source: vlo/trunk/vlo-importer/src/main/java/eu/clarin/cmdi/vlo/importer/OrganisationPostProcessor.java @ 6811

Last change on this file since 6811 was 6811, checked in by davor.ostojic@oeaw.ac.at, 9 years ago

#773 Building uniform mapping file format for PostProcessing?

File size: 1.3 KB
Line 
1package eu.clarin.cmdi.vlo.importer;
2
3import java.util.Arrays;
4import java.util.List;
5
6public class OrganisationPostProcessor extends PostProcessorsWithControlledVocabulary{
7         
8    /**
9     * Splits values for organisation facet at delimiter ';' and replaces
10     * organisation name variants with their official name from a controlled
11     * vocabulary
12     *
13     * @param value extracted organisation name/names
14     * @return List of organisation names (splitted at semicolon) and variations
15     * replaced with controlled vocabulary
16     */
17    @Override
18    public List<String> process(String value) {
19        String[] splitArray = normalizeInputString(value).split(";");
20        for (int i = 0; i < splitArray.length; i++) {
21                String normalizedVal = normalize(splitArray[i], null);
22                if(normalizedVal != null)
23                splitArray[i] = normalizedVal;
24        }
25       
26        return Arrays.asList(splitArray);
27    }
28   
29        @Override
30        public String getNormalizationMapURL() {
31                return MetadataImporter.config.getOrganisationNamesUrl();
32        }
33   
34    private String normalizeInputString(String value) {
35        return value.replaceAll("\\s+", " ");
36    }
37   
38    private String normalizeVariant(String key) {
39        return key.toLowerCase().replaceAll("-", " ");
40    }
41
42
43       
44   
45   
46}
Note: See TracBrowser for help on using the repository browser.