这里分类和汇总了欣宸的全部原创(含配套源码):https://github.com/zq2599/blog_demos
create table address (addressid int, province string, city string)
row format delimited
fields terminated by ',';
1,guangdong,guangzhou
2,guangdong,shenzhen
3,shanxi,xian
4,shanxi,hanzhong
6,jiangshu,nanjing
load data
local inpath '/home/hadoop/temp/202010/25/address.txt'
into table address;
create table student (name string, age int, addressid int)
row format delimited
fields terminated by ',';
tom,11,1
jerry,12,2
mike,13,3
john,14,4
mary,15,5
load data
local inpath '/home/hadoop/temp/202010/25/student.txt'
into table student;
hive> select * from address;
OK
1 guangdong guangzhou
2 guangdong shenzhen
3 shanxi xian
4 shanxi hanzhong
6 jiangshu nanjing
Time taken: 0.043 seconds, Fetched: 5 row(s)
hive> select * from student;
OK
tom 11 1
jerry 12 2
mike 13 3
john 14 4
mary 15 5
Time taken: 0.068 seconds, Fetched: 5 row(s)
hive> show functions;
OK
!
!=
%
&
*
+
-
/
<
<=
<=>
<>
=
==
>
>=
^
abs
acos
add_months
and
array
array_contains
ascii
asin
assert_true
atan
avg
base64
between
bin
case
cbrt
ceil
ceiling
coalesce
collect_list
collect_set
compute_stats
concat
concat_ws
context_ngrams
conv
corr
cos
count
covar_pop
covar_samp
create_union
cume_dist
current_database
current_date
current_timestamp
current_user
date_add
date_format
date_sub
datediff
day
dayofmonth
decode
degrees
dense_rank
div
e
elt
encode
ewah_bitmap
ewah_bitmap_and
ewah_bitmap_empty
ewah_bitmap_or
exp
explode
factorial
field
find_in_set
first_value
floor
format_number
from_unixtime
from_utc_timestamp
get_json_object
greatest
hash
hex
histogram_numeric
hour
if
in
in_file
index
initcap
inline
instr
isnotnull
isnull
java_method
json_tuple
lag
last_day
last_value
lcase
lead
least
length
levenshtein
like
ln
locate
log
log10
log2
lower
lpad
ltrim
map
map_keys
map_values
matchpath
max
min
minute
month
months_between
named_struct
negative
next_day
ngrams
noop
noopstreaming
noopwithmap
noopwithmapstreaming
not
ntile
nvl
or
parse_url
parse_url_tuple
percent_rank
percentile
percentile_approx
pi
pmod
posexplode
positive
pow
power
printf
radians
rand
rank
reflect
reflect2
regexp
regexp_extract
regexp_replace
repeat
reverse
rlike
round
row_number
rpad
rtrim
second
sentences
shiftleft
shiftright
shiftrightunsigned
sign
sin
size
sort_array
soundex
space
split
sqrt
stack
std
stddev
stddev_pop
stddev_samp
str_to_map
struct
substr
substring
sum
tan
to_date
to_unix_timestamp
to_utc_timestamp
translate
trim
trunc
ucase
unbase64
unhex
unix_timestamp
upper
var_pop
var_samp
variance
weekofyear
when
windowingtablefunction
xpath
xpath_boolean
xpath_double
xpath_float
xpath_int
xpath_long
xpath_number
xpath_short
xpath_string
year
|
~
Time taken: 0.003 seconds, Fetched: 216 row(s)
hive> describe function lower;
OK
lower(str) - Returns str with all characters changed to lowercase
Time taken: 0.005 seconds, Fetched: 1 row(s)
set hive.cli.print.header=true;
hive> select name, age, age+1 as add_value from student;
OK
name age add_value
tom 11 12
jerry 12 13
mike 13 14
john 14 15
mary 15 16
Time taken: 0.098 seconds, Fetched: 5 row(s)
hive> select round(1.1), round(1.6);
OK
_c0 _c1
1.0 2.0
Time taken: 0.028 seconds, Fetched: 1 row(s)
hive> select ceil(1.1);
OK
_c0
2
Time taken: 0.024 seconds, Fetched: 1 row(s)
hive> select floor(1.1);
OK
_c0
1
Time taken: 0.024 seconds, Fetched: 1 row(s)
hive> select pmod(10,3);
OK
_c0
1
Time taken: 0.059 seconds, Fetched: 1 row(s)
hive> select lower(name), upper(name) from student;
OK
_c0 _c1
tom TOM
jerry JERRY
mike MIKE
john JOHN
mary MARY
Time taken: 0.051 seconds, Fetched: 5 row(s)
hive> select name, length(name) from student;
OK
tom 3
jerry 5
mike 4
john 4
mary 4
Time taken: 0.322 seconds, Fetched: 5 row(s)
hive> select concat("prefix_", name) from student;
OK
prefix_tom
prefix_jerry
prefix_mike
prefix_john
prefix_mary
Time taken: 0.106 seconds, Fetched: 5 row(s)
hive> select substr("0123456",2);
OK
123456
Time taken: 0.067 seconds, Fetched: 1 row(s)
hive> select substr("0123456",2,3);
OK
123
Time taken: 0.08 seconds, Fetched: 1 row(s)
hive> select trim(" 123 ");
OK
123
Time taken: 0.065 seconds, Fetched: 1 row(s)
为了使用json处理的函数,先准备一些数据:
create table t15(json_raw string)
row format delimited;
{"name":"tom","age":"10"}
{"name":"jerry","age":"11"}
load data
local inpath '/home/hadoop/temp/202010/25/015.txt'
into table t15;
select
get_json_object(json_raw, "$.name"),
get_json_object(json_raw, "$.age")
from t15;
得到结果:
hive> select
> get_json_object(json_raw, "$.name"),
> get_json_object(json_raw, "$.age")
> from t15;
OK
tom 10
jerry 11
Time taken: 0.081 seconds, Fetched: 2 row(s)
hive> select current_date();
OK
2020-11-02
Time taken: 0.052 seconds, Fetched: 1 row(s)
hive> select current_timestamp();
OK
2020-11-02 10:07:58.967
Time taken: 0.049 seconds, Fetched: 1 row(s)
hive> select year(current_date()), month(current_date()), day(current_date());
OK
2020 11 2
Time taken: 0.054 seconds, Fetched: 1 row(s)
hive> select year(current_timestamp()), month(current_timestamp()), day(current_timestamp());
OK
2020 11 2
Time taken: 0.042 seconds, Fetched: 1 row(s)
hive> select to_date(current_timestamp());
OK
2020-11-02
Time taken: 0.051 seconds, Fetched: 1 row(s)
select name,
case name when 'tom' then 'tom_case'
when 'jerry' then 'jerry_case'
else 'other_case'
end
from student;
结果如下:
hive> select name,
> case name when 'tom' then 'tom_case'
> when 'jerry' then 'jerry_case'
> else 'other_case'
> end
> from student;
OK
tom tom_case
jerry jerry_case
mike other_case
john other_case
mary other_case
Time taken: 0.08 seconds, Fetched: 5 row(s)
select count(*) from student;
触发MR,结果如下:
Total MapReduce CPU Time Spent: 2 seconds 170 msec
OK
5
Time taken: 20.823 seconds, Fetched: 1 row(s)
select province, sum(1) from address group by province;
触发MR,结果如下:
Total MapReduce CPU Time Spent: 1 seconds 870 msec
OK
guangdong 2
jiangshu 1
shanxi 2
Time taken: 19.524 seconds, Fetched: 3 row(s)
select province, min(addressid), max(addressid), avg(addressid) from address group by province;
触发MR,结果如下:
Total MapReduce CPU Time Spent: 1 seconds 650 msec
OK
guangdong 1 2 1.5
jiangshu 6 6 6.0
shanxi 3 4 3.5
Time taken: 20.106 seconds, Fetched: 3 row(s)
如果您不想自己搭建kubernetes环境,推荐使用腾讯云容器服务TKE:无需自建,即可在腾讯云上使用稳定, 安全,高效,灵活扩展的 Kubernetes 容器平台;
如果您希望自己的镜像可以通过外网上传和下载,推荐腾讯云容器镜像服务TCR:像数据加密存储,大镜像多节点快速分发,跨地域镜像同步
微信搜索「程序员欣宸」,我是欣宸,期待与您一同畅游Java世界...
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。
原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。
如有侵权,请联系 cloudcommunity@tencent.com 删除。