Examples with StringField edu.uci.ics.textdb.api.field.StringField used on opensource projects

Example 41 with StringField

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

the class RelationManagerTest method test10.

/*
     * Test inserting multiple tuples to a table, getting them by a query, then deleting them by a query
     */
@Test
public void test10() throws Exception {
    String tableName = "relation_manager_test_table";
    String tableDirectory = "./index/test_table";
    Schema tableSchema = new Schema(new Attribute("content", AttributeType.STRING), new Attribute("number", AttributeType.STRING));
    RelationManager relationManager = RelationManager.getRelationManager();
    relationManager.deleteTable(tableName);
    relationManager.createTable(tableName, tableDirectory, tableSchema, LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter dataWriter = relationManager.getTableDataWriter(tableName);
    dataWriter.open();
    Tuple insertedTuple = new Tuple(tableSchema, new StringField("test"), new StringField("1"));
    dataWriter.insertTuple(insertedTuple);
    Tuple insertedTuple2 = new Tuple(tableSchema, new StringField("test"), new StringField("2"));
    IDField idField2 = dataWriter.insertTuple(insertedTuple2);
    Tuple insertedTuple3 = new Tuple(tableSchema, new StringField("test"), new StringField("3"));
    dataWriter.insertTuple(insertedTuple3);
    dataWriter.close();
    // test should match all 3 tuples
    Query allTupleQuery = new TermQuery(new Term("content", "test"));
    DataReader allTupleReader = relationManager.getTableDataReader(tableName, allTupleQuery);
    int tupleCounter = 0;
    allTupleReader.open();
    while (allTupleReader.getNextTuple() != null) {
        tupleCounter++;
    }
    allTupleReader.close();
    Assert.assertEquals(3, tupleCounter);
    // tuple 2 should be deleted
    Query tuple2Query = new TermQuery(new Term("number", "2"));
    dataWriter.open();
    dataWriter.deleteTuple(tuple2Query);
    dataWriter.close();
    Tuple deletedTuple = relationManager.getTupleByID(tableName, idField2);
    Assert.assertNull(deletedTuple);
    relationManager.deleteTable(tableName);
}

Example 42 with StringField

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

the class SampleExtraction method parsePromedHTML.

public static Tuple parsePromedHTML(String fileName, String content) {
    try {
        Document parsedDocument = Jsoup.parse(content);
        String mainText = parsedDocument.getElementById("preview").text();
        Tuple tuple = new Tuple(PromedSchema.PROMED_SCHEMA, new StringField(fileName), new TextField(mainText));
        return tuple;
    } catch (Exception e) {
        return null;
    }
}

Example 43 with StringField

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

the class TwitterSample method writeTwitterIndex.

public static void writeTwitterIndex() throws Exception {
    RelationManager relationManager = RelationManager.getRelationManager();
    relationManager.deleteTable(twitterClimateTable);
    relationManager.createTable(twitterClimateTable, "../index/twitter/", TwitterSchema.TWITTER_SCHEMA, LuceneAnalyzerConstants.standardAnalyzerString());
    DataWriter dataWriter = relationManager.getTableDataWriter(twitterClimateTable);
    dataWriter.open();
    int counter = 0;
    JsonNode jsonNode = new ObjectMapper().readTree(new File(twitterFilePath));
    for (JsonNode tweet : jsonNode) {
        try {
            String text = tweet.get("text").asText();
            Long id = tweet.get("id").asLong();
            String tweetLink = "https://twitter.com/statuses/" + id;
            JsonNode userNode = tweet.get("user");
            String userScreenName = userNode.get("screen_name").asText();
            String userLink = "https://twitter.com/" + userScreenName;
            String userName = userNode.get("name").asText();
            String userDescription = userNode.get("description").asText();
            Integer userFollowersCount = userNode.get("followers_count").asInt();
            Integer userFriendsCount = userNode.get("friends_count").asInt();
            JsonNode geoTagNode = tweet.get("geo_tag");
            String state = geoTagNode.get("stateName").asText();
            String county = geoTagNode.get("countyName").asText();
            String city = geoTagNode.get("cityName").asText();
            String createAt = tweet.get("create_at").asText();
            Tuple tuple = new Tuple(TwitterSchema.TWITTER_SCHEMA, new TextField(text), new StringField(tweetLink), new StringField(userLink), new TextField(userScreenName), new TextField(userName), new TextField(userDescription), new IntegerField(userFollowersCount), new IntegerField(userFriendsCount), new TextField(state), new TextField(county), new TextField(city), new StringField(createAt));
            dataWriter.insertTuple(tuple);
            counter++;
        } catch (RuntimeException e) {
            e.printStackTrace();
            continue;
        }
    }
    dataWriter.close();
    System.out.println("write twitter data finished");
    System.out.println(counter + " tweets written");
}

Example 44 with StringField

use of edu.uci.ics.textdb.api.field.StringField 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()));
}

Example 45 with StringField

use of edu.uci.ics.textdb.api.field.StringField 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);
}