use of edu.uci.ics.texera.api.field.TextField 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());
}
use of edu.uci.ics.texera.api.field.TextField 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();
}
use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.
the class TwitterFeedOperatorTest method testWithMockClient.
/**
* Mock the TwitterConnector class and the BasicClient class inside it to test the TwitterFeedOperator alone.
* Use the pre-defined queue with a Json formatted tweet to generate a tuple.
* Check if the tuple is well-formatted.
*/
@Test
public void testWithMockClient() throws Exception {
TwitterConnector mockTwitterConnector = mock(TwitterConnector.class);
queue.add(inputStream);
TwitterFeedSourcePredicate predicate = new TwitterFeedSourcePredicate(1, keywordList, "", null, null, null, null, null);
TwitterFeedOperator operator = new TwitterFeedOperator(predicate, mockTwitterConnector);
operator.setTimeout(timeOut);
BasicClient mockClient = mock(BasicClient.class);
when(mockTwitterConnector.getClient()).thenReturn(mockClient);
when(mockTwitterConnector.getMsgQueue()).thenReturn(queue);
TupleSink tupleSink = new TupleSink();
tupleSink.setInputOperator(operator);
tupleSink.open();
List<Tuple> exactResults = tupleSink.collectAllTuples();
tupleSink.close();
JsonNode tweet = new ObjectMapper().readValue(inputStream, JsonNode.class);
Tuple expectedTuple = new Tuple(TwitterUtils.TwitterSchema.TWITTER_SCHEMA, new TextField(TwitterUtils.getText(tweet)), new StringField(TwitterUtils.getMediaLink(tweet)), new StringField(TwitterUtils.getTweetLink(tweet)), new StringField(TwitterUtils.getUserLink(tweet)), new TextField(TwitterUtils.getUserScreenName(tweet)), new TextField(TwitterUtils.getUserName(tweet)), new TextField(TwitterUtils.getUserDescription(tweet)), new IntegerField(TwitterUtils.getUserFollowerCnt(tweet)), new IntegerField(TwitterUtils.getUserFriendsCnt(tweet)), new TextField(TwitterUtils.getUserLocation(tweet)), new StringField(TwitterUtils.getCreateTime(tweet)), new TextField(TwitterUtils.getPlaceName(tweet)), new StringField(TwitterUtils.getCoordinates(tweet)), new StringField(TwitterUtils.getLanguage(tweet)));
String exactID = exactResults.get(0).getFields().get(0).getValue().toString();
String expectedID = exactResults.get(0).getField(SchemaConstants._ID).getValue().toString();
Assert.assertEquals(exactResults.size(), 1);
Assert.assertEquals(exactID, expectedID);
Assert.assertTrue(TwitterFeedTestHelper.compareTuple(exactResults, expectedTuple));
}
use of edu.uci.ics.texera.api.field.TextField 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);
}
use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.
the class KeywordConjunctionTest method testSingleWordQueryInTextField.
/**
* Verifies GetNextTuple of Keyword Matcher and single word queries in Text
* Field
*
* @throws Exception
*/
@Test
public void testSingleWordQueryInTextField() throws Exception {
// Prepare the query
String query = "TaLL";
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 span = new Span("description", 0, 4, "tall", "Tall", 0);
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] = new Attribute(RESULTS, AttributeType.LIST);
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("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<>(list) };
Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
List<Tuple> expectedResultList = new ArrayList<>();
expectedResultList.add(tuple1);
expectedResultList.add(tuple2);
// Perform the query
List<Tuple> resultList = KeywordTestHelper.getQueryResults(PEOPLE_TABLE, query, attributeNames, conjunction);
// check the results
boolean contains = TestUtils.equals(expectedResultList, resultList);
Assert.assertTrue(contains);
}
Aggregations