thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 16:42:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'evillique/nlp' into evillique-nlp

Browse Source
This commit is contained in:
alesapin 2021-07-30 16:46:58 +03:00
commit acc4e9e79d
2 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docker/packager/unbundled/Dockerfile
View File

@ -59,7 +59,6 @@ RUN apt-get update \
libc-ares-dev \
rapidjson-dev \
libsnappy-dev \
libparquet-dev \
libthrift-dev \
libutf8proc-dev \
libbz2-dev \

16
tests/performance/nlp.xml Normal file
View File

@ -0,0 +1,16 @@
<test>
<preconditions>
<table_exists>hits_100m_single</table_exists>
</preconditions>
<create_query>CREATE TABLE hits_100m_words (words Array(String), UserID UInt64) ENGINE Memory</create_query>
<create_query>CREATE TABLE hits_100m_words_ws (words Array(String), UserID UInt64) ENGINE Memory</create_query>
<query>INSERT INTO hits_100m_words SELECT splitByNonAlpha(SearchPhrase) AS words, UserID FROM hits_100m_single WHERE length(words) > 0</query>
<query>INSERT INTO hits_100m_words_ws SELECT splitByWhitespace(SearchPhrase) AS words, UserID FROM hits_100m_single WHERE length(words) > 0</query>
<query>SELECT arrayMap(x -> stem('ru', x), words) FROM hits_100m_words FORMAT Null</query>
<drop_query>DROP TABLE IF EXISTS hits_100m_words</drop_query>
<drop_query>DROP TABLE IF EXISTS hits_100m_words_ws</drop_query>
</test>