3.4-3.6 Hive Storage Format

file_format:
  : SEQUENCEFILE
  | TEXTFILE    -- (Default, depending on hive.default.fileformat configuration)
  | RCFILE      -- (Note: Available in Hive 0.6.0 and later)
  | ORC         -- (Note: Available in Hive 0.11.0 and later)
  | PARQUET     -- (Note: Available in Hive 0.13.0 and later)
  | AVRO        -- (Note: Available in Hive 0.14.0 and later)
  | JSONFILE    -- (Note: Available in Hive 4.0.0 and later)
  | INPUTFORMAT input_format_classname OUTPUTFORMAT output_format_classname



数据存储：
    按行存储
    按列存储


#TEXTFILE ：行式存储
#其他的都是列存储，ORC是对RCFILE的优化；ORC和PARQUET用的较多；

#建表
hive (default)> create table page_views(
              > track_time string, 
              > url string, 
              > session_id string, 
              > referer string, 
              > ip string, 
              > end_user_id string, 
              > city_id string
              > ) 
              > ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t‘
              > STORED AS TEXTFILE;
OK
Time taken: 0.089 seconds


#加载数据
hive (default)> load data local inpath ‘/opt/datas/page_views.data‘ into table page_views;
Copying data from file:/opt/datas/page_views.data
Copying file: file:/opt/datas/page_views.data
Loading data to table default.page_views
Table default.page_views stats: [numFiles=1, numRows=0, totalSize=19014993, rawDataSize=0]
OK
Time taken: 0.326 seconds

hive (default)> create table page_views_orc(
              > track_time string, 
              > url string, 
              > session_id string, 
              > referer string, 
              > ip string, 
              > end_user_id string, 
              > city_id string
              > ) 
              > ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t‘
              > STORED AS orc;
OK
Time taken: 0.04 seconds

hive (default)> insert into table page_views_orc select * from page_views;

hive (default)> create table page_views_parquet(
              > track_time string, 
              > url string, 
              > session_id string, 
              > referer string, 
              > ip string, 
              > end_user_id string, 
              > city_id string
              > ) 
              > ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t‘
              > STORED AS parquet;
OK
Time taken: 0.037 seconds

hive (default)> insert into table page_views_parquet select * from page_views;

hive (default)> dfs -du -h /user/hive/warehouse/page_views/;
18.1 M  /user/hive/warehouse/page_views/page_views.data

hive (default)> dfs -du -h /user/hive/warehouse/page_views_orc/;              
2.6 M  /user/hive/warehouse/page_views_orc/000000_0

hive (default)> dfs -du -h /user/hive/warehouse/page_views_parquet/;
13.1 M  /user/hive/warehouse/page_views_parquet/000000_0


#明显的可以看出，数据相同时，存储为不同的格式：
TEXTFILE格式的表：18.1M
ORCFILE格式的表：2.6M
PARQUET格式的表：13.1M

#TEXTFILE表查询
hive (default)> select session_id, count(*) cnt from page_views group by session_id order by cnt desc limit 30;
......
Time taken: 39.427 seconds, Fetched: 30 row(s)        #39.427秒


#ORCFILE表查询
hive (default)> select session_id, count(*) cnt from page_views_orc group by session_id order by cnt desc limit 30;
......
Time taken: 38.319 seconds, Fetched: 30 row(s)        #38.319秒


#可见orc格式的表，不仅数据体积小很多，查询也有优势

#建表
hive (default)> create table page_views_orc_snappy(
              > track_time string, 
              > url string, 
              > session_id string, 
              > referer string, 
              > ip string, 
              > end_user_id string, 
              > city_id string
              > ) 
              > ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\t‘
              > STORED AS orc tblproperties ("orc.compress"="SNAPPY");
OK
Time taken: 0.033 seconds

#插入数据
hive (default)> insert into table page_views_orc_snappy select * from page_views;

#查询
hive (default)> dfs -du -h /user/hive/warehouse/page_views_orc_snappy/;
3.8 M  /user/hive/warehouse/page_views_orc_snappy/000000_0


#此时发现，用snappy压缩完，数据反而比orcfile表数据还大了，怎么回事呢？
因为建ORCFILE表时，不指定压缩，默认使用ZLIB压缩，但是指定了snappy压缩就会使用snappy，
而且ZLIB的压缩比大于snappy，所以此时的snappy压缩稍微大一些；

在实际的项目开发当中，hive表的数据
    *存储格式I orcfile/qarquet    #推荐
    *数据压缩
        snappy        #推荐