forked from D-Net/dnet-hadoop
26 lines
488 B
Java
26 lines
488 B
Java
|
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
|
|
|
import java.util.regex.Matcher;
|
|
import java.util.regex.Pattern;
|
|
|
|
// https://researchguides.stevens.edu/c.php?g=442331&p=6577176
|
|
public class PmidCleaningRule {
|
|
|
|
public static final Pattern PATTERN = Pattern.compile("0*(\\d{1,8})");
|
|
|
|
public static String clean(String pmid) {
|
|
String s = pmid
|
|
.toLowerCase()
|
|
.replaceAll("\\s", "");
|
|
|
|
final Matcher m = PATTERN.matcher(s);
|
|
|
|
if (m.find()) {
|
|
return m.group(1);
|
|
}
|
|
return "";
|
|
}
|
|
|
|
}
|