-- 单字符分隔符
create table t1
(
a int,
b string
)
row format delimited
fields terminated by ',';
-- 单字符分隔符、跳过首行
create table t1
(
a int,
b string
)
row format delimited
fields terminated by ','
SKIP_HEADER=TRUE;
-- 单字符分隔符、跳过第1行
create table t1
(
a int,
b string
)
row format delimited
fields terminated by ','
SKIP_HEADER=TRUE
tblproperties("skip.header.line.count"="1");
-- 单字符分隔符、双引号括起来
CREATE TABLE t1
(
a int,
b string
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
ESCAPED BY '"';
CREATE TABLE t1
(
a int,
b string
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
WITH SERDEPROPERTIES (
"separatorChar" = ",",
"quoteChar" = "\""
);
-- 多字符分隔符
create external table test02
(
a int,
b string
)
row format serde
'org.apache.hadoop.hive.contrib.serde2.MultiDelimitSerDe'
with serdeproperties ("field.delim"=",,");
-- 正则表达式分隔符
create external table test03
(
a int,
b string
)
ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'
WITH SERDEPROPERTIES ("input.regex" = "([^ ,]+),+([^ ,]+),,([^ ,]+)");
-- 指定文件格式
create table t1
(
a int,
b string
)
stored as textfile|sequencefile|rcfile|orc|parquet;
-- 指定文件路径
create table t1
(
a int,
b string
)
row format delimited
fields terminated by ','
location '/hivedatatest/t1.csv';
-- 外部表
create EXTERNAL table t1
(
a int,
b string
)
row format delimited
fields terminated by ','
location '/hivedatatest/t1.csv';
-- 分区表
create EXTERNAL table t1
(
a int,
b string
)
PARTITIONED BY (filedate string);
-- 增量load数据
LOAD DATA INPATH '/user/test1.csv' INTO TABLE t1
-- 覆盖load数据
LOAD DATA INPATH '/user/test1.csv' OVERWRITE INTO TABLE t1