Search in sources :

Example 11 with TextField

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

the class DictionaryMatcherTest method testWordInMultipleFieldsQueryUsingKeyword.

/**
     * Scenario S-12:verifies: data source has multiple attributes, and an
     * entity can appear in all the fields and multiple times using KEYWORD
     * OPERATOR.
     */
@Test
public void testWordInMultipleFieldsQueryUsingKeyword() 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, 3, "lin", "Lin", 0);
    Span span3 = new Span("description", 4, 11, "clooney", "Clooney", 1);
    Span span4 = new Span("description", 25, 28, "lin", "lin", 5);
    Span span5 = new Span("description", 29, 36, "clooney", "clooney", 6);
    list.add(span1);
    list.add(span2);
    list.add(span3);
    list.add(span4);
    list.add(span5);
    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.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 12 with TextField

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

the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingScanChinese.

/**
     * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
     * queries in String Field using SUBSTRING_SCANBASED
     * Test in Chinese.
     */
@Test
public void testSingleWordQueryInStringFieldUsingScanChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("孔明"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("firstName", 0, 2, "孔明", "孔明");
    list.add(span);
    Schema resultSchema = Utils.addAttributeToSchema(TestConstantsChinese.SCHEMA_PEOPLE, 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(resultSchema, fields1);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    List<String> attributeNames = Arrays.asList(TestConstants.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) 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 13 with TextField

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

the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingKeywordChinese.

/**
     * Scenario: verifies GetNextTuple of DictionaryMatcher and multiple word
     * queries in String Field using KEYWORDOPERATOR
     * Test in Chinese.
     */
@Test
public void testSingleWordQueryInStringFieldUsingKeywordChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("无忌", "长孙"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list1 = new ArrayList<Span>();
    List<Span> list2 = new ArrayList<Span>();
    Span span1 = new Span("lastName", 0, 2, "长孙", "长孙");
    Span span2 = new Span("firstName", 0, 2, "无忌", "无忌");
    list1.add(span1);
    list2.add(span2);
    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("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list1) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    IField[] fields2 = { new StringField("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list2) };
    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(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 14 with TextField

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

the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingKeywordChinese.

/**
     * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
     * queries in Text Field using KEYWORD OPERATOR in Chinese
     */
@Test
public void testSingleWordQueryInTextFieldUsingKeywordChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("北京大学"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("description", 0, 4, "北京大学", "北京大学", 0);
    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("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list) };
    IField[] fields2 = { 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);
    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(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 15 with TextField

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

the class JoinDistanceTest method testBothTheSpansAreSame.

// This case tests for the scenario when the spans to be joined are the same, i.e. both the keywords
// are same.
// e.g.
// [<11, 18>]
// [<11, 18>]
// threshold = 20 (can be any non-negative number)
// [ ]
// [ ]
// Test result: Join should return same span and key and the value in span
// should be the same.
// [<11, 18>]
@Test
public void testBothTheSpansAreSame() throws Exception {
    JoinTestHelper.insertToTable(BOOK_TABLE, JoinTestConstants.bookGroup1.get(0));
    KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
    KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
    List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 20), Integer.MAX_VALUE, 0);
    Schema resultSchema = Utils.createSpanSchema(JoinTestConstants.BOOK_SCHEMA);
    List<Span> spanList = new ArrayList<>();
    Span span1 = new Span(JoinTestConstants.REVIEW, 11, 18, "special_special", "special");
    spanList.add(span1);
    IField[] book1 = { new IntegerField(52), new StringField("Mary Roach"), new StringField("Grunt: The Curious Science of Humans at War"), new IntegerField(288), new TextField("It takes a special kind " + "of writer to make topics ranging from death to our " + "gastrointestinal tract interesting (sometimes " + "hilariously so), and pop science writer Mary Roach is " + "always up to the task."), new ListField<>(spanList) };
    Tuple expectedTuple = new Tuple(resultSchema, book1);
    List<Tuple> expectedResult = new ArrayList<>();
    expectedResult.add(expectedTuple);
    Assert.assertEquals(1, resultList.size());
    Assert.assertTrue(TestUtils.equals(expectedResult, resultList));
}
Also used : 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) JoinDistancePredicate(edu.uci.ics.textdb.exp.join.JoinDistancePredicate) Span(edu.uci.ics.textdb.api.span.Span) KeywordMatcherSourceOperator(edu.uci.ics.textdb.exp.keywordmatcher.KeywordMatcherSourceOperator) StringField(edu.uci.ics.textdb.api.field.StringField) TextField(edu.uci.ics.textdb.api.field.TextField) Tuple(edu.uci.ics.textdb.api.tuple.Tuple) Test(org.junit.Test)

Aggregations

TextField (edu.uci.ics.textdb.api.field.TextField)117 IField (edu.uci.ics.textdb.api.field.IField)105 Tuple (edu.uci.ics.textdb.api.tuple.Tuple)92 ArrayList (java.util.ArrayList)91 Schema (edu.uci.ics.textdb.api.schema.Schema)83 Test (org.junit.Test)83 StringField (edu.uci.ics.textdb.api.field.StringField)81 IntegerField (edu.uci.ics.textdb.api.field.IntegerField)80 Attribute (edu.uci.ics.textdb.api.schema.Attribute)74 Span (edu.uci.ics.textdb.api.span.Span)71 DoubleField (edu.uci.ics.textdb.api.field.DoubleField)68 DateField (edu.uci.ics.textdb.api.field.DateField)64 SimpleDateFormat (java.text.SimpleDateFormat)63 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 ParseException (java.text.ParseException)4 IOperator (edu.uci.ics.textdb.api.dataflow.IOperator)3 ScanBasedSourceOperator (edu.uci.ics.textdb.exp.source.scan.ScanBasedSourceOperator)3 ScanSourcePredicate (edu.uci.ics.textdb.exp.source.scan.ScanSourcePredicate)3