create table ods_weblog_origin(
valid string,
remote_addr string,
remote_user string,
time_local string,
request string,
status string,
body_bytes_sent string,
http_referer string,
http_user_agent string)
partitioned by (datestr string)
row format delimited fields terminated by '\001';
create table ods_click_pageviews(
session string,
remote_addr string,
remote_user string,
time_local string,
request string,
visit_step string,
page_staylong string,
http_referer string,
http_user_agent string,
body_bytes_sent string,
status string)
partitioned by (datestr string)
row format delimited fields terminated by '\001';
create table ods_click_stream_visit(
session string,
remote_addr string,
inTime string,
outTime string,
inPage string,
outPage string,
referal string,
pageVisits int)
partitioned by (datestr string)
row format delimited fields terminated by '\001';
create table t_dim_time(
date_key int,
year string,
month string,
day string,
hour string)
row format delimited fields terminated by ',';
（宽表：对'ods_weblog_origin'表中的'url'字段进行拓宽，和访问日期进行拓宽）
对url解析用到了lateral view , 对字段rul拓宽 拆分，用到了 parse_url_tuple() 字段, regexp_replace 替换格式是：(str,regexp,rep),把"" 替换成空，因为parse_url_tuple() 字段
只解析url，在这个日志中用到了"",所以要把"" 替换成空。 substring 和 sunstr 都能对字符串进行截取。
parse_url_tuple()字段 的详细解析
+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--+
| parse_url_tuple(url, partname1, partname2, ..., partnameN) - extracts N (N>=1) parts from a URL. |
| It takes a URL and one or multiple partnames, and returns a tuple. All the input parameters and output column types are string. |
| Partname: HOST, PATH, QUERY, REF, PROTOCOL, AUTHORITY, FILE, USERINFO, QUERY:<KEY_NAME> |
