Examples with StringField edu.uci.ics.texera.api.field.StringField used on opensource projects

Example 91 with StringField

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

the class AggregatorTest method testMaxDOBMinNameMaxNameAggregation.

// TEST 10: Find max in DOB, min in Name (String) and max in Name (String) column
@Test
public void testMaxDOBMinNameMaxNameAggregation() throws Exception {
    Attribute attribute1 = TestConstants.DATE_OF_BIRTH_ATTR;
    String attributeName1 = attribute1.getName();
    AggregationType aggType1 = AggregationType.MAX;
    Attribute attribute2 = TestConstants.FIRST_NAME_ATTR;
    String attributeName2 = attribute2.getName();
    AggregationType aggType2 = AggregationType.MIN;
    Attribute attribute3 = TestConstants.FIRST_NAME_ATTR;
    String attributeName3 = attribute2.getName();
    AggregationType aggType3 = AggregationType.MAX;
    String resultAttributeName1 = AggregatorTestConstants.MAX_DATE_RESULT_ATTR_NAME;
    String resultAttributeName2 = AggregatorTestConstants.MIN_FIRST_NAME_RESULT_ATTR_NAME;
    String resultAttributeName3 = AggregatorTestConstants.MAX_FIRST_NAME_RESULT_ATTR_NAME;
    AggregationAttributeAndResult aggEntity1 = new AggregationAttributeAndResult(attributeName1, aggType1, resultAttributeName1);
    AggregationAttributeAndResult aggEntity2 = new AggregationAttributeAndResult(attributeName2, aggType2, resultAttributeName2);
    AggregationAttributeAndResult aggEntity3 = new AggregationAttributeAndResult(attributeName3, aggType3, resultAttributeName3);
    List<AggregationAttributeAndResult> aggEntitiesList = new ArrayList<>();
    aggEntitiesList.add(aggEntity1);
    aggEntitiesList.add(aggEntity2);
    aggEntitiesList.add(aggEntity3);
    IField[] row1 = { new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new StringField("Mary brown"), new StringField("tom hanks") };
    Schema schema = new Schema(new Attribute(resultAttributeName1, AttributeType.DATE), new Attribute(resultAttributeName2, AttributeType.STRING), new Attribute(resultAttributeName3, AttributeType.STRING));
    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));
}

Example 92 with StringField

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

the class AsterixSource method getNextTuple.

@Override
public Tuple getNextTuple() throws TexeraException {
    if (cursor == CLOSED) {
        throw new DataflowException(ErrorMessages.OPERATOR_NOT_OPENED);
    }
    if (cursor < resultJsonArray.length()) {
        Tuple tuple = new Tuple(this.outputSchema, IDField.newRandomID(), new StringField(resultJsonArray.getJSONObject(cursor).get("ds").toString()));
        cursor++;
        return tuple;
    }
    return null;
}

Example 93 with StringField

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

the class TwitterJsonConverter method generateFieldsFromJson.

/**
 * Generates Fields from the raw JSON tweet.
 * Returns Optional.Empty() if something goes wrong while parsing this tweet.
 */
private Optional<List<IField>> generateFieldsFromJson(String rawJsonData) {
    try {
        // read the JSON string into a JSON object
        JsonNode tweet = new ObjectMapper().readTree(rawJsonData);
        // extract fields from the JSON object
        String text = tweet.get("text").asText();
        Long id = tweet.get("id").asLong();
        String tweetLink = "https://twitter.com/statuses/" + id;
        JsonNode userNode = tweet.get("user");
        String userScreenName = userNode.get("screen_name").asText();
        String userLink = "https://twitter.com/" + userScreenName;
        String userName = userNode.get("name").asText();
        String userDescription = userNode.get("description").asText();
        Integer userFollowersCount = userNode.get("followers_count").asInt();
        Integer userFriendsCount = userNode.get("friends_count").asInt();
        JsonNode geoTagNode = tweet.get("geo_tag");
        String state = geoTagNode.get("stateName").asText();
        String county = geoTagNode.get("countyName").asText();
        String city = geoTagNode.get("cityName").asText();
        String createAt = tweet.get("create_at").asText();
        ZonedDateTime zonedCreateAt = ZonedDateTime.parse(createAt, DateTimeFormatter.ISO_INSTANT.withZone(ZoneId.systemDefault()));
        String isRetweet = tweet.get("is_retweet").asText();
        return Optional.of(Arrays.asList(new StringField(id.toString()), new TextField(text), new StringField(tweetLink), new StringField(userLink), new TextField(userScreenName), new TextField(userName), new TextField(userDescription), new IntegerField(userFollowersCount), new IntegerField(userFriendsCount), new TextField(state), new TextField(county), new TextField(city), new DateTimeField(zonedCreateAt.toLocalDateTime()), new StringField(isRetweet)));
    } catch (Exception e) {
        return Optional.empty();
    }
}

Example 94 with StringField

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

the class TwitterFeedOperator method getNextTuple.

@Override
public Tuple getNextTuple() throws TexeraException {
    if (cursor == CLOSED || resultCursor >= limit - 1 || resultCursor >= predicate.getTweetNum() - 1) {
        return null;
    }
    if (twitterConnector.getClient().isDone()) {
        System.out.println("Client connection closed unexpectedly: " + twitterConnector.getClient().getExitEvent().getMessage());
        return null;
    }
    try {
        msg = twitterConnector.getMsgQueue().poll(timeout, TimeUnit.SECONDS);
        if (msg == null || msg.length() == 0) {
            System.out.println("Did not receive a message in " + timeout + " seconds");
            return null;
        }
        JsonNode tweet = new ObjectMapper().readValue(msg, JsonNode.class);
        sourceTuple = new Tuple(outputSchema, IDField.newRandomID(), 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)));
        resultCursor++;
        return sourceTuple;
    } catch (InterruptedException e) {
        System.out.println(e);
    } catch (IOException e) {
        e.printStackTrace();
    }
    return null;
}

Example 95 with StringField

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

the class KeywordPhraseTest method testPhraseSearchForStringField.

/**
 * Verifies List<ITuple> returned by Phrase Matcher on multiple word query
 * on a String Field
 *
 * @throws Exception
 */
@Test
public void testPhraseSearchForStringField() throws Exception {
    // Prepare Query
    String query = "george lin 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>();
    Span span1 = new Span("firstName", 0, 14, "george lin lin", "george 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.getQueryResults(PEOPLE_TABLE, query, attributeNames, phrase);
    // Perform Check
    boolean contains = TestUtils.equals(expectedResultList, resultList);
    Assert.assertTrue(contains);
}