カスタムマッチングアルゴリズムの作成

package org.talend.mydistance;

import org.talend.dataquality.record.linkage.attribute.AbstractAttributeMatcher;
import org.talend.dataquality.record.linkage.constant.AttributeMatcherType;

/**
 * @author scorreia
 * 
 * Example of Matching distance.
 */
public class MyDistance extends AbstractAttributeMatcher {

    /*
     * (non-Javadoc)
     * 
     * @see org.talend.dataquality.record.linkage.attribute.IAttributeMatcher#getMatchType()
     */
    @Override
    public AttributeMatcherType getMatchType() {
        // a custom implementation should return this type AttributeMatcherType.custom
        return AttributeMatcherType.CUSTOM;
    }

    /*
     * (non-Javadoc)
     * 
     * @see org.talend.dataquality.record.linkage.attribute.IAttributeMatcher#getMatchingWeight(java.lang.String,
     * java.lang.String)
     */
    @Override
    public double getWeight(String arg0, String arg1) {
        // Here goes the custom implementation of the matching distance between the two given strings.
        // the algorithm should return a value between 0 and 1.

        // in this example, we consider that 2 strings match if their first 4 characters are identical
        // the arguments are not null (the check for nullity is done by the caller)
        int MAX_CHAR = 4;
        final int max = Math.min(MAX_CHAR, Math.min(arg0.length(), arg1.length()));
        int nbIdenticalChar = 0;
        for (; nbIdenticalChar < max; nbIdenticalChar++) {
            if (arg0.charAt(nbIdenticalChar) != arg1.charAt(nbIdenticalChar)) {
                break;
            }
        }
        if (arg0.length() < MAX_CHAR && arg1.length() < MAX_CHAR) {
            MAX_CHAR = Math.max(arg0.length(), arg1.length());
        }
        return (nbIdenticalChar) / ((double) MAX_CHAR);
}

        int MAX_CHAR = 4;
        final int max = Math.min(MAX_CHAR, Math.min(arg0.length(), arg1.length()));
        int nbIdenticalChar = 0;
        for (; nbIdenticalChar < max; nbIdenticalChar++) {
            if (arg0.charAt(nbIdenticalChar) != arg1.charAt(nbIdenticalChar)) {
                break;
            }
        }
        if (arg0.length() < MAX_CHAR && arg1.length() < MAX_CHAR) {
            MAX_CHAR = Math.max(arg0.length(), arg1.length());
        }
        return (nbIdenticalChar) / ((double) MAX_CHAR);