Search in sources :

Example 61 with Attribute

use of edu.uci.ics.textdb.api.schema.Attribute in project textdb by TextDB.

the class FileSourceOperatorTest method test4.

/*
     * Test FileSourceOperator with a Directory with recursive = true and maxDepth = 2.
     * 
     * The files under the recursive sub-directories with recursive depth 2 will be read.
     *     
     * expected results: test1.txt, test2.txt and test4.txt will be included
     */
@Test
public void test4() throws Exception {
    String attrName = "content";
    Schema schema = new Schema(new Attribute(attrName, AttributeType.TEXT));
    FileSourcePredicate predicate = new FileSourcePredicate(tempFolderPath.toString(), attrName, true, 2, null);
    FileSourceOperator fileSource = new FileSourceOperator(predicate);
    Tuple tuple;
    ArrayList<Tuple> exactResults = new ArrayList<>();
    fileSource.open();
    while ((tuple = fileSource.getNextTuple()) != null) {
        exactResults.add(tuple);
    }
    fileSource.close();
    List<Tuple> expectedResults = Arrays.asList(new Tuple(schema, new TextField(tempFile1String)), new Tuple(schema, new TextField(tempFile2String)), new Tuple(schema, new TextField(tempFile4String)));
    Assert.assertTrue(TestUtils.equals(expectedResults, exactResults));
}
Also used : Attribute(edu.uci.ics.textdb.api.schema.Attribute) Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) TextField(edu.uci.ics.textdb.api.field.TextField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Example 62 with Attribute

use of edu.uci.ics.textdb.api.schema.Attribute 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(Paths.get(excelSink.getFilePath()));
}
Also used : Attribute(edu.uci.ics.textdb.api.schema.Attribute) IOperator(edu.uci.ics.textdb.api.dataflow.IOperator) Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) Span(edu.uci.ics.textdb.api.span.Span) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) DateField(edu.uci.ics.textdb.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.textdb.api.field.DoubleField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Example 63 with Attribute

use of edu.uci.ics.textdb.api.schema.Attribute in project textdb by TextDB.

the class ExcelSinkTest method testOpen.

@Test
public void testOpen() throws Exception {
    excelSink.open();
    //        // verify that inputOperator called open() method
    Mockito.verify(inputOperator).open();
    //        // assert that the tuple stream sink removes the _ID and PAYLOAD attribute
    Assert.assertEquals(new Schema(new Attribute("content", AttributeType.TEXT)), excelSink.getOutputSchema());
    excelSink.close();
    Files.deleteIfExists(Paths.get(excelSink.getFilePath()));
}
Also used : Attribute(edu.uci.ics.textdb.api.schema.Attribute) Schema(edu.uci.ics.textdb.api.schema.Schema) Test(org.junit.Test)

Example 64 with Attribute

use of edu.uci.ics.textdb.api.schema.Attribute in project textdb by TextDB.

the class TupleSinkTest method testOpenClose.

@Test
public void testOpenClose() throws Exception {
    TupleSink tupleSink = new TupleSink();
    tupleSink.setInputOperator(inputOperator);
    tupleSink.open();
    // verify that inputOperator called open() method
    Mockito.verify(inputOperator).open();
    // assert that the tuple stream sink removes the PAYLOAD attribute
    Assert.assertEquals(new Schema(SchemaConstants._ID_ATTRIBUTE, new Attribute("content", AttributeType.TEXT)), tupleSink.getOutputSchema());
    tupleSink.close();
    // verify that inputOperator called close() method
    Mockito.verify(inputOperator).close();
}
Also used : TupleSink(edu.uci.ics.textdb.exp.sink.tuple.TupleSink) Attribute(edu.uci.ics.textdb.api.schema.Attribute) Schema(edu.uci.ics.textdb.api.schema.Schema) Test(org.junit.Test)

Example 65 with Attribute

use of edu.uci.ics.textdb.api.schema.Attribute in project textdb by TextDB.

the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingScan.

/**
     * Scenario S-5:verifies GetNextTuple of DictionaryMatcher and single word
     * queries in Text Field using SCANOPERATOR
     */
@Test
public void testSingleWordQueryInTextFieldUsingScan() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("tall"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("description", 0, 4, "tall", "Tall");
    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] = RESULTS_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<Span>(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<Span>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    expectedResults.add(tuple2);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.SUBSTRING_SCANBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.textdb.exp.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.textdb.api.schema.Attribute) Schema(edu.uci.ics.textdb.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) Span(edu.uci.ics.textdb.api.span.Span) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) DateField(edu.uci.ics.textdb.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.textdb.api.field.DoubleField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Aggregations

Attribute (edu.uci.ics.textdb.api.schema.Attribute)118 ArrayList (java.util.ArrayList)94 Schema (edu.uci.ics.textdb.api.schema.Schema)93 Test (org.junit.Test)88 IField (edu.uci.ics.textdb.api.field.IField)87 Tuple (edu.uci.ics.textdb.api.tuple.Tuple)85 TextField (edu.uci.ics.textdb.api.field.TextField)74 Span (edu.uci.ics.textdb.api.span.Span)69 StringField (edu.uci.ics.textdb.api.field.StringField)61 IntegerField (edu.uci.ics.textdb.api.field.IntegerField)58 DoubleField (edu.uci.ics.textdb.api.field.DoubleField)57 DateField (edu.uci.ics.textdb.api.field.DateField)54 SimpleDateFormat (java.text.SimpleDateFormat)53 Dictionary (edu.uci.ics.textdb.exp.dictionarymatcher.Dictionary)23 ListField (edu.uci.ics.textdb.api.field.ListField)14 AttributeType (edu.uci.ics.textdb.api.schema.AttributeType)9 List (java.util.List)7 DataFlowException (edu.uci.ics.textdb.api.exception.DataFlowException)6 Collectors (java.util.stream.Collectors)6 SchemaConstants (edu.uci.ics.textdb.api.constants.SchemaConstants)5