Replace old docs with symlinks

This commit is contained in:
Alexey Milovidov 2023-08-08 22:38:52 +02:00
parent 98a2a117c2
commit 1ab99e5fdd
3 changed files with 2 additions and 65 deletions

View File

@ -1,32 +0,0 @@
---
slug: /ru/getting-started/example-datasets/wikistat
sidebar_position: 17
sidebar_label: WikiStat
---
# WikiStat {#wikistat}
См: http://dumps.wikimedia.org/other/pagecounts-raw/
Создание таблицы:
``` sql
CREATE TABLE wikistat
(
date Date,
time DateTime,
project String,
subproject String,
path String,
hits UInt64,
size UInt64
) ENGINE = MergeTree(date, (path, time), 8192);
```
Загрузка данных:
``` 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
```

View File

@ -0,0 +1 @@
../../../en/getting-started/example-datasets/wikistat.md

View File

@ -1,32 +0,0 @@
---
slug: /zh/getting-started/example-datasets/wikistat
sidebar_position: 17
sidebar_label: WikiStat
---
# WikiStat {#wikistat}
参考: http://dumps.wikimedia.org/other/pagecounts-raw/
创建表结构:
``` sql
CREATE TABLE wikistat
(
date Date,
time DateTime,
project String,
subproject String,
path String,
hits UInt64,
size UInt64
) ENGINE = MergeTree(date, (path, time), 8192);
```
加载数据:
``` 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
```

View File

@ -0,0 +1 @@
../../../en/getting-started/example-datasets/wikistat.md

View File

@ -577,7 +577,6 @@ String FeatureFlagsCommand::run()
}
return ret.str();
}
}