hive UDF实现一个字符串解码函数
其实hive的udf 是比较容易实现的，只需要继承UDF,实现其evaluate（）方法，代码如下。
@Description(name = "decoder_url", value = "_FUNC_(url [,code][,count]) - decoder a URL from a String for count times using code as encoding scheme ", extended = "" + "if count is not given ,the url will be decoderd for 2 time," + "if code is not given ,GBK is used")public class UDFDecoderUrl extends UDF { private String url = null; private int times = 2; private String code = "GBK"; public UDFDecoderUrl() { } public String evaluate(String urlStr, String srcCode, int count) { if (urlStr == null) { return null; } if (count <= 0) { return urlStr; } if (srcCode != null) { code = srcCode; } url = urlStr; times = count; for (int i = 0; i < times; i++) { url = decoder(url, code); } return url; } public String evaluate(String urlStr, String srcCode) { if (urlStr == null) { return null; } url = urlStr; code = srcCode; return evaluate(url, code,times); } public String evaluate(String urlStr, int count) { if (urlStr == null) { return null; } if (count <= 0) { return urlStr; } url = urlStr; times = count; return evaluate(url, code,times); } public String evaluate(String urlStr) { if (urlStr == null) { return null; } url = urlStr; return evaluate(url, code,times); } private String decoder(String urlStr, String code) { if (urlStr == null || code == null) { return null; } try { urlStr = URLDecoder.decode(urlStr, code); } catch (Exception e) { return null; } return urlStr; }}在类中org.apache.hadoop.hive.ql.exec.FunctionRegistry中添加
registerUDF("decoder_url", UDFDecoderUrl.class, false);
编译hive ,或者通过配置文件方式，让其读取，以后新加的函数配置到配置文件中一劳永逸。
上面的类UDFDecoderUrl需要打成jar包加载到hive中，需要再hive-site.xml配置如下加载jar包
<property>
<name>hive.aux.jars.path</name>
<value>file:///opt/hive/sohu/hive-udf-0.0.1.jar</value>
<description>These JAR file are available to all users for all jobs</description>
</property>