Examples with ScanBasedSourceOperator edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator used on opensource projects

Example 6 with ScanBasedSourceOperator

use of edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator in project textdb by TextDB.

the class JoinTestHelper method getRegexMatcher.

public static RegexMatcher getRegexMatcher(String tableName, String query, String attrName) {
    try {
        ScanBasedSourceOperator scanBasedSourceOperator = new ScanBasedSourceOperator(new ScanSourcePredicate(tableName));
        RegexMatcher regexMatcher = new RegexMatcher(new RegexPredicate(query, Arrays.asList(attrName), SchemaConstants.SPAN_LIST));
        regexMatcher.setInputOperator(scanBasedSourceOperator);
        return regexMatcher;
    } catch (DataflowException e) {
        e.printStackTrace();
        return null;
    }
}

Example 7 with ScanBasedSourceOperator

use of edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator in project textdb by TextDB.

the class ProjectionOperatorTest method testProjection1.

@Test
public void testProjection1() throws Exception {
    List<String> projectionFields = Arrays.asList(TestConstants.DESCRIPTION);
    Schema projectionSchema = new Schema(TestConstants.DESCRIPTION_ATTR);
    IField[] fields1 = { new TextField("Tall Angry") };
    IField[] fields2 = { new TextField("Short Brown") };
    IField[] fields3 = { new TextField("White Angry") };
    IField[] fields4 = { new TextField("Lin Clooney is Short and lin clooney is Angry") };
    IField[] fields5 = { new TextField("Tall Fair") };
    IField[] fields6 = { new TextField("Short angry") };
    Tuple tuple1 = new Tuple(projectionSchema, fields1);
    Tuple tuple2 = new Tuple(projectionSchema, fields2);
    Tuple tuple3 = new Tuple(projectionSchema, fields3);
    Tuple tuple4 = new Tuple(projectionSchema, fields4);
    Tuple tuple5 = new Tuple(projectionSchema, fields5);
    Tuple tuple6 = new Tuple(projectionSchema, fields6);
    List<Tuple> expectedResults = Arrays.asList(tuple1, tuple2, tuple3, tuple4, tuple5, tuple6);
    List<Tuple> returnedResults = getProjectionResults(new ScanBasedSourceOperator(new ScanSourcePredicate(PEOPLE_TABLE)), projectionFields);
    Assert.assertTrue(TestUtils.equals(expectedResults, returnedResults));
}

Example 8 with ScanBasedSourceOperator

use of edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator in project textdb by TextDB.

the class RegexMatcherTestHelper method getScanSourceResults.

public static List<Tuple> getScanSourceResults(String tableName, String keywordQuery1, String regex, List<String> attributeNames, KeywordMatchingType matchingType, String spanListName1, int limit, int offset, String keywordQuery2, String spanListName2) throws TexeraException {
    ScanBasedSourceOperator scanSource = new ScanBasedSourceOperator(new ScanSourcePredicate(tableName));
    KeywordPredicate keywordPredicate = new KeywordPredicate(keywordQuery1, attributeNames, LuceneAnalyzerConstants.standardAnalyzerString(), matchingType, spanListName1);
    KeywordMatcher keywordMatcher = new KeywordMatcher(keywordPredicate);
    KeywordPredicate keywordPredicate1 = new KeywordPredicate(keywordQuery2, attributeNames, LuceneAnalyzerConstants.standardAnalyzerString(), matchingType, spanListName2);
    KeywordMatcher keywordMatcher1 = new KeywordMatcher(keywordPredicate1);
    keywordMatcher1.setInputOperator(keywordMatcher);
    keywordMatcher.setInputOperator(scanSource);
    RegexPredicate regexPredicate = new RegexPredicate(regex, attributeNames, RESULTS);
    RegexMatcher regexMatcher = new RegexMatcher(regexPredicate);
    regexMatcher.setLimit(limit);
    regexMatcher.setOffset(offset);
    regexMatcher.setInputOperator(keywordMatcher1);
    Tuple tuple;
    List<Tuple> results = new ArrayList<>();
    regexMatcher.open();
    while ((tuple = regexMatcher.getNextTuple()) != null) {
        results.add(tuple);
    }
    regexMatcher.close();
    return results;
}

Example 9 with ScanBasedSourceOperator

use of edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator in project textdb by TextDB.

the class ScanBasedSourceOperatorTest method testFlow.

@Test
public void testFlow() throws TexeraException, ParseException {
    List<Tuple> actualTuples = TestConstants.getSamplePeopleTuples();
    ScanBasedSourceOperator scanBasedSourceOperator = new ScanBasedSourceOperator(new ScanSourcePredicate(PEOPLE_TABLE));
    scanBasedSourceOperator.open();
    Tuple nextTuple = null;
    int numTuples = 0;
    List<Tuple> returnedTuples = new ArrayList<Tuple>();
    while ((nextTuple = scanBasedSourceOperator.getNextTuple()) != null) {
        returnedTuples.add(nextTuple);
        numTuples++;
    }
    Assert.assertEquals(actualTuples.size(), numTuples);
    boolean contains = TestUtils.equals(actualTuples, returnedTuples);
    Assert.assertTrue(contains);
    scanBasedSourceOperator.close();
}

Example 10 with ScanBasedSourceOperator

use of edu.uci.ics.texera.dataflow.source.scan.ScanBasedSourceOperator in project textdb by TextDB.

the class WordCountTest method computePayLoadWordCount.

// Compute result by tuple's PayLoad.
public static HashMap<String, Integer> computePayLoadWordCount(String tableName, String attribute) throws TexeraException {
    ScanBasedSourceOperator scanSource = new ScanBasedSourceOperator(new ScanSourcePredicate(tableName));
    WordCountOperator wordCount = null;
    HashMap<String, Integer> result = new HashMap<String, Integer>();
    if (tableName.equals(COUNT_TABLE)) {
        wordCount = new WordCountOperator(new WordCountOperatorPredicate(TestConstants.DESCRIPTION, LuceneAnalyzerConstants.standardAnalyzerString()));
    } else if (tableName.equals(COUNT_CHINESE_TABLE)) {
        wordCount = new WordCountOperator(new WordCountOperatorPredicate(TestConstantsChineseWordCount.DESCRIPTION, LuceneAnalyzerConstants.chineseAnalyzerString()));
    }
    wordCount.setInputOperator(scanSource);
    wordCount.open();
    Tuple tuple;
    while ((tuple = wordCount.getNextTuple()) != null) {
        result.put((String) tuple.getField(WordCountOperator.WORD).getValue(), (Integer) tuple.getField(WordCountOperator.COUNT).getValue());
    }
    wordCount.close();
    return result;
}