thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-10 01:25:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added instruction to load wikistat data [#METR-20000].

Browse Source
This commit is contained in:
Alexey Milovidov 2016-03-21 07:48:18 +03:00
parent 8f423c0e57
commit 227c7fcdcc
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
doc/example_datasets/wikistat.txt
View File

@ -4,3 +4,15 @@ for i in {2007..2016}; do for j in {01..12}; do echo $i-$j >&2; curl -sS "http:/
cat links.txt | while read link; do wget http://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
CREATE TABLE wikistat
(
date Date,
time DateTime,
project String,
subproject String,
path String,
hits UInt64,
size UInt64
) ENGINE = MergeTree(date, (path, time), 8192);
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