use of edu.uci.ics.textdb.api.field.IField in project textdb by TextDB.
the class ExcelSinkTest method attributeTypeTest.
@Test
public // writing 10000 tuples
void attributeTypeTest() 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 inputOperator = Mockito.mock(IOperator.class);
Mockito.when(inputOperator.getOutputSchema()).thenReturn(new Schema(schemaAttributes));
OngoingStubbing<Tuple> stubbing = Mockito.when(inputOperator.getNextTuple());
for (Tuple t : tupleList) {
stubbing = stubbing.thenReturn(t);
}
stubbing = stubbing.thenReturn(null);
// excel writing test
excelSink = new ExcelSink(new ExcelSinkPredicate());
excelSink.setInputOperator(inputOperator);
excelSink.open();
excelSink.collectAllTuples();
excelSink.close();
Files.deleteIfExists(Paths.get(excelSink.getFilePath()));
}
use of edu.uci.ics.textdb.api.field.IField in project textdb by TextDB.
the class KeywordSubstringTest method testSubstringWithStopwordQuery.
/**
* Verifies: Verifies List<ITuple> returned multiple results by Substring
* Matcher on query with spaces on both left side and right side.
*
* @throws Exception
*/
@Test
public void testSubstringWithStopwordQuery() throws Exception {
// Prepare Query
String query = "is";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstants.FIRST_NAME);
attributeNames.add(TestConstants.LAST_NAME);
attributeNames.add(TestConstants.DESCRIPTION);
// Prepare expected result list
List<Span> list = new ArrayList<>();
Span span1 = new Span("description", 12, 14, "is", "is");
Span span2 = new Span("description", 37, 39, "is", "is");
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("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<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
// Perform Query
List<Tuple> resultList = KeywordTestHelper.getScanSourceResults(PEOPLE_TABLE, query, attributeNames, substring, Integer.MAX_VALUE, 0);
// Perform Check
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
use of edu.uci.ics.textdb.api.field.IField in project textdb by TextDB.
the class KeywordSubstringTest method testCombinedSpanInMultipleFieldsQuery.
/**
* Verifies: Verifies List<ITuple> returned multiple results by Substring
* Matcher on query with spaces on both left side and right side.
*
* @throws Exception
*/
@Test
public void testCombinedSpanInMultipleFieldsQuery() throws Exception {
// Prepare Query
String query = " lin ";
ArrayList<String> attributeNames = new ArrayList<>();
attributeNames.add(TestConstants.FIRST_NAME);
attributeNames.add(TestConstants.LAST_NAME);
attributeNames.add(TestConstants.DESCRIPTION);
// Prepare expected result list
List<Span> list = new ArrayList<>();
Span span1 = new Span("description", 24, 29, " lin ", " lin ");
list.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] = new Attribute(RESULTS, AttributeType.LIST);
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<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
// Perform Query
List<Tuple> resultList = KeywordTestHelper.getScanSourceResults(PEOPLE_TABLE, query, attributeNames, substring, Integer.MAX_VALUE, 0);
// Perform Check
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
use of edu.uci.ics.textdb.api.field.IField in project textdb by TextDB.
the class RegexMatcherTest method testRegexText1.
@Test
public void testRegexText1() throws Exception {
String query = "test(er|ing|ed|s)?";
List<Tuple> exactResults = RegexMatcherTestHelper.getQueryResults(TEXT_TABLE, query, Arrays.asList(RegexTestConstantsText.CONTENT));
List<Tuple> expectedResults = new ArrayList<Tuple>();
// expected to match "test" & testing"
List<Tuple> data = RegexTestConstantsText.getSampleTextTuples();
Schema spanSchema = Utils.addAttributeToSchema(RegexTestConstantsText.SCHEMA_TEXT, new Attribute(RESULTS, AttributeType.LIST));
List<Span> spans = new ArrayList<Span>();
spans.add(new Span(RegexTestConstantsText.CONTENT, 5, 9, query, "test"));
spans.add(new Span(RegexTestConstantsText.CONTENT, 21, 28, query, "testing"));
IField spanField = new ListField<Span>(new ArrayList<Span>(spans));
List<IField> fields = new ArrayList<IField>(data.get(0).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
// expected to match "tests"
spans.clear();
spans.add(new Span(RegexTestConstantsText.CONTENT, 87, 92, query, "tests"));
spanField = new ListField<Span>(new ArrayList<Span>(spans));
fields = new ArrayList<IField>(data.get(2).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
// expected to match "tested"
spans.clear();
spans.add(new Span(RegexTestConstantsText.CONTENT, 43, 49, query, "tested"));
spanField = new ListField<Span>(new ArrayList<Span>(spans));
fields = new ArrayList<IField>(data.get(3).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
Assert.assertTrue(TestUtils.equals(expectedResults, exactResults));
}
use of edu.uci.ics.textdb.api.field.IField in project textdb by TextDB.
the class RegexMatcherTest method testRegexText3.
@Test
public void testRegexText3() throws Exception {
String query = "([a-zA-Z])+o[a-z]a[a-z]o";
List<Tuple> exactResults = RegexMatcherTestHelper.getQueryResults(TEXT_TABLE, query, Arrays.asList(RegexTestConstantsText.CONTENT));
List<Tuple> expectedResults = new ArrayList<Tuple>();
// expected to match "Tomato" & "tomato"
List<Tuple> data = RegexTestConstantsText.getSampleTextTuples();
Schema spanSchema = Utils.addAttributeToSchema(RegexTestConstantsText.SCHEMA_TEXT, new Attribute(RESULTS, AttributeType.LIST));
List<Span> spans = new ArrayList<Span>();
spans.add(new Span(RegexTestConstantsText.CONTENT, 0, 6, query, "Tomato"));
spans.add(new Span(RegexTestConstantsText.CONTENT, 94, 100, query, "tomato"));
IField spanField = new ListField<Span>(new ArrayList<Span>(spans));
List<IField> fields = new ArrayList<IField>(data.get(7).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
// expected to match "Potato"
spans.clear();
spans.add(new Span(RegexTestConstantsText.CONTENT, 0, 6, query, "Potato"));
spanField = new ListField<Span>(new ArrayList<Span>(spans));
fields = new ArrayList<IField>(data.get(8).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
// expected to match "avocado"
spans.clear();
spans.add(new Span(RegexTestConstantsText.CONTENT, 53, 60, query, "avocado"));
spanField = new ListField<Span>(new ArrayList<Span>(spans));
fields = new ArrayList<IField>(data.get(9).getFields());
fields.add(spanField);
expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
Assert.assertTrue(TestUtils.equals(expectedResults, exactResults));
}
Aggregations