Search in sources :

Example 51 with DoubleField

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

the class DictionaryMatcherTest method testMatchingWithLimitOffset.

@Test
public void testMatchingWithLimitOffset() throws Exception {
    ArrayList<String> word = new ArrayList<String>(Arrays.asList("angry"));
    Dictionary dictionary = new Dictionary(word);
    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;
    Span span1 = new Span("description", 5, 10, "angry", "Angry");
    Span span2 = new Span("description", 6, 11, "angry", "Angry");
    Span span3 = new Span("description", 40, 45, "angry", "Angry");
    Span span4 = new Span("description", 6, 11, "angry", "angry");
    List<Span> list1 = new ArrayList<>();
    list1.add(span1);
    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<>(list1) };
    List<Span> list2 = new ArrayList<>();
    list2.add(span2);
    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<>(list2) };
    List<Span> list3 = new ArrayList<>();
    list3.add(span3);
    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<>(list3) };
    List<Span> list4 = new ArrayList<>();
    list4.add(span4);
    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<>(list4) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    Tuple tuple3 = new Tuple(new Schema(schemaAttributes), fields3);
    Tuple tuple4 = new Tuple(new Schema(schemaAttributes), fields4);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
    List<Tuple> expectedList = new ArrayList<>();
    List<Tuple> resultList = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.PHRASE_INDEXBASED, 1, 3);
    expectedList.add(tuple1);
    expectedList.add(tuple2);
    expectedList.add(tuple3);
    expectedList.add(tuple4);
    Assert.assertEquals(expectedList.size(), 4);
    Assert.assertEquals(resultList.size(), 1);
    Assert.assertTrue(TestUtils.containsAll(expectedList, resultList));
}
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 52 with DoubleField

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

the class FuzzyTokenMatcherTest method TestFuzzyTokenMatcher2.

@Test
public void TestFuzzyTokenMatcher2() throws Exception {
    String query = "Twelve Angry Men";
    // The ratio of tokens that need to be matched
    double threshold = 0.5;
    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 53 with DoubleField

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

the class ExcelSinkTest method writeSampleExcelFile.

/**
 * Create two tuples, write into a excel file. Need to manually delete the generated file.
 * @throws ParseException
 */
@Test
public void writeSampleExcelFile() throws Exception {
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstants.FIRST_NAME);
    attributeNames.add(TestConstants.LAST_NAME);
    attributeNames.add(TestConstants.DESCRIPTION);
    // Prepare the expected result list
    List<Span> list = new ArrayList<>();
    Span span1 = new Span("firstName", 0, 5, "bruce", "bruce");
    Span span2 = new Span("lastnName", 0, 5, "jacki", "jacki");
    list.add(span1);
    list.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] = SchemaConstants.SPAN_LIST_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<>(list) };
    IField[] fields2 = { new StringField("test"), new StringField("jackie chan"), new IntegerField(0), new DoubleField(6.0), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("09-18-1994")), new TextField("Angry Bird"), new ListField<>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    IOperator inputOperator = Mockito.mock(IOperator.class);
    Mockito.when(inputOperator.getOutputSchema()).thenReturn(new Schema(schemaAttributes)).thenReturn(null);
    Mockito.when(inputOperator.getNextTuple()).thenReturn(tuple1).thenReturn(tuple2).thenReturn(null);
    excelSink = new ExcelSink(new ExcelSinkPredicate());
    excelSink.setInputOperator(inputOperator);
    excelSink.open();
    excelSink.collectAllTuples();
    excelSink.close();
    Files.deleteIfExists(excelSink.getFilePath());
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) IOperator(edu.uci.ics.texera.api.dataflow.IOperator) 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 54 with DoubleField

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

the class MysqlSinkTest method testTupleListInsertion.

/**
 * Create 10000 tuples with all regular fields
 * Insert into mysql database
 */
public void testTupleListInsertion() throws Exception {
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstants.FIRST_NAME);
    attributeNames.add(TestConstants.LAST_NAME);
    attributeNames.add(TestConstants.AGE);
    attributeNames.add(TestConstants.HEIGHT);
    attributeNames.add(TestConstants.DATE_OF_BIRTH);
    attributeNames.add(TestConstants.DESCRIPTION);
    // Prepare Schema
    Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length];
    for (int count = 0; count < schemaAttributes.length; count++) {
        schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
    }
    // Prepare 10000 tuples as a tupleList
    int testSize = 10000;
    Random rand = new Random();
    List<Tuple> tupleList = new ArrayList<Tuple>();
    for (int i = 0; i < testSize; i++) {
        IField[] fields = { new StringField(getRandomString()), new StringField(getRandomString()), new IntegerField(rand.nextInt()), new DoubleField(rand.nextDouble() * rand.nextInt()), new DateField(getRandomDate()), new TextField(getRandomString()) };
        tupleList.add(new Tuple(new Schema(schemaAttributes), fields));
    }
    assert (tupleList.size() == testSize);
    IOperator localInputOperator = Mockito.mock(IOperator.class);
    Mockito.when(localInputOperator.getOutputSchema()).thenReturn(new Schema(schemaAttributes));
    OngoingStubbing<Tuple> stubbing = Mockito.when(localInputOperator.getNextTuple());
    for (Tuple t : tupleList) {
        stubbing = stubbing.thenReturn(t);
    }
    stubbing = stubbing.thenReturn(null);
    mysqlSink.setInputOperator(localInputOperator);
    mysqlSink.open();
    mysqlSink.processTuples();
    mysqlSink.close();
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) IOperator(edu.uci.ics.texera.api.dataflow.IOperator) 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) Random(java.util.Random) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) DoubleField(edu.uci.ics.texera.api.field.DoubleField)

Example 55 with DoubleField

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

the class KeywordConjunctionTest method testWordInMultipleFieldsQueryChinese.

/**
 * Verifies: data source has multiple attributes, and an entity can appear
 * in all the fields and multiple times.
 * Test for Chinese data.
 *
 * @throws Exception
 */
@Test
public void testWordInMultipleFieldsQueryChinese() throws Exception {
    // Prepare the query
    String query = "建筑";
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstantsChinese.FIRST_NAME);
    attributeNames.add(TestConstantsChinese.LAST_NAME);
    attributeNames.add(TestConstantsChinese.DESCRIPTION);
    // Prepare the expected result list
    List<Span> list = new ArrayList<>();
    Span span1 = new Span("lastName", 0, 2, "建筑", "建筑");
    Span span2 = new Span("description", 3, 5, "建筑", "建筑", 2);
    list.add(span1);
    list.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] = new Attribute(RESULTS, AttributeType.LIST);
    IField[] fields1 = { new StringField("宋江"), new StringField("建筑"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("伟大的建筑是历史的坐标,具有传承的价值。"), new ListField<>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    List<Tuple> expectedResultList = new ArrayList<>();
    expectedResultList.add(tuple1);
    // Perform the query
    List<Tuple> resultList = KeywordTestHelper.getQueryResults(CHINESE_TABLE, query, attributeNames, conjunction, Integer.MAX_VALUE, 0);
    // check the results
    boolean contains = TestUtils.equals(expectedResultList, resultList);
    Assert.assertTrue(contains);
}
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) 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)

Aggregations

DoubleField (edu.uci.ics.texera.api.field.DoubleField)64 IField (edu.uci.ics.texera.api.field.IField)63 IntegerField (edu.uci.ics.texera.api.field.IntegerField)63 StringField (edu.uci.ics.texera.api.field.StringField)63 TextField (edu.uci.ics.texera.api.field.TextField)63 Tuple (edu.uci.ics.texera.api.tuple.Tuple)59 DateField (edu.uci.ics.texera.api.field.DateField)58 Schema (edu.uci.ics.texera.api.schema.Schema)58 ArrayList (java.util.ArrayList)58 SimpleDateFormat (java.text.SimpleDateFormat)56 Test (org.junit.Test)56 Span (edu.uci.ics.texera.api.span.Span)55 Attribute (edu.uci.ics.texera.api.schema.Attribute)51 Dictionary (edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary)29 IOperator (edu.uci.ics.texera.api.dataflow.IOperator)4 ParseException (java.text.ParseException)3 Random (java.util.Random)2 JsonNode (com.fasterxml.jackson.databind.JsonNode)1 DateTimeField (edu.uci.ics.texera.api.field.DateTimeField)1 ListField (edu.uci.ics.texera.api.field.ListField)1