Search in sources :

Example 51 with StringField

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

the class WordCountIndexSource method computeNextMatchingTuple.

private Tuple computeNextMatchingTuple() throws TextDBException {
    if (sortedWordCountMap == null) {
        computeWordCount();
    }
    if (wordCountIterator.hasNext()) {
        Entry<String, Integer> entry = wordCountIterator.next();
        List<IField> tupleFieldList = new ArrayList<>();
        // Generate the new UUID.
        tupleFieldList.add(IDField.newRandomID());
        tupleFieldList.add(new StringField(entry.getKey()));
        tupleFieldList.add(new IntegerField(entry.getValue()));
        cursor++;
        return new Tuple(SCHEMA_WORD_COUNT, tupleFieldList);
    }
    return null;
}
Also used : StringField(edu.uci.ics.textdb.api.field.StringField) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.textdb.api.field.IntegerField) IField(edu.uci.ics.textdb.api.field.IField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple)

Example 52 with StringField

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

the class DictionaryMatcherTest method testMatchingWithLimitOffset.

@Test
public void testMatchingWithLimitOffset() throws Exception {
    ArrayList<String> word = new ArrayList<String>(Arrays.asList("angry"));
    Dictionary dictionary = new Dictionary(word);
    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;
    Span span1 = new Span("description", 5, 10, "angry", "Angry");
    Span span2 = new Span("description", 6, 11, "angry", "Angry");
    Span span3 = new Span("description", 40, 45, "angry", "Angry");
    Span span4 = new Span("description", 6, 11, "angry", "angry");
    List<Span> list1 = new ArrayList<>();
    list1.add(span1);
    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<>(list1) };
    List<Span> list2 = new ArrayList<>();
    list2.add(span2);
    IField[] fields2 = { new StringField("brad lie angelina"), new StringField("pitt"), new IntegerField(44), new DoubleField(6.10), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-12-1972")), new TextField("White Angry"), new ListField<>(list2) };
    List<Span> list3 = new ArrayList<>();
    list3.add(span3);
    IField[] fields3 = { 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<>(list3) };
    List<Span> list4 = new ArrayList<>();
    list4.add(span4);
    IField[] fields4 = { new StringField("Mary brown"), new StringField("Lake Forest"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Short angry"), new ListField<>(list4) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    Tuple tuple3 = new Tuple(new Schema(schemaAttributes), fields3);
    Tuple tuple4 = new Tuple(new Schema(schemaAttributes), fields4);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
    List<Tuple> expectedList = new ArrayList<>();
    List<Tuple> resultList = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.PHRASE_INDEXBASED, 1, 1);
    expectedList.add(tuple1);
    expectedList.add(tuple2);
    expectedList.add(tuple3);
    expectedList.add(tuple4);
    Assert.assertEquals(expectedList.size(), 4);
    Assert.assertEquals(resultList.size(), 1);
    Assert.assertTrue(TestUtils.containsAll(expectedList, resultList));
}
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)

Example 53 with StringField

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

the class DictionaryMatcherTest method testMultipleWordsQueryUsingScanChinese.

/**
     * Scenario: verifies ITuple returned by DictionaryMatcher and multiple
     * word queries using SCAN OPERATOR in Chinese
     */
@Test
public void testMultipleWordsQueryUsingScanChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("洛克贝尔"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("lastName", 0, 4, "洛克贝尔", "洛克贝尔");
    list.add(span);
    Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
    IField[] fields1 = { new StringField("孔明"), new StringField("洛克贝尔"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("北京大学计算机学院"), new ListField<Span>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_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)

Example 54 with StringField

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

the class DictionaryMatcherTest method testMultipleWordsQueryUsingKeywordChinese.

/**
     * Scenario: verifies ITuple returned by DictionaryMatcher and multiple
     * word queries using KEYWORD OPERATOR
     */
@Test
public void testMultipleWordsQueryUsingKeywordChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("洛克贝尔"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("lastName", 0, 4, "洛克贝尔", "洛克贝尔");
    ;
    list.add(span);
    Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
    IField[] fields1 = { new StringField("孔明"), new StringField("洛克贝尔"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("北京大学计算机学院"), new ListField<Span>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.CONJUNCTION_INDEXBASED);
    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)

Example 55 with StringField

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

the class DictionaryMatcherTest method testWordInMultipleFieldsQueryUsingPhrase.

/**
     * Scenario S-13:verifies: data source has multiple attributes, and an
     * entity can appear in all the fields and multiple times using PHRASE
     * OPERATOR.
     */
@Test
public void testWordInMultipleFieldsQueryUsingPhrase() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("lin clooney"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span1 = new Span("lastName", 0, 11, "lin clooney", "lin clooney");
    Span span2 = new Span("description", 0, 11, "lin clooney", "Lin Clooney");
    Span span3 = new Span("description", 25, 36, "lin clooney", "lin clooney");
    list.add(span1);
    list.add(span2);
    list.add(span3);
    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("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<Span>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.PHRASE_INDEXBASED);
    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

StringField (edu.uci.ics.textdb.api.field.StringField)91 Tuple (edu.uci.ics.textdb.api.tuple.Tuple)85 IField (edu.uci.ics.textdb.api.field.IField)84 IntegerField (edu.uci.ics.textdb.api.field.IntegerField)81 TextField (edu.uci.ics.textdb.api.field.TextField)81 ArrayList (java.util.ArrayList)76 Test (org.junit.Test)75 DoubleField (edu.uci.ics.textdb.api.field.DoubleField)68 DateField (edu.uci.ics.textdb.api.field.DateField)64 Schema (edu.uci.ics.textdb.api.schema.Schema)64 SimpleDateFormat (java.text.SimpleDateFormat)63 Attribute (edu.uci.ics.textdb.api.schema.Attribute)60 Span (edu.uci.ics.textdb.api.span.Span)58 Dictionary (edu.uci.ics.textdb.exp.dictionarymatcher.Dictionary)24 JoinDistancePredicate (edu.uci.ics.textdb.exp.join.JoinDistancePredicate)9 KeywordMatcherSourceOperator (edu.uci.ics.textdb.exp.keywordmatcher.KeywordMatcherSourceOperator)9 IDField (edu.uci.ics.textdb.api.field.IDField)5 ParseException (java.text.ParseException)4 JsonNode (com.fasterxml.jackson.databind.JsonNode)3 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)3