mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-19 22:22:00 +00:00
d91c97d15d
* Replace underscores with hyphens * remove temporary code * fix style check * fix collapse
36 lines
1.4 KiB
Markdown
36 lines
1.4 KiB
Markdown
---
|
||
machine_translated: true
|
||
machine_translated_rev: e8cd92bba3269f47787db090899f7c242adf7818
|
||
toc_priority: 18
|
||
toc_title: WikiStat
|
||
---
|
||
|
||
# WikiStat {#wikistat}
|
||
|
||
Bakınız: http://dumps.wikimedia.org/other/pagecounts-raw/
|
||
|
||
Tablo oluşturma:
|
||
|
||
``` sql
|
||
CREATE TABLE wikistat
|
||
(
|
||
date Date,
|
||
time DateTime,
|
||
project String,
|
||
subproject String,
|
||
path String,
|
||
hits UInt64,
|
||
size UInt64
|
||
) ENGINE = MergeTree(date, (path, time), 8192);
|
||
```
|
||
|
||
Veri yükleme:
|
||
|
||
``` bash
|
||
$ for i in {2007..2016}; do for j in {01..12}; do echo $i-$j >&2; curl -sSL "http://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 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
|
||
$ 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
|
||
```
|
||
|
||
[Orijinal makale](https://clickhouse.tech/docs/en/getting_started/example_datasets/wikistat/) <!--hide-->
|