[cloudera@quickstart ~]$ sqoop import-all-tables \

>     -m 1 \

>     --connect jdbc:mysql://quickstart:3306/retail_db \

>     --username=retail_dba \

>     --password=cloudera \

>     --compression-codec=snappy \

>     --as-parquetfile \

>     --warehouse-dir=/user/hive/warehouse \

>     --hive-import

Warning: /usr/lib/sqoop/../accumulo does not exist! Accumulo imports will fail.

Please set $ACCUMULO_HOME to the root of your Accumulo installation.

19/04/29 18:31:46 INFO sqoop.Sqoop: Running Sqoop version: 1.4.6-cdh5.13.0

19/04/29 18:31:46 WARN tool.BaseSqoopTool: Setting your password on the command-line is insecure. Consider using -P instead.

19/04/29 18:31:46 INFO tool.BaseSqoopTool: Using Hive-specific delimiters for output. You can override

19/04/29 18:31:46 INFO tool.BaseSqoopTool: delimiters with --fields-terminated-by, etc.

19/04/29 18:31:46 WARN tool.BaseSqoopTool: It seems that you're doing hive import directly into default

(many more lines suppressed)

                Failed Shuffles=0

                Merged Map outputs=0

                GC time elapsed (ms)=87

                CPU time spent (ms)=3690

                Physical memory (bytes) snapshot=443174912

                Virtual memory (bytes) snapshot=1616969728

                Total committed heap usage (bytes)=352845824

        File Input Format Counters

                Bytes Read=0

        File Output Format Counters

                Bytes Written=0

19/04/29 18:38:27 INFO mapreduce.ImportJobBase: Transferred 46.1328 KB in 85.1717 seconds (554.6442 bytes/sec)

19/04/29 18:38:27 INFO mapreduce.ImportJobBase: Retrieved 1345 records.

[cloudera@quickstart ~]$ hadoop fs -ls /user/hive/warehouse/

Found 6 items

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:32 /user/hive/warehouse/categories

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:33 /user/hive/warehouse/customers

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:34 /user/hive/warehouse/departments

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:35 /user/hive/warehouse/order_items

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:36 /user/hive/warehouse/orders

drwxrwxrwx   - cloudera supergroup          0 2019-04-29 18:38 /user/hive/warehouse/products

[cloudera@quickstart ~]$ hadoop fs -ls /user/hive/warehouse/categories/

Found 3 items

drwxr-xr-x   - cloudera supergroup          0 2019-04-29 18:31 /user/hive/warehouse/categories/.metadata

drwxr-xr-x   - cloudera supergroup          0 2019-04-29 18:32 /user/hive/warehouse/categories/.signals

-rw-r--r--   1 cloudera supergroup       1957 2019-04-29 18:32 /user/hive/warehouse/categories/6e701a22-4f74-4623-abd1-965077105fd3.parquet

[cloudera@quickstart ~]$

CREATE EXTERNAL TABLE intermediate_access_logs (

    ip STRING,

    date STRING,

    method STRING,

    url STRING,

    http_version STRING,

    code1 STRING,

    code2 STRING,

    dash STRING,

    user_agent STRING)

ROW FORMAT SERDE 'org.apache.hadoop.hive.contrib.serde2.RegexSerDe'

WITH SERDEPROPERTIES (

    'input.regex' = '([^ ]*) - - \\[([^\\]]*)\\] "([^\ ]*) ([^\ ]*) ([^\ ]*)" (\\d*) (\\d*) "([^"]*)" "([^"]*)"',

    'output.format.string' = "%1$$s %2$$s %3$$s %4$$s %5$$s %6$$s %7$$s %8$$s %9$$s")

LOCATION '/user/hive/warehouse/original_access_logs';

CREATE EXTERNAL TABLE tokenized_access_logs (

    ip STRING,

    date STRING,

    method STRING,

    url STRING,

    http_version STRING,

    code1 STRING,

    code2 STRING,

    dash STRING,

    user_agent STRING)

ROW FORMAT DELIMITED FIELDS TERMINATED BY ','

LOCATION '/user/hive/warehouse/tokenized_access_logs';

ADD JAR /usr/lib/hive/lib/hive-contrib.jar;

INSERT OVERWRITE TABLE tokenized_access_logs SELECT * FROM intermediate_access_logs;