mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-20 14:42:02 +00:00
28 lines
1.2 KiB
ReStructuredText
28 lines
1.2 KiB
ReStructuredText
WikiStat
|
|
========
|
|
|
|
See: https://dumps.wikimedia.org/other/pagecounts-raw/
|
|
|
|
Create table:
|
|
|
|
.. code-block:: sql
|
|
|
|
CREATE TABLE wikistat
|
|
(
|
|
date Date,
|
|
time DateTime,
|
|
project String,
|
|
subproject String,
|
|
path String,
|
|
hits UInt64,
|
|
size UInt64
|
|
) ENGINE = MergeTree(date, (path, time), 8192);
|
|
|
|
Load data:
|
|
|
|
.. code-block:: bash
|
|
|
|
for i in {2007..2016}; do for j in {01..12}; do echo $i-$j >&2; curl -sSL "https://dumps.wikimedia.org/other/pagecounts-raw/$i/$i-$j/" | grep -oE 'pagecounts-[0-9]+-[0-9]+\.gz'; done; done | sort | uniq | tee links.txt
|
|
cat links.txt | while read link; do wget https://dumps.wikimedia.org/other/pagecounts-raw/$(echo $link | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})[0-9]{2}-[0-9]+\.gz/\1/')/$(echo $link | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})[0-9]{2}-[0-9]+\.gz/\1-\2/')/$link; done
|
|
ls -1 /opt/wikistat/ | grep gz | while read i; do echo $i; gzip -cd /opt/wikistat/$i | ./wikistat-loader --time="$(echo -n $i | sed -r 's/pagecounts-([0-9]{4})([0-9]{2})([0-9]{2})-([0-9]{2})([0-9]{2})([0-9]{2})\.gz/\1-\2-\3 \4-00-00/')" | clickhouse-client --query="INSERT INTO wikistat FORMAT TabSeparated"; done
|