Search in sources :

Example 71 with IntegerField

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

the class DictionaryMatcherTest method testMultipleWordsQueryUsingPhrase.

/**
 * Scenario S-10:verifies ITuple returned by DictionaryMatcher and multiple
 * word queries using PHRASE OPERATOR
 */
@Test
public void testMultipleWordsQueryUsingPhrase() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("george lin lin"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("firstName", 0, 14, "george lin lin", "george lin lin");
    list.add(span);
    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.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 72 with IntegerField

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

the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingScanChinese.

/**
 * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
 * queries in String Field using SUBSTRING_SCANBASED
 * Test in Chinese.
 */
@Test
public void testSingleWordQueryInStringFieldUsingScanChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("孔明"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("firstName", 0, 2, "孔明", "孔明");
    list.add(span);
    Schema resultSchema = new Schema.Builder().add(TestConstantsChinese.SCHEMA_PEOPLE).add(RESULTS_ATTRIBUTE).build();
    IField[] fields1 = { 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(resultSchema, fields1);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.SUBSTRING_SCANBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) 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 73 with IntegerField

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

the class DictionaryMatcherTest method testMultipleWordsQueryUsingKeyword.

/**
 * Scenario S-9:verifies ITuple returned by DictionaryMatcher and multiple
 * word queries using KEYWORD OPERATOR
 */
@Test
public void testMultipleWordsQueryUsingKeyword() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("george lin lin"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("firstName", 0, 14, "george lin lin", "george lin lin");
    list.add(span);
    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.CONJUNCTION_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 74 with IntegerField

use of edu.uci.ics.texera.api.field.IntegerField 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 75 with IntegerField

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

the class DictionaryMatcherTest method testMultipleWordQueryInTextFieldUsingScan1.

/**
 * Testcases for scan-based DictionaryMatcher, use getScanSourceResults method only.
 * @throws Exception
 */
@Test
public void testMultipleWordQueryInTextFieldUsingScan1() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("tall", "fair"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    List<Span> list1 = new ArrayList<Span>();
    Span span = new Span("description", 0, 4, "tall", "Tall");
    Span span1 = new Span("description", 5, 9, "fair", "Fair");
    list.add(span);
    list1.add(span);
    list1.add(span1);
    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>(list) };
    IField[] fields2 = { new StringField("christian john wayne"), new StringField("rock bale"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Tall Fair"), new ListField<Span>(list1) };
    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(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);
}
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)

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