导入MapReduce结果到hive中

set hive.cli.print.header=true;

use hive;

# 临时表是不带id的表
CREATE TABLE tmp (
  name STRING,
  count INT
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY '\t'
LINES TERMINATED BY '\n'
NULL DEFINED AS '';

# 然后导入数据
# '/output/part-r-00000' 路径是 mapreduce 的结果文件
LOAD DATA INPATH '/output/part-r-00000' INTO TABLE tmp;

# result 表包含 id 字段
CREATE TABLE result (
  id INT,
  name STRING,
  count INT
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
LINES TERMINATED BY '\n';

# 拷贝 tmp 表到 result 表并添加行号为 id
INSERT INTO TABLE result
SELECT ROW_NUMBER() OVER (), name, count
FROM tmp;

# 查看结果
SELECT * FROM result;

DROP TABLE tmp;