeightMaxAgeAggregation() throws Exception {
    Attribute attribute1 = TestConstants.HEIGHT_ATTR;
    String attributeName1 = attribute1.getName();
    AggregationType aggType1 = AggregationType.MIN;
    Attribute attribute2 = TestConstants.AGE_ATTR;
    String attributeName2 = attribute2.getName();
    AggregationType aggType2 = AggregationType.MAX;
    String resultAttributeName1 = AggregatorTestConstants.MIN_HEIGHT_RESULT_ATTR_NAME;
    String resultAttributeName2 = AggregatorTestConstants.MAX_AGE_RESULT_ATTR_NAME;
    AggregationAttributeAndResult aggEntity1 = new AggregationAttributeAndResult(attributeName1, aggType1, resultAttributeName1);
    AggregationAttributeAndResult aggEntity2 = new AggregationAttributeAndResult(attributeName2, aggType2, resultAttributeName2);
    List<AggregationAttributeAndResult> aggEntitiesList = new ArrayList<>();
    aggEntitiesList.add(aggEntity1);
    aggEntitiesList.add(aggEntity2);
    IField[] row1 = { new DoubleField(5.50), new IntegerField(46) };
    Schema schema = new Schema(new Attribute(resultAttributeName1, AttributeType.DOUBLE), new Attribute(resultAttributeName2, AttributeType.INTEGER));
    List<Tuple> expectedResults = new ArrayList<>();
    expectedResults.add(new Tuple(schema, row1));
    List<Tuple> returnedResults = getQueryResults(aggEntitiesList);
    Assert.assertEquals(1, returnedResults.size());
    Assert.assertTrue(TestUtils.equals(expectedResults, returnedResults));
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 45 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField in project textdb by TextDB.

the class EmojiSentimentOperator method getNextTuple.

@Override
public Tuple getNextTuple() throws TexeraException {
    if (cursor == CLOSED) {
        return null;
    }
    Tuple inputTuple = inputOperator.getNextTuple();
    if (inputTuple == null) {
        return null;
    }
    List<IField> outputFields = new ArrayList<>();
    outputFields.addAll(inputTuple.getFields());
    outputFields.add(new IntegerField(computeSentimentScore(inputTuple)));
    return new Tuple(outputSchema, outputFields);
}
Also used : IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Tuple(edu.uci.ics.texera.api.tuple.Tuple)

Aggregations

IntegerField (edu.uci.ics.texera.api.field.IntegerField)98 Tuple (edu.uci.ics.texera.api.tuple.Tuple)90 IField (edu.uci.ics.texera.api.field.IField)88 StringField (edu.uci.ics.texera.api.field.StringField)87 TextField (edu.uci.ics.texera.api.field.TextField)79 ArrayList (java.util.ArrayList)75 Schema (edu.uci.ics.texera.api.schema.Schema)72 Test (org.junit.Test)70 Span (edu.uci.ics.texera.api.span.Span)66 DoubleField (edu.uci.ics.texera.api.field.DoubleField)65 DateField (edu.uci.ics.texera.api.field.DateField)59 SimpleDateFormat (java.text.SimpleDateFormat)57 Attribute (edu.uci.ics.texera.api.schema.Attribute)56 Dictionary (edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary)29 JoinDistancePredicate (edu.uci.ics.texera.dataflow.join.JoinDistancePredicate)9 KeywordMatcherSourceOperator (edu.uci.ics.texera.dataflow.keywordmatcher.KeywordMatcherSourceOperator)9 JsonNode (com.fasterxml.jackson.databind.JsonNode)5 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)4 IOperator (edu.uci.ics.texera.api.dataflow.IOperator)4 DateTimeField (edu.uci.ics.texera.api.field.DateTimeField)3