统计关键词

import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.hadoop.hive.ql.exec.UDF;

public class GroupByUrl extends UDF {
	public String evaluate(String url) {
		String result;
		if (url.contains("utm_source=baidu")) {
			result = "baidu";

		} else if (url.contains("utm_source=360")) {
			result = "360";

		} else if (url.contains("utm_source=sogou")) {
			result = "sogou";

		} else if (url.contains("utm_source=bdpzpc")) {
			result = "bdpzpc";

		} else if (!url.contains("utm_source")) {
			result = "self";

		} else {
			result = "none";

		}

		String regEx = "(utm_term=.*)\\&|(utm_term=.*)$";
		Pattern pattern = Pattern.compile(regEx);

		Matcher m = pattern.matcher(url);

		String rslt = "";

		if (m.find()) {
			rslt = m.group();
			rslt = rslt.split("=")[1];
			if (!rslt.trim().equals("") && rslt.charAt(rslt.length() - 1) == '&') {
				rslt = rslt.substring(0, rslt.length() - 1);
			}
		}

		return result + " " + rslt;
	}
}