Extraction script examples

FieldExtractor.ExtractRegularExpression( "(grant(s))|(convey to)|(grant)", "keyWords" );
FieldExtractor.ExtractWordsFromUserDictionary("dictionary", "English");
FieldExtractor.ExtractNerObjects();

// Access identified objects by collection name
IExtractedObjects personObjects = FieldExtractor.ExtractedObjects( "NerPerson" );
IExtractedObjects keyWordsObjects = FieldExtractor.ExtractedObjects( "keyWords" );

// Look for matching person to left of keyword
for( int i = 0; i < keyWordsObjects.Count; i++ ) {
    IExtractedObject keyWord = personObjects.Item( i );
    IInterval span = keyWord.Span;
    IExtractedObject grantor = personObjects.Find( span.StartPos, false );
    string grantorName = grantor.Value;
    if ( grantorName.Length > 2 && grantorName != "Doug Darrell" ) {
        FieldExtractor.PutSpanToField( grantor.Span, "NlpField1" );
    }
}

// Access source text
string sourceText = FieldExtractor.SourceText;

// Write any text span to field
FieldExtractor.PutTextToField( 0, sourceText.Length - 1, "NlpField2" );

// An XML query that looks for two-word dictionary phrases
string query = "<Request> " +
    "<Query>" +
    "<Contain MaxDistance=\"1\">" +
    "<Required>" +
    "<Form><Attributes><Attribute>dictionary1</Attribute></Attributes></Form>" +
    "</Required>" +
    "<Required>" +
    "<Form><Attributes><Attribute>dictionary2</Attribute></Attributes></Form>" +
    "</Required>" +
    "</Contain>" +
    "</Query>" +
    "</Request>";

// Run query, get collection of results, and save them to field
FieldExtractor.RunQueryAndSaveToField( query, "query1", "NlpField3");

// Run query and get collection of results
IExtractedObjects queryResults1 = FieldExtractor.RunQuery( query, "query2" );

// An alternative way of accessing query results after running the query
IExtractedObjects queryResults2 = FieldExtractor.QueryResults( "query2" );

// Parse the address
this.ParseAddress();

// Extract the components into separate fields
var zip = this.ExtractedObjects( "NerZipCode" );
var street = this.ExtractedObjects( "NerStreet" );

for( var i = 0; i < zip.Count; i++ ) {
    this.PutSpanToField( zip.Item(i).Span, "ZipCode" );
}

for( var j = 0; j < street.Count; j++ ) {
    this.PutSpanToField( street.Item(j).Span, "Street" );
}

// Detect all NER objects in the text of the field or section
this.ExtractNerObjects();

// Extract the Address object
var address = this.ExtractedObjects( "NerAddress" );

// Split the address into components
for( var addressSpanIndex = 0; addressSpanIndex < address.Count; addressSpanIndex++ ) {
    this.PutSpanToField( address.Item(addressSpanIndex).Span, "Address" );

    // Assign a unique prefix to the names of all component collections for the given address
    var collectionName = "nerAddress" + String(addressSpanIndex);

    // Extract the address
    this.ParseAddressInPosition( collectionName, address.Item(addressSpanIndex).Span.StartPos, address.Item(addressSpanIndex).Span.EndPos );

    // Save the components into separate fields
    var zip = this.ExtractedObjects( collectionName, "NerZipCode" );
    var street = this.ExtractedObjects( collectionName, "NerStreet" );
    RunQueryAndSaveToField
    for( var i = 0; i < zip.Count; i++ ) {
        this.PutSpanToField( zip.Item(i).Span, "ZipCode" );
    }
    for( var j = 0; j < street.Count; j++ ) {
        this.PutSpanToField( street.Item(j).Span, "Street" );
    }
}