Examples with Tuple edu.uci.ics.texera.api.tuple.Tuple used on opensource projects

Example 56 with Tuple

use of edu.uci.ics.texera.api.tuple.Tuple in project textdb by TextDB.

the class RegexMatcherTest method testGetNextTupleStaffEmail.

@Test
public void testGetNextTupleStaffEmail() throws Exception {
    String query = "^([a-z0-9_\\.-]+)@([\\da-z\\.-]+)\\.([a-z\\.]{2,6})$";
    List<Tuple> exactResults = RegexMatcherTestHelper.getQueryResults(STAFF_TABLE, query, Arrays.asList(RegexTestConstantStaff.EMAIL));
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    // expected to match "k.bocanegra@uci.edu"
    List<Tuple> data = RegexTestConstantStaff.getSampleStaffTuples();
    Schema spanSchema = new Schema.Builder().add(RegexTestConstantStaff.SCHEMA_STAFF).add(RESULTS, AttributeType.LIST).build();
    List<Span> spans = new ArrayList<Span>();
    spans.add(new Span(RegexTestConstantStaff.EMAIL, 0, 19, query, "m.bocanegra@164.com"));
    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 "hwangl@ics.uci.edu"
    spans.clear();
    spans.add(new Span(RegexTestConstantStaff.EMAIL, 0, 18, query, "hwangk@ske.akb.edu"));
    spanField = new ListField<Span>(new ArrayList<Span>(spans));
    fields = new ArrayList<IField>(data.get(1).getFields());
    fields.add(spanField);
    expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
    Assert.assertTrue(TestUtils.equals(expectedResults, exactResults));
}

Example 57 with Tuple

use of edu.uci.ics.texera.api.tuple.Tuple in project textdb by TextDB.

the class LabeledRegexMatcherTest method testIgnoreCaseLabeledRegex.

@Test
public void testIgnoreCaseLabeledRegex() throws Exception {
    String query = "<NAME>";
    String keywordQuery = "george lin lin";
    List<Tuple> exactResults = RegexMatcherTestHelper.getQueryResults(PEOPLE_TABLE, query, keywordQuery, Arrays.asList(TestConstants.FIRST_NAME), "name", false, Integer.MAX_VALUE, 0);
    List<Tuple> expectedResults = new ArrayList<>();
    // expected to match "george lin lin"
    List<Tuple> data = TestConstants.getSamplePeopleTuples();
    Schema spanSchema = new Schema.Builder().add(TestConstants.SCHEMA_PEOPLE).add(RESULTS, AttributeType.LIST).build();
    List<Span> spans = new ArrayList<>();
    spans.add(new Span(TestConstants.FIRST_NAME, 0, 14, query, "george lin lin"));
    IField spanField = new ListField<>(new ArrayList<>(spans));
    List<IField> fields = new ArrayList<>(data.get(3).getFields());
    fields.add(spanField);
    expectedResults.add(new Tuple(spanSchema, fields.toArray(new IField[fields.size()])));
    List<String> attributeNames = new ArrayList<>();
    attributeNames.add(RESULTS);
    Assert.assertTrue(TestUtils.attributeEquals(expectedResults, exactResults, attributeNames));
}

Example 58 with Tuple

use of edu.uci.ics.texera.api.tuple.Tuple in project textdb by TextDB.

the class SampleExtraction method parsePromedHTML.

public static Tuple parsePromedHTML(String fileName, String content) {
    try {
        Document parsedDocument = Jsoup.parse(content);
        String mainText = parsedDocument.getElementById("preview").text();
        Tuple tuple = new Tuple(PromedSchema.PROMED_SCHEMA, new StringField(fileName), new TextField(mainText));
        return tuple;
    } catch (Exception e) {
        return null;
    }
}

Example 59 with Tuple

use of edu.uci.ics.texera.api.tuple.Tuple in project textdb by TextDB.

the class SampleExtraction method writeSampleIndex.

public static void writeSampleIndex() throws Exception {
    // parse the original file
    File sourceFileFolder = new File(promedFilesDirectory);
    ArrayList<Tuple> fileTuples = new ArrayList<>();
    for (File htmlFile : sourceFileFolder.listFiles()) {
        StringBuilder sb = new StringBuilder();
        Scanner scanner = new Scanner(htmlFile);
        while (scanner.hasNext()) {
            sb.append(scanner.nextLine());
        }
        scanner.close();
        Tuple tuple = parsePromedHTML(htmlFile.getName(), sb.toString());
        if (tuple != null) {
            fileTuples.add(tuple);
        }
    }
    // write tuples into the table
    RelationManager relationManager = RelationManager.getInstance();
    relationManager.deleteTable(PROMED_SAMPLE_TABLE);
    relationManager.createTable(PROMED_SAMPLE_TABLE, Paths.get(promedIndexDirectory), PromedSchema.PROMED_SCHEMA, LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter dataWriter = relationManager.getTableDataWriter(PROMED_SAMPLE_TABLE);
    dataWriter.open();
    for (Tuple tuple : fileTuples) {
        dataWriter.insertTuple(tuple);
    }
    dataWriter.close();
}

Example 60 with Tuple

use of edu.uci.ics.texera.api.tuple.Tuple in project textdb by TextDB.

the class TwitterSample method createTwitterTable.

/**
 * A helper function to create a table and write twitter data into it.
 *
 * @param tableName
 * @param twitterJsonSourceOperator, a source operator that provides the input raw twitter JSON string tuples
 * @return
 */
public static int createTwitterTable(String tableName, ISourceOperator twitterJsonSourceOperator) {
    TwitterJsonConverter twitterJsonConverter = new TwitterJsonConverterPredicate("twitterJson").newOperator();
    TupleSink tupleSink = new TupleSinkPredicate(null, null).newOperator();
    twitterJsonConverter.setInputOperator(twitterJsonSourceOperator);
    tupleSink.setInputOperator(twitterJsonConverter);
    // open the workflow plan and get the output schema
    tupleSink.open();
    // create the table with TupleSink's output schema
    RelationManager relationManager = RelationManager.getInstance();
    if (relationManager.checkTableExistence(tableName)) {
        relationManager.deleteTable(tableName);
    }
    relationManager.createTable(tableName, Utils.getDefaultIndexDirectory().resolve(tableName), tupleSink.getOutputSchema(), LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter dataWriter = relationManager.getTableDataWriter(tableName);
    dataWriter.open();
    Tuple tuple;
    int counter = 0;
    while ((tuple = tupleSink.getNextTuple()) != null) {
        dataWriter.insertTuple(tuple);
        counter++;
    }
    dataWriter.close();
    tupleSink.close();
    return counter;
}