Search in sources :

Example 96 with StringField

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

the class KeywordPhraseTest method testWordInMultipleFieldsQueryWithStopWords5.

/**
 * Verifies: Query with Stop Words match corresponding phrases in the
 * document Used to cause exception sometimes if there is a space between
 * words
 *
 * @throws Exception
 *             with Medline data
 */
@Test
public void testWordInMultipleFieldsQueryWithStopWords5() throws Exception {
    // Prepare Query
    String query = "gain weight";
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(keywordTestConstants.ABSTRACT);
    // Prepare expected result list
    List<Span> list = new ArrayList<>();
    Span span1 = new Span(keywordTestConstants.ABSTRACT, 26, 37, "gain weight", "gain weight");
    list.add(span1);
    Attribute[] schemaAttributes = new Attribute[keywordTestConstants.ATTRIBUTES_MEDLINE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = keywordTestConstants.ATTRIBUTES_MEDLINE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
    IField[] fields = { new IntegerField(4566015), new TextField(""), new TextField("Significance of milk pH in newborn infants."), new TextField("V C Harrison, G Peat"), new StringField("4-5839 Dec 2, 1972"), new TextField("British medical journal"), new TextField(""), new TextField("Infant Nutritional Physiological Phenomena, Infant, Newborn, Milk"), new TextField("Bottle-fed infants do not gain weight as rapidly as breast-fed babies during the first week of life. This " + "weight lag can be corrected by the addition of a small amount of alkali (sodium bicarbonate or trometamol) to " + "the feeds. The alkali corrects the acidity of cow's milk which now assumes some of the properties of human breast " + "milk. It has a bacteriostatic effect on specific Escherichia coli in vitro, and in infants it produces a stool with" + " a preponderance of lactobacilli over E. coli organisms. When alkali is removed from the milk there is a decrease in" + " the weight of an infant and the stools contain excessive numbers of E. coli bacteria.A pH-corrected milk appears to" + " be more physiological than unaltered cow's milk and may provide some protection against gastroenteritis in early " + "life. Its bacteriostatic effect on specific E. coli may be of practical significance in feed preparations where " + "terminal sterilization and refrigeration are not available. The study was conducted during the week after birth, and " + "no conclusions are derived for older infants. The long-term effects of trometamol are unknown. No recommendation can " + "be given for the addition of sodium bicarbonate to milks containing a higher content of sodium."), new DoubleField(0.667832788), new ListField<>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields);
    List<Tuple> expectedResultList = new ArrayList<>();
    expectedResultList.add(tuple1);
    List<Tuple> results = KeywordTestHelper.getQueryResults(MEDLINE_TABLE, query, attributeNames, phrase);
    // Perform Check
    boolean contains = TestUtils.equals(expectedResultList, results);
    Assert.assertTrue(contains);
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 97 with StringField

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

the class KeywordPhraseTest method testWordInMultipleFieldsQueryWithStopWords4.

/**
 * Verifies: Query with Stop Words match corresponding phrases in the
 * document Used to cause exception if there is a special symbol with the
 * words, ex: big(
 *
 * @throws Exception
 *             with Medline data
 */
@Test
public void testWordInMultipleFieldsQueryWithStopWords4() throws Exception {
    // Prepare Query
    String query = "x-ray";
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(keywordTestConstants.ABSTRACT);
    // Prepare expected result list
    List<Span> list = new ArrayList<>();
    Span span1 = new Span(keywordTestConstants.ABSTRACT, 226, 231, "x-ray", "x-ray");
    list.add(span1);
    Attribute[] schemaAttributes = new Attribute[keywordTestConstants.ATTRIBUTES_MEDLINE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = keywordTestConstants.ATTRIBUTES_MEDLINE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = new Attribute(RESULTS, AttributeType.LIST);
    IField[] fields = { new IntegerField(17832788), new TextField(""), new TextField("Cosmic X-ray Sources."), new TextField("S Bowyer, E T Byram, T A Chubb, H Friedman"), new StringField("147-3656 Jan 22, 1965"), new TextField("Science (New York, N.Y.)"), new TextField(""), new TextField(""), new TextField("Eight new sources of cosmic x-rays were detected by two Aerobee surveys in 1964. One source, from Sagittarius, is close to the galactic center, and the other, " + "from Ophiuchus, may coincide with Kepler's 1604 supernova. All the x-ray sources are fairly close to the galactic plane."), new DoubleField(0.667832788), new ListField<>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields);
    List<Tuple> expectedResultList = new ArrayList<>();
    expectedResultList.add(tuple1);
    List<Tuple> results = KeywordTestHelper.getQueryResults(MEDLINE_TABLE, query, attributeNames, phrase);
    // Perform Check
    boolean contains = TestUtils.equals(expectedResultList, results);
    Assert.assertTrue(contains);
}
Also used : Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 98 with StringField

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

the class DictionaryMatcherTest method testSingleWordQueryInStringFieldUsingScan.

/**
 * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
 * queries in String Field using SCANOPERATOR
 */
@Test
public void testSingleWordQueryInStringFieldUsingScan() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("bruce"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("firstName", 0, 5, "bruce", "bruce");
    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) };
    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.SUBSTRING_SCANBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 99 with StringField

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

the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingScanChinese.

/**
 * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
 * queries in Text Field using SCANOPERATOR in Chinese.
 */
@Test
public void testSingleWordQueryInTextFieldUsingScanChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("学院"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list1 = new ArrayList<Span>();
    Span span1 = new Span("description", 8, 10, "学院", "学院");
    list1.add(span1);
    List<Span> list2 = new ArrayList<Span>();
    Span span2 = new Span("description", 7, 9, "学院", "学院");
    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) };
    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>(list2) };
    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.SUBSTRING_SCANBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 100 with StringField

use of edu.uci.ics.texera.api.field.StringField 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>();
    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);
    list1.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);
    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.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Aggregations

StringField (edu.uci.ics.texera.api.field.StringField)103 Tuple (edu.uci.ics.texera.api.tuple.Tuple)94 IField (edu.uci.ics.texera.api.field.IField)87 IntegerField (edu.uci.ics.texera.api.field.IntegerField)87 TextField (edu.uci.ics.texera.api.field.TextField)79 Schema (edu.uci.ics.texera.api.schema.Schema)75 ArrayList (java.util.ArrayList)74 Test (org.junit.Test)70 Span (edu.uci.ics.texera.api.span.Span)64 DoubleField (edu.uci.ics.texera.api.field.DoubleField)63 DateField (edu.uci.ics.texera.api.field.DateField)60 Attribute (edu.uci.ics.texera.api.schema.Attribute)60 SimpleDateFormat (java.text.SimpleDateFormat)58 Dictionary (edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary)29 JoinDistancePredicate (edu.uci.ics.texera.dataflow.join.JoinDistancePredicate)9 KeywordMatcherSourceOperator (edu.uci.ics.texera.dataflow.keywordmatcher.KeywordMatcherSourceOperator)9 JsonNode (com.fasterxml.jackson.databind.JsonNode)8 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)8 IDField (edu.uci.ics.texera.api.field.IDField)5 IOperator (edu.uci.ics.texera.api.dataflow.IOperator)4