Hive 体系结构介绍

    CREATE TABLE base64_test(col1 STRING, col2 STRING)
    STORED AS
    INPUTFORMAT ‘org.apache.hadoop.hive.contrib.
    fileformat.base64.Base64TextInputFormat‘
    OUTPUTFORMAT ‘org.apache.hadoop.hive.contrib.
    fileformat.base64.Base64TextOutputFormat‘;

    CREATE TABLE mythrift_table
    ROW FORMAT SERDE
    ‘org.apache.hadoop.hive.contrib.serde2.thrift.ThriftSerDe‘
    WITH SERDEPROPERTIES (
    "serialization.class" = "com.facebook.serde.tprofiles.full",
    "serialization.format" = "com.facebook.thrift.protocol.TBinaryProtocol";);

    FROM (
    SELECT TRANSFORM(user_id, page_url, unix_time)
    USING ‘page_url_to_id.py‘
    AS (user_id, page_id, unix_time)
    FROM mylog
    DISTRIBUTE BY user_id
    SORT BY user_id, unix_time)
    mylog2
    SELECT TRANSFORM(user_id, page_id, unix_time)
    USING ‘my_python_session_cutter.py‘ AS (user_id, session_info);

<P>[sql]</P>
<P>add jar build/ql/test/test-udfs.jar;
CREATE TEMPORARY FUNCTION testlength
AS ‘org.apache.hadoop.hive.ql.udf.UDFTestLength‘;

SELECT testlength(src.value) FROM src;

DROP TEMPORARY FUNCTION testlength;</P>

 1     public class UDAFCount extends UDAF {
 2     public static class Evaluator implements UDAFEvaluator {
 3     private int mCount;
 4 
 5     public void init() {
 6     mcount = 0;
 7     }
 8 
 9     public boolean iterate(Object o) {
10     if (o!=null)
11     mCount++;
12 
13     return true;
14     }
15 
16     public Integer terminatePartial() {
17     return mCount;
18     }
19 
20     public boolean merge(Integer o) {
21     mCount += o;
22     return true;
23     }
24 
25     public Integer terminate() {
26     return mCount;
27     }
28     }