Script - Import data from CSV file

The script can be executed from the administration scripting (or used as an automation script too) to import metadata values.

Note

• There’s a metadata CSV file with two columns, one for the document path and the other for the metadata value. The script can be easily changed to use more than two columns.
• The script searches for documents by document name. In theory there is only one document with the same name in the system; otherwise the script shows an error. Here the document path from the first CSV column could be used, but to provide a more complete sample a search engine has been used to find the document.
• For each document found, the script adds a metadata group with the CSV values.

The CSV file has two columns; the first column contains the document path and the second column has the metadata value.

Download the CSV sample file csv_metadata.zip.

The metadata group definition:

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE property-groups PUBLIC "-//OpenKM//DTD Property Groups 3.10//EN"
"http://www.openkm.com/dtd/property-groups-3.10.dtd">
<property-groups>
    <property-group label="Metadata" name="okg:metadata">
        <input label="Document ID" name="okp:metadata.value" type="text"/>
    </property-group>
</property-groups>

The script:

import java.io.FileReader;
import java.io.Reader;
import java.util.Collection;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;

import com.googlecode.jcsv.CSVStrategy;
import com.googlecode.jcsv.reader.CSVReader;
import com.googlecode.jcsv.reader.internal.CSVReaderBuilder;
import com.googlecode.jcsv.reader.internal.DefaultCSVEntryParser;
import com.openkm.api.OKMDocument;
import com.openkm.api.OKMPropertyGroup;
import com.openkm.api.OKMSearch;
import com.openkm.bean.Document;
import com.openkm.bean.QueryResult;
import com.openkm.db.bean.QueryParams;
import com.openkm.util.ContextWrapper;
import com.openkm.util.PathUtils;

String grpName = "okg:metadata";
String FILE_LOG_NAME = "CSVLOG";
String META_PATH = "/home/openkm/csv/";
String META_FILE_NAME = "metadata.csv";
int uniqueFileName = 0;
int valueColumn = 1;

// Format defintion
char delimiter = ',';
char quoteCharacter = '"';
char commentIndicator = '#';
boolean skipHeader = false;
boolean ignoreEmptyLines = true;
CSVStrategy strategy = new CSVStrategy(delimiter, quoteCharacter, commentIndicator, skipHeader, ignoreEmptyLines);
// File reader
Reader reader = new FileReader(META_PATH + META_FILE_NAME);
// CSV reader
CSVReader csvParser = new CSVReaderBuilder(reader).strategy(strategy).entryParser(new DefaultCSVEntryParser()).build();
List data = csvParser.readAll();
int count = 0;
int countFound = 0;
int countNotDocument = 0;
int moreThanOneDocumentFound = 0;
int notFound = 0;
int noName = 0;

OKMSearch okmSearch = ContextWrapper.getContext().getBean(OKMSearch.class);
OKMPropertyGroup okmPropertyGroup = ContextWrapper.getContext().getBean(OKMPropertyGroup.class);
PathUtils pathUtils = ContextWrapper.getContext().getBean(PathUtils.class);

for (int i = 0; i < data.size(); i++) {
    String[] row = (String[]) data.get(i);
    String docPath = row[uniqueFileName];
    print(count + ">>>> " + docPath);

    if (docPath != null && !docPath.equals("")) {
        QueryParams queryParams = new QueryParams();
        queryParams.setDomain(QueryParams.DOCUMENT);
        queryParams.setName(pathUtils.getName(docPath));
        Collection results = okmSearch.find(null, queryParams);

        if (results.size() == 1) {
            QueryResult queryResult = (QueryResult) results.iterator().next();
            if (queryResult.getNode() != null && queryResult.getNode() instanceof Document) {
                print("found");
                countFound++;

                Map properties = new HashMap();
                properties.put("okp:metadata.value", row[valueColumn]);

                // Add Group and metadata
                okmPropertyGroup.addGroup(null, docPath, grpName, properties);
            } else {
                print("error is not document");
                countNotDocument++;
            }
        } else if (results.size() > 1) {
            print("error more than one document found can not decide");
            moreThanOneDocumentFound++;
        } else {
            print("not found");
            notFound++;
        }
    } else {
        print("error document has no name");
        noName++;
    }

    print("</br>");

    count++;
}

print("Total:" + count + "</br>");
print("Found:" + countFound + "</br>");
print("Error not document:" + countNotDocument + "</br>");
print("Error more then one document found:" + moreThanOneDocumentFound + "</br>");
print("Error not found:" + notFound + "</br>");
print("Error name empty:" + notFound + "</br>");

Image

Register the metadata group

Repository view

Execution

Script results

Imported metadata